@agent-ix/quoin 0.23.1 → 0.26.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +8 -258
- package/bin/launcher.js +138 -0
- package/package.json +22 -123
- package/.agents/plugins/marketplace.json +0 -14
- package/.claude-plugin/marketplace.json +0 -16
- package/.claude-plugin/plugin.json +0 -8
- package/.codex-plugin/plugin.json +0 -27
- package/.github/plugin/marketplace.json +0 -16
- package/bin/quoin.js +0 -21
- package/default-modules.yaml +0 -107
- package/dist/advisor/advise.d.ts +0 -199
- package/dist/advisor/advise.d.ts.map +0 -1
- package/dist/advisor/index.d.ts +0 -10
- package/dist/advisor/index.d.ts.map +0 -1
- package/dist/advisor/methods.d.ts +0 -60
- package/dist/advisor/methods.d.ts.map +0 -1
- package/dist/advisor-B0rESCx1.js +0 -63
- package/dist/assurance/graph.d.ts +0 -87
- package/dist/assurance/graph.d.ts.map +0 -1
- package/dist/assurance/index.d.ts +0 -9
- package/dist/assurance/index.d.ts.map +0 -1
- package/dist/assurance/render.d.ts +0 -3
- package/dist/assurance/render.d.ts.map +0 -1
- package/dist/auditor/audit.d.ts +0 -146
- package/dist/auditor/audit.d.ts.map +0 -1
- package/dist/auditor/combinatorial.d.ts +0 -53
- package/dist/auditor/combinatorial.d.ts.map +0 -1
- package/dist/auditor/index.d.ts +0 -9
- package/dist/auditor/index.d.ts.map +0 -1
- package/dist/auditor-Dd3i9Aqx.js +0 -340
- package/dist/base-gAClyCNd.js +0 -137
- package/dist/base.d.ts +0 -23
- package/dist/base.d.ts.map +0 -1
- package/dist/catalog.d.ts +0 -33
- package/dist/catalog.d.ts.map +0 -1
- package/dist/change-assurance/attestations.d.ts +0 -7
- package/dist/change-assurance/attestations.d.ts.map +0 -1
- package/dist/change-assurance/index.d.ts +0 -14
- package/dist/change-assurance/index.d.ts.map +0 -1
- package/dist/change-assurance/integrity.d.ts +0 -11
- package/dist/change-assurance/integrity.d.ts.map +0 -1
- package/dist/change-assurance/records.d.ts +0 -22
- package/dist/change-assurance/records.d.ts.map +0 -1
- package/dist/change-assurance/schema-assets.d.ts +0 -8
- package/dist/change-assurance/schema-assets.d.ts.map +0 -1
- package/dist/change-assurance/store.d.ts +0 -18
- package/dist/change-assurance/store.d.ts.map +0 -1
- package/dist/change-assurance/types.d.ts +0 -180
- package/dist/change-assurance/types.d.ts.map +0 -1
- package/dist/change-assurance/verify.d.ts +0 -4
- package/dist/change-assurance/verify.d.ts.map +0 -1
- package/dist/change-assurance-CyKLPeKa.js +0 -1236
- package/dist/cli.d.ts +0 -61
- package/dist/cli.d.ts.map +0 -1
- package/dist/cli.js +0 -34
- package/dist/commands/advise.d.ts +0 -16
- package/dist/commands/advise.d.ts.map +0 -1
- package/dist/commands/advise.js +0 -234
- package/dist/commands/assurance.d.ts +0 -14
- package/dist/commands/assurance.d.ts.map +0 -1
- package/dist/commands/assurance.js +0 -204
- package/dist/commands/catalog/index.d.ts +0 -2
- package/dist/commands/catalog/index.d.ts.map +0 -1
- package/dist/commands/catalog/index.js +0 -2
- package/dist/commands/catalog/list.d.ts +0 -11
- package/dist/commands/catalog/list.d.ts.map +0 -1
- package/dist/commands/catalog/list.js +0 -22
- package/dist/commands/catalog/methods.d.ts +0 -12
- package/dist/commands/catalog/methods.d.ts.map +0 -1
- package/dist/commands/catalog/methods.js +0 -43
- package/dist/commands/catalog/show.d.ts +0 -13
- package/dist/commands/catalog/show.d.ts.map +0 -1
- package/dist/commands/catalog/show.js +0 -25
- package/dist/commands/catalog/validate.d.ts +0 -10
- package/dist/commands/catalog/validate.d.ts.map +0 -1
- package/dist/commands/catalog/validate.js +0 -27
- package/dist/commands/change-assurance/common.d.ts +0 -37
- package/dist/commands/change-assurance/common.d.ts.map +0 -1
- package/dist/commands/change-assurance/index.d.ts +0 -8
- package/dist/commands/change-assurance/index.d.ts.map +0 -1
- package/dist/commands/change-assurance/index.js +0 -12
- package/dist/commands/change-assurance/intake.d.ts +0 -15
- package/dist/commands/change-assurance/intake.d.ts.map +0 -1
- package/dist/commands/change-assurance/intake.js +0 -53
- package/dist/commands/change-assurance/receipt.d.ts +0 -21
- package/dist/commands/change-assurance/receipt.d.ts.map +0 -1
- package/dist/commands/change-assurance/receipt.js +0 -99
- package/dist/commands/change-assurance/recover.d.ts +0 -13
- package/dist/commands/change-assurance/recover.d.ts.map +0 -1
- package/dist/commands/change-assurance/recover.js +0 -29
- package/dist/commands/change-assurance/schema.d.ts +0 -13
- package/dist/commands/change-assurance/schema.d.ts.map +0 -1
- package/dist/commands/change-assurance/schema.js +0 -40
- package/dist/commands/change-assurance/seal-attestation.d.ts +0 -15
- package/dist/commands/change-assurance/seal-attestation.d.ts.map +0 -1
- package/dist/commands/change-assurance/seal-attestation.js +0 -58
- package/dist/commands/change-assurance/seal-record.d.ts +0 -14
- package/dist/commands/change-assurance/seal-record.d.ts.map +0 -1
- package/dist/commands/change-assurance/seal-record.js +0 -53
- package/dist/commands/change-assurance/verify-receipt.d.ts +0 -13
- package/dist/commands/change-assurance/verify-receipt.d.ts.map +0 -1
- package/dist/commands/change-assurance/verify-receipt.js +0 -41
- package/dist/commands/completeness.d.ts +0 -16
- package/dist/commands/completeness.d.ts.map +0 -1
- package/dist/commands/completeness.js +0 -49
- package/dist/commands/config/doctor.d.ts +0 -7
- package/dist/commands/config/doctor.d.ts.map +0 -1
- package/dist/commands/config/doctor.js +0 -15
- package/dist/commands/config/edit.d.ts +0 -7
- package/dist/commands/config/edit.d.ts.map +0 -1
- package/dist/commands/config/edit.js +0 -13
- package/dist/commands/config/get.d.ts +0 -11
- package/dist/commands/config/get.d.ts.map +0 -1
- package/dist/commands/config/get.js +0 -20
- package/dist/commands/config/index.d.ts +0 -2
- package/dist/commands/config/index.d.ts.map +0 -1
- package/dist/commands/config/index.js +0 -2
- package/dist/commands/config/set.d.ts +0 -12
- package/dist/commands/config/set.d.ts.map +0 -1
- package/dist/commands/config/set.js +0 -26
- package/dist/commands/evidence/affirm.d.ts +0 -17
- package/dist/commands/evidence/affirm.d.ts.map +0 -1
- package/dist/commands/evidence/affirm.js +0 -65
- package/dist/commands/evidence/audit.d.ts +0 -34
- package/dist/commands/evidence/audit.d.ts.map +0 -1
- package/dist/commands/evidence/audit.js +0 -107
- package/dist/commands/evidence/baseline.d.ts +0 -14
- package/dist/commands/evidence/baseline.d.ts.map +0 -1
- package/dist/commands/evidence/baseline.js +0 -89
- package/dist/commands/evidence/gc.d.ts +0 -13
- package/dist/commands/evidence/gc.d.ts.map +0 -1
- package/dist/commands/evidence/gc.js +0 -35
- package/dist/commands/evidence/index.d.ts +0 -8
- package/dist/commands/evidence/index.d.ts.map +0 -1
- package/dist/commands/evidence/index.js +0 -18
- package/dist/commands/evidence/inspect-mocks.d.ts +0 -16
- package/dist/commands/evidence/inspect-mocks.d.ts.map +0 -1
- package/dist/commands/evidence/inspect-mocks.js +0 -49
- package/dist/commands/evidence/record.d.ts +0 -22
- package/dist/commands/evidence/record.d.ts.map +0 -1
- package/dist/commands/evidence/record.js +0 -144
- package/dist/commands/graph/change-impact.d.ts +0 -16
- package/dist/commands/graph/change-impact.d.ts.map +0 -1
- package/dist/commands/graph/change-impact.js +0 -29
- package/dist/commands/graph/churn.d.ts +0 -14
- package/dist/commands/graph/churn.d.ts.map +0 -1
- package/dist/commands/graph/churn.js +0 -15
- package/dist/commands/graph/common.d.ts +0 -16
- package/dist/commands/graph/common.d.ts.map +0 -1
- package/dist/commands/graph/fan-out.d.ts +0 -14
- package/dist/commands/graph/fan-out.d.ts.map +0 -1
- package/dist/commands/graph/fan-out.js +0 -15
- package/dist/commands/graph/index.d.ts +0 -8
- package/dist/commands/graph/index.d.ts.map +0 -1
- package/dist/commands/graph/index.js +0 -12
- package/dist/commands/matrix.d.ts +0 -14
- package/dist/commands/matrix.d.ts.map +0 -1
- package/dist/commands/matrix.js +0 -15
- package/dist/commands/measurement/index.d.ts +0 -7
- package/dist/commands/measurement/index.d.ts.map +0 -1
- package/dist/commands/measurement/index.js +0 -11
- package/dist/commands/measurement/intervention.d.ts +0 -11
- package/dist/commands/measurement/intervention.d.ts.map +0 -1
- package/dist/commands/measurement/intervention.js +0 -31
- package/dist/commands/measurement/operational-release.d.ts +0 -11
- package/dist/commands/measurement/operational-release.d.ts.map +0 -1
- package/dist/commands/measurement/operational-release.js +0 -31
- package/dist/commands/measurement/record.d.ts +0 -10
- package/dist/commands/measurement/record.d.ts.map +0 -1
- package/dist/commands/measurement/record.js +0 -36
- package/dist/commands/module/ensure-defaults.d.ts +0 -8
- package/dist/commands/module/ensure-defaults.d.ts.map +0 -1
- package/dist/commands/module/ensure-defaults.js +0 -17
- package/dist/commands/module/index.d.ts +0 -2
- package/dist/commands/module/index.d.ts.map +0 -1
- package/dist/commands/module/index.js +0 -2
- package/dist/commands/module/install.d.ts +0 -11
- package/dist/commands/module/install.d.ts.map +0 -1
- package/dist/commands/module/install.js +0 -22
- package/dist/commands/module/list.d.ts +0 -8
- package/dist/commands/module/list.d.ts.map +0 -1
- package/dist/commands/module/list.js +0 -13
- package/dist/commands/module/remove.d.ts +0 -10
- package/dist/commands/module/remove.d.ts.map +0 -1
- package/dist/commands/module/remove.js +0 -16
- package/dist/commands/plugin/deprecation.d.ts +0 -10
- package/dist/commands/plugin/deprecation.d.ts.map +0 -1
- package/dist/commands/plugin/ensure-defaults.d.ts +0 -8
- package/dist/commands/plugin/ensure-defaults.d.ts.map +0 -1
- package/dist/commands/plugin/ensure-defaults.js +0 -12
- package/dist/commands/plugin/index.d.ts +0 -2
- package/dist/commands/plugin/index.d.ts.map +0 -1
- package/dist/commands/plugin/index.js +0 -2
- package/dist/commands/plugin/install.d.ts +0 -8
- package/dist/commands/plugin/install.d.ts.map +0 -1
- package/dist/commands/plugin/install.js +0 -12
- package/dist/commands/plugin/list.d.ts +0 -8
- package/dist/commands/plugin/list.d.ts.map +0 -1
- package/dist/commands/plugin/list.js +0 -12
- package/dist/commands/plugin/remove.d.ts +0 -8
- package/dist/commands/plugin/remove.d.ts.map +0 -1
- package/dist/commands/plugin/remove.js +0 -12
- package/dist/commands/report.d.ts +0 -19
- package/dist/commands/report.d.ts.map +0 -1
- package/dist/commands/report.js +0 -96
- package/dist/commands/review.d.ts +0 -14
- package/dist/commands/review.d.ts.map +0 -1
- package/dist/commands/review.js +0 -15
- package/dist/commands/to-plan.d.ts +0 -14
- package/dist/commands/to-plan.d.ts.map +0 -1
- package/dist/commands/to-plan.js +0 -15
- package/dist/commands/update.d.ts +0 -13
- package/dist/commands/update.d.ts.map +0 -1
- package/dist/commands/update.js +0 -34
- package/dist/commands/validate.d.ts +0 -13
- package/dist/commands/validate.d.ts.map +0 -1
- package/dist/commands/validate.js +0 -123
- package/dist/commands/write.d.ts +0 -16
- package/dist/commands/write.d.ts.map +0 -1
- package/dist/commands/write.js +0 -33
- package/dist/common-B1ZJ8CSO.js +0 -36
- package/dist/common-DTrmnvL-.js +0 -35
- package/dist/completeness/assess.d.ts +0 -82
- package/dist/completeness/assess.d.ts.map +0 -1
- package/dist/completeness/bundle.d.ts +0 -52
- package/dist/completeness/bundle.d.ts.map +0 -1
- package/dist/completeness/declarations.d.ts +0 -46
- package/dist/completeness/declarations.d.ts.map +0 -1
- package/dist/completeness/index.d.ts +0 -11
- package/dist/completeness/index.d.ts.map +0 -1
- package/dist/completeness/run.d.ts +0 -35
- package/dist/completeness/run.d.ts.map +0 -1
- package/dist/completeness-BzBuNq6w.js +0 -228
- package/dist/config-schema-Dp-vlxuR.js +0 -13
- package/dist/config-schema.d.ts +0 -52
- package/dist/config-schema.d.ts.map +0 -1
- package/dist/deprecation-fRxUHoxv.js +0 -4
- package/dist/evidence/adapters/agent-eval.d.ts +0 -26
- package/dist/evidence/adapters/agent-eval.d.ts.map +0 -1
- package/dist/evidence/adapters/audit-script.d.ts +0 -25
- package/dist/evidence/adapters/audit-script.d.ts.map +0 -1
- package/dist/evidence/adapters/cargo-mutants.d.ts +0 -3
- package/dist/evidence/adapters/cargo-mutants.d.ts.map +0 -1
- package/dist/evidence/adapters/contract-conformance.d.ts +0 -16
- package/dist/evidence/adapters/contract-conformance.d.ts.map +0 -1
- package/dist/evidence/adapters/differential-report.d.ts +0 -18
- package/dist/evidence/adapters/differential-report.d.ts.map +0 -1
- package/dist/evidence/adapters/junit.d.ts +0 -17
- package/dist/evidence/adapters/junit.d.ts.map +0 -1
- package/dist/evidence/adapters/registry.d.ts +0 -63
- package/dist/evidence/adapters/registry.d.ts.map +0 -1
- package/dist/evidence/adapters/sarif.d.ts +0 -35
- package/dist/evidence/adapters/sarif.d.ts.map +0 -1
- package/dist/evidence/adapters/sbom.d.ts +0 -35
- package/dist/evidence/adapters/sbom.d.ts.map +0 -1
- package/dist/evidence/adapters/types.d.ts +0 -86
- package/dist/evidence/adapters/types.d.ts.map +0 -1
- package/dist/evidence/index.d.ts +0 -27
- package/dist/evidence/index.d.ts.map +0 -1
- package/dist/evidence/mock-inspection.d.ts +0 -16
- package/dist/evidence/mock-inspection.d.ts.map +0 -1
- package/dist/evidence/record.d.ts +0 -58
- package/dist/evidence/record.d.ts.map +0 -1
- package/dist/evidence/store.d.ts +0 -215
- package/dist/evidence/store.d.ts.map +0 -1
- package/dist/evidence/types.d.ts +0 -281
- package/dist/evidence/types.d.ts.map +0 -1
- package/dist/evidence-OyqpqHLS.js +0 -614
- package/dist/flow-command-CCRTE5Oe.js +0 -88
- package/dist/flow-command.d.ts +0 -25
- package/dist/flow-command.d.ts.map +0 -1
- package/dist/flows.d.ts +0 -7
- package/dist/flows.d.ts.map +0 -1
- package/dist/graph-analysis/analysis.d.ts +0 -106
- package/dist/graph-analysis/analysis.d.ts.map +0 -1
- package/dist/graph-analysis/index.d.ts +0 -6
- package/dist/graph-analysis/index.d.ts.map +0 -1
- package/dist/graph-analysis/input.d.ts +0 -33
- package/dist/graph-analysis/input.d.ts.map +0 -1
- package/dist/graph-analysis/load.d.ts +0 -21
- package/dist/graph-analysis/load.d.ts.map +0 -1
- package/dist/graph-analysis/render.d.ts +0 -4
- package/dist/graph-analysis/render.d.ts.map +0 -1
- package/dist/graph-analysis-IWaoJJSN.js +0 -657
- package/dist/hooks/command-not-found.d.ts +0 -23
- package/dist/hooks/command-not-found.d.ts.map +0 -1
- package/dist/hooks/command-not-found.js +0 -8
- package/dist/index.d.ts +0 -13
- package/dist/index.d.ts.map +0 -1
- package/dist/index.js +0 -12
- package/dist/measurement/agent-eval-intervention.d.ts +0 -6
- package/dist/measurement/agent-eval-intervention.d.ts.map +0 -1
- package/dist/measurement/atomic-file.d.ts +0 -5
- package/dist/measurement/atomic-file.d.ts.map +0 -1
- package/dist/measurement/compare.d.ts +0 -4
- package/dist/measurement/compare.d.ts.map +0 -1
- package/dist/measurement/date-time.d.ts +0 -3
- package/dist/measurement/date-time.d.ts.map +0 -1
- package/dist/measurement/github-release-operational.d.ts +0 -7
- package/dist/measurement/github-release-operational.d.ts.map +0 -1
- package/dist/measurement/graph-adapters.d.ts +0 -304
- package/dist/measurement/graph-adapters.d.ts.map +0 -1
- package/dist/measurement/graph-portfolio-load.d.ts +0 -3
- package/dist/measurement/graph-portfolio-load.d.ts.map +0 -1
- package/dist/measurement/graph-portfolio.d.ts +0 -158
- package/dist/measurement/graph-portfolio.d.ts.map +0 -1
- package/dist/measurement/index.d.ts +0 -22
- package/dist/measurement/index.d.ts.map +0 -1
- package/dist/measurement/intervention-report.d.ts +0 -24
- package/dist/measurement/intervention-report.d.ts.map +0 -1
- package/dist/measurement/intervention-schema.d.ts +0 -144
- package/dist/measurement/intervention-schema.d.ts.map +0 -1
- package/dist/measurement/intervention-types.d.ts +0 -105
- package/dist/measurement/intervention-types.d.ts.map +0 -1
- package/dist/measurement/intervention.d.ts +0 -16
- package/dist/measurement/intervention.d.ts.map +0 -1
- package/dist/measurement/operational-report.d.ts +0 -17
- package/dist/measurement/operational-report.d.ts.map +0 -1
- package/dist/measurement/operational-schema.d.ts +0 -461
- package/dist/measurement/operational-schema.d.ts.map +0 -1
- package/dist/measurement/operational-types.d.ts +0 -121
- package/dist/measurement/operational-types.d.ts.map +0 -1
- package/dist/measurement/operational.d.ts +0 -13
- package/dist/measurement/operational.d.ts.map +0 -1
- package/dist/measurement/plans.d.ts +0 -6
- package/dist/measurement/plans.d.ts.map +0 -1
- package/dist/measurement/portfolio.d.ts +0 -54
- package/dist/measurement/portfolio.d.ts.map +0 -1
- package/dist/measurement/profiles.d.ts +0 -9
- package/dist/measurement/profiles.d.ts.map +0 -1
- package/dist/measurement/report.d.ts +0 -48
- package/dist/measurement/report.d.ts.map +0 -1
- package/dist/measurement/schemas/operational-evidence-v1.schema.json.d.ts +0 -384
- package/dist/measurement/store.d.ts +0 -14
- package/dist/measurement/store.d.ts.map +0 -1
- package/dist/measurement/types.d.ts +0 -85
- package/dist/measurement/types.d.ts.map +0 -1
- package/dist/measurement/validate.d.ts +0 -9
- package/dist/measurement/validate.d.ts.map +0 -1
- package/dist/measurement-j8sDSqx5.js +0 -2980
- package/dist/modules-DDQkKC4l.js +0 -23
- package/dist/modules.d.ts +0 -10
- package/dist/modules.d.ts.map +0 -1
- package/dist/org.d.ts +0 -61
- package/dist/org.d.ts.map +0 -1
- package/dist/plugins-CHpYhpEI.js +0 -77
- package/dist/plugins.d.ts +0 -13
- package/dist/plugins.d.ts.map +0 -1
- package/dist/quire/assurance.d.ts +0 -109
- package/dist/quire/assurance.d.ts.map +0 -1
- package/dist/quire/contract.d.ts +0 -88
- package/dist/quire/contract.d.ts.map +0 -1
- package/dist/quire/exec.d.ts +0 -66
- package/dist/quire/exec.d.ts.map +0 -1
- package/dist/quire/index.d.ts +0 -13
- package/dist/quire/index.d.ts.map +0 -1
- package/dist/quire/types.d.ts +0 -415
- package/dist/quire/types.d.ts.map +0 -1
- package/dist/quire/validate.d.ts +0 -39
- package/dist/quire/validate.d.ts.map +0 -1
- package/dist/quire-BsVj1xIR.js +0 -4968
- package/dist/schema-assets-HZWo_iFN.js +0 -233
- package/dist/schemas/assurance-v1.schema.json +0 -225
- package/dist/schemas/change-assurance-record-v1.schema.json +0 -234
- package/dist/schemas/coverage-v1.schema.json +0 -1111
- package/dist/schemas/operational-evidence-v1.schema.json +0 -381
- package/dist/schemas/proof-attestation-v1.schema.json +0 -96
- package/dist/schemas/properties-v1.schema.json +0 -159
- package/dist/schemas/verification-receipt-v1.schema.json +0 -208
- package/dist/validators/gates.d.ts +0 -18
- package/dist/validators/gates.d.ts.map +0 -1
- package/dist/validators/index.d.ts +0 -2
- package/dist/validators/index.d.ts.map +0 -1
- package/dist/version-CMxMIh5g.js +0 -17
- package/dist/version.d.ts +0 -3
- package/dist/version.d.ts.map +0 -1
- package/dist/write-CGTI0dRO.js +0 -157
- package/dist/write.d.ts +0 -28
- package/dist/write.d.ts.map +0 -1
- package/skills/assurance-status-report/SKILL.md +0 -135
- package/skills/assurance-status-report/references/report-contract.md +0 -110
- package/skills/gap-analysis/SKILL.md +0 -111
- package/skills/gap-analysis/references/step-1-target-selection.md +0 -53
- package/skills/gap-analysis/references/step-2-plan-completion.md +0 -49
- package/skills/gap-analysis/references/step-3-matrix-verification.md +0 -147
- package/skills/gap-analysis/references/step-4-underspecified-code.md +0 -92
- package/skills/gap-analysis/references/step-5-semantic-review.md +0 -51
- package/skills/gap-analysis/references/step-6-specreview-artifact.md +0 -108
- package/skills/spec-app-review/SKILL.md +0 -51
- package/skills/spec-app-review/references/checklist.md +0 -197
- package/skills/spec-architecture-evaluation/SKILL.md +0 -30
- package/skills/spec-correctness/SKILL.md +0 -96
- package/skills/spec-correctness/assets/strategy-table.md +0 -101
- package/skills/spec-correctness/assets/templates/fast-check.ts.md +0 -169
- package/skills/spec-correctness/assets/templates/hypothesis.py.md +0 -156
- package/skills/spec-correctness/assets/templates/proptest.rs.md +0 -147
- package/skills/spec-correctness/references/step-0-scope-and-harness.md +0 -94
- package/skills/spec-correctness/references/step-1-census.md +0 -53
- package/skills/spec-correctness/references/step-2-clause-grounding.md +0 -159
- package/skills/spec-correctness/references/step-3-strategy-selection.md +0 -85
- package/skills/spec-correctness/references/step-4-generate-tests.md +0 -117
- package/skills/spec-correctness/references/step-5-second-pass.md +0 -81
- package/skills/spec-correctness/references/step-6-review-artifact.md +0 -134
- package/skills/spec-correctness/references/step-7-report-and-handoff.md +0 -102
- package/skills/spec-dependency-analysis/SKILL.md +0 -90
- package/skills/spec-ears-analysis/SKILL.md +0 -102
- package/skills/spec-evidence-analysis/SKILL.md +0 -156
- package/skills/spec-failure-domain-analysis/SKILL.md +0 -59
- package/skills/spec-fuzz/SKILL.md +0 -133
- package/skills/spec-fuzz/assets/templates/atheris.py.md +0 -74
- package/skills/spec-fuzz/assets/templates/cargo-fuzz.rs.md +0 -83
- package/skills/spec-fuzz/assets/templates/fast-check.ts.md +0 -76
- package/skills/spec-fuzz/references/step-0-scope-and-harness.md +0 -51
- package/skills/spec-fuzz/references/step-1-select-obligations.md +0 -47
- package/skills/spec-fuzz/references/step-2-ground-entry-point.md +0 -55
- package/skills/spec-fuzz/references/step-3-emit-targets.md +0 -65
- package/skills/spec-fuzz/references/step-4-report.md +0 -56
- package/skills/spec-ideation/SKILL.md +0 -46
- package/skills/spec-integrity-analysis/SKILL.md +0 -62
- package/skills/spec-matrix/SKILL.md +0 -186
- package/skills/spec-matrix/assets/test-cases/TC-001.md +0 -35
- package/skills/spec-matrix/assets/test-cases/TC-002.md +0 -37
- package/skills/spec-matrix/assets/test-cases/TC-006.md +0 -50
- package/skills/spec-matrix/assets/test-matrix-example.md +0 -104
- package/skills/spec-matrix/assets/test-matrix-template.md +0 -123
- package/skills/spec-matrix/workflow-assets/dist/index.d.ts +0 -146
- package/skills/spec-matrix/workflow-assets/dist/index.d.ts.map +0 -1
- package/skills/spec-matrix/workflow-assets/dist/index.js +0 -7525
- package/skills/spec-matrix/workflow-assets/dist/invariants.d.ts +0 -6
- package/skills/spec-matrix/workflow-assets/dist/invariants.d.ts.map +0 -1
- package/skills/spec-matrix/workflow-assets/skills/matrix/SKILL.md +0 -35
- package/skills/spec-matrix/workflow-assets/skills/matrix/scripts/invariants.js +0 -1
- package/skills/spec-matrix/workflow-assets/skills/matrix/templates/report/default.md +0 -30
- package/skills/spec-matrix/workflow-assets/skills/matrix/workflows/matrix/def.yaml +0 -82
- package/skills/spec-object-review/SKILL.md +0 -125
- package/skills/spec-object-review/references/object-type-guide.md +0 -118
- package/skills/spec-review/SKILL.md +0 -92
- package/skills/spec-review/references/checklist.md +0 -50
- package/skills/spec-review/workflow-assets/dist/index.d.ts +0 -146
- package/skills/spec-review/workflow-assets/dist/index.d.ts.map +0 -1
- package/skills/spec-review/workflow-assets/dist/index.js +0 -7525
- package/skills/spec-review/workflow-assets/dist/invariants.d.ts +0 -6
- package/skills/spec-review/workflow-assets/dist/invariants.d.ts.map +0 -1
- package/skills/spec-review/workflow-assets/skills/review/SKILL.md +0 -96
- package/skills/spec-review/workflow-assets/skills/review/scripts/invariants.js +0 -61
- package/skills/spec-review/workflow-assets/skills/review/workflows/review/def.yaml +0 -68
- package/skills/spec-risk-complexity-analysis/SKILL.md +0 -92
- package/skills/spec-scope-boundary-analysis/SKILL.md +0 -101
- package/skills/spec-security-analysis/SKILL.md +0 -84
- package/skills/spec-security-analysis/assets/security-analysis-example.md +0 -89
- package/skills/spec-security-analysis/assets/security-analysis-template.md +0 -73
- package/skills/spec-security-analysis/references/component-type-mapping.md +0 -161
- package/skills/spec-security-analysis/references/gdpr/ChII-Principles.md +0 -58
- package/skills/spec-security-analysis/references/gdpr/ChIII-DataSubjectRights.md +0 -84
- package/skills/spec-security-analysis/references/gdpr/ChIV-ControllerProcessor.md +0 -83
- package/skills/spec-security-analysis/references/gdpr/ChV-DataTransfers.md +0 -62
- package/skills/spec-security-analysis/references/gdpr/index.md +0 -54
- package/skills/spec-security-analysis/references/iso27001/A5-OrganizationalControls.md +0 -64
- package/skills/spec-security-analysis/references/iso27001/A6-PeopleControls.md +0 -30
- package/skills/spec-security-analysis/references/iso27001/A7-PhysicalControls.md +0 -35
- package/skills/spec-security-analysis/references/iso27001/A8-TechnologicalControls.md +0 -66
- package/skills/spec-security-analysis/references/iso27001/index.md +0 -43
- package/skills/spec-security-analysis/references/nist-800-53/AC-AccessControl.md +0 -57
- package/skills/spec-security-analysis/references/nist-800-53/AU-AuditAccountability.md +0 -49
- package/skills/spec-security-analysis/references/nist-800-53/CM-ConfigurationManagement.md +0 -36
- package/skills/spec-security-analysis/references/nist-800-53/IA-IdentificationAuthentication.md +0 -44
- package/skills/spec-security-analysis/references/nist-800-53/SA-SystemServicesAcquisition.md +0 -50
- package/skills/spec-security-analysis/references/nist-800-53/SC-SystemCommunications.md +0 -53
- package/skills/spec-security-analysis/references/nist-800-53/SI-SystemInformationIntegrity.md +0 -52
- package/skills/spec-security-analysis/references/nist-800-53/index.md +0 -58
- package/skills/spec-security-analysis/references/owasp-asvs/V1-Architecture.md +0 -33
- package/skills/spec-security-analysis/references/owasp-asvs/V10-MaliciousCode.md +0 -33
- package/skills/spec-security-analysis/references/owasp-asvs/V11-BusinessLogic.md +0 -32
- package/skills/spec-security-analysis/references/owasp-asvs/V12-Files.md +0 -34
- package/skills/spec-security-analysis/references/owasp-asvs/V13-API.md +0 -34
- package/skills/spec-security-analysis/references/owasp-asvs/V14-Configuration.md +0 -35
- package/skills/spec-security-analysis/references/owasp-asvs/V2-Authentication.md +0 -36
- package/skills/spec-security-analysis/references/owasp-asvs/V3-SessionManagement.md +0 -35
- package/skills/spec-security-analysis/references/owasp-asvs/V4-AccessControl.md +0 -39
- package/skills/spec-security-analysis/references/owasp-asvs/V5-Validation.md +0 -37
- package/skills/spec-security-analysis/references/owasp-asvs/V6-Cryptography.md +0 -34
- package/skills/spec-security-analysis/references/owasp-asvs/V7-ErrorLogging.md +0 -37
- package/skills/spec-security-analysis/references/owasp-asvs/V8-DataProtection.md +0 -34
- package/skills/spec-security-analysis/references/owasp-asvs/V9-Communication.md +0 -32
- package/skills/spec-security-analysis/references/owasp-asvs/index.md +0 -59
- package/skills/spec-security-analysis/references/soc2/CC1-ControlEnvironment.md +0 -31
- package/skills/spec-security-analysis/references/soc2/CC2-CommunicationInformation.md +0 -27
- package/skills/spec-security-analysis/references/soc2/CC3-RiskAssessment.md +0 -29
- package/skills/spec-security-analysis/references/soc2/CC4-MonitoringActivities.md +0 -27
- package/skills/spec-security-analysis/references/soc2/CC5-ControlActivities.md +0 -28
- package/skills/spec-security-analysis/references/soc2/CC6-LogicalPhysicalAccess.md +0 -45
- package/skills/spec-security-analysis/references/soc2/CC7-SystemOperations.md +0 -42
- package/skills/spec-security-analysis/references/soc2/CC8-ChangeManagement.md +0 -32
- package/skills/spec-security-analysis/references/soc2/CC9-RiskMitigation.md +0 -34
- package/skills/spec-security-analysis/references/soc2/index.md +0 -46
- package/skills/spec-security-analysis/references/standards-index.md +0 -46
- package/skills/spec-to-plan/SKILL.md +0 -88
- package/skills/spec-to-plan/references/step-0-plan-selection.md +0 -121
- package/skills/spec-to-plan/references/step-1-analysis.md +0 -88
- package/skills/spec-to-plan/references/step-2-test-plan.md +0 -43
- package/skills/spec-to-plan/references/step-3-execution-plan.md +0 -218
- package/skills/spec-to-plan/workflow-assets/dist/index.d.ts +0 -146
- package/skills/spec-to-plan/workflow-assets/dist/index.d.ts.map +0 -1
- package/skills/spec-to-plan/workflow-assets/dist/index.js +0 -7525
- package/skills/spec-to-plan/workflow-assets/dist/invariants.d.ts +0 -6
- package/skills/spec-to-plan/workflow-assets/dist/invariants.d.ts.map +0 -1
- package/skills/spec-to-plan/workflow-assets/skills/to-plan/SKILL.md +0 -35
- package/skills/spec-to-plan/workflow-assets/skills/to-plan/scripts/invariants.js +0 -1
- package/skills/spec-to-plan/workflow-assets/skills/to-plan/templates/implementation-plan/default.md +0 -44
- package/skills/spec-to-plan/workflow-assets/skills/to-plan/workflows/to-plan/def.yaml +0 -85
- package/skills/specify/SKILL.md +0 -154
- package/skills/specify/assets/app-spec-template.md +0 -143
- package/skills/specify/assets/spec-template.md +0 -299
- package/skills/specify/references/integration-tests.md +0 -72
- package/skills/specify/references/us-to-fr.md +0 -40
- package/skills/specify/references/writing-good-requirements.md +0 -61
|
@@ -1,110 +0,0 @@
|
|
|
1
|
-
# Assurance status report contract
|
|
2
|
-
|
|
3
|
-
Use this contract for a detailed report. Short status requests may compress
|
|
4
|
-
sections, but they retain the same evidence and comparison rules.
|
|
5
|
-
|
|
6
|
-
## Evidence states
|
|
7
|
-
|
|
8
|
-
- **Proven:** Direct current or retained evidence satisfies the requirement.
|
|
9
|
-
- **Contradicted:** Direct evidence shows the requirement is not satisfied.
|
|
10
|
-
- **Incomplete:** Some required evidence exists, but the full requirement is not
|
|
11
|
-
demonstrated.
|
|
12
|
-
- **Missing:** No authoritative evidence was found.
|
|
13
|
-
- **Incomparable:** Values exist, but their definitions or populations do not
|
|
14
|
-
permit a numeric delta.
|
|
15
|
-
|
|
16
|
-
Never turn incomplete, missing, or incomparable evidence into zero, green, or
|
|
17
|
-
complete.
|
|
18
|
-
|
|
19
|
-
## Required order
|
|
20
|
-
|
|
21
|
-
### 1. Executive status
|
|
22
|
-
|
|
23
|
-
Name the goal, current disposition, as-of time and timezone, current promoted
|
|
24
|
-
revision, scope boundary, and progress method. Distinguish completion of the
|
|
25
|
-
named phase from progress of the larger program.
|
|
26
|
-
|
|
27
|
-
### 2. Definitions
|
|
28
|
-
|
|
29
|
-
Define each project-specific term before the metrics table. Definitions cite the
|
|
30
|
-
active versioned contract. Prefer plain language, then state the exact counting
|
|
31
|
-
rule where it matters.
|
|
32
|
-
|
|
33
|
-
Examples of distinctions that must remain visible:
|
|
34
|
-
|
|
35
|
-
- localization identifies the correct place; it does not prove the explanation
|
|
36
|
-
or remedy is correct;
|
|
37
|
-
- actionability-field presence does not prove guidance correctness;
|
|
38
|
-
- safe refusal preserves uncertainty and does not count as an exact span;
|
|
39
|
-
- a controlled-corpus result does not estimate ecosystem-wide precision; and
|
|
40
|
-
- a closed ticket does not by itself prove its acceptance criteria.
|
|
41
|
-
|
|
42
|
-
### 3. Metric progression
|
|
43
|
-
|
|
44
|
-
Use a table with these conceptual columns:
|
|
45
|
-
|
|
46
|
-
| Metric | Baseline | Intermediate | Current | Delta | Comparability | Evidence |
|
|
47
|
-
| --- | --- | --- | --- | --- | --- | --- |
|
|
48
|
-
|
|
49
|
-
Every ratio displays `matched/examined` beside the percentage. Each row retains
|
|
50
|
-
the metric definition version and population identity, either inline or in its
|
|
51
|
-
evidence link. Use `—` for a deliberately absent intermediate snapshot and
|
|
52
|
-
`not_computed: REASON` for an unavailable value.
|
|
53
|
-
|
|
54
|
-
Do not calculate a delta when:
|
|
55
|
-
|
|
56
|
-
- the definition version changed;
|
|
57
|
-
- the applicable population was redefined;
|
|
58
|
-
- the source or corpus identity cannot be proved;
|
|
59
|
-
- either value is not computed; or
|
|
60
|
-
- a producer or required capability changed without an accepted comparison.
|
|
61
|
-
|
|
62
|
-
When the population merely grows under the same contract, report both the count
|
|
63
|
-
change and the rate change. A rate decline with a larger numerator can be scope
|
|
64
|
-
growth rather than a product regression; explain which occurred.
|
|
65
|
-
|
|
66
|
-
### 4. Completed work
|
|
67
|
-
|
|
68
|
-
Enumerate every in-scope ticket/task with title, repository, final state, delivery
|
|
69
|
-
PR or commit, and the evidence that proves acceptance. Group by workstream when
|
|
70
|
-
the list is long. Separately enumerate promotion PRs and exact merge commits.
|
|
71
|
-
|
|
72
|
-
### 5. Open work
|
|
73
|
-
|
|
74
|
-
Enumerate unresolved items and assign exactly one disposition:
|
|
75
|
-
|
|
76
|
-
- **blocking:** prevents the named goal;
|
|
77
|
-
- **non-blocking:** retained limitation that does not prevent this goal;
|
|
78
|
-
- **downstream:** belongs to a later goal or phase;
|
|
79
|
-
- **excluded:** explicitly outside the user's scope; or
|
|
80
|
-
- **unknown:** relationship or impact is not proven.
|
|
81
|
-
|
|
82
|
-
Do not omit open work merely because the named phase is complete.
|
|
83
|
-
|
|
84
|
-
### 6. Drift controls
|
|
85
|
-
|
|
86
|
-
Report the guard and its proof for each relevant drift class: repository,
|
|
87
|
-
submodule, tool/engine, executable bytes, package resolution, toolchain, workflow
|
|
88
|
-
action, container, schema, configuration, corpus, metric definition, evidence
|
|
89
|
-
overlay, and promotion topology. Distinguish a guard observed in code from a
|
|
90
|
-
mutation test proving it fails before governed execution.
|
|
91
|
-
|
|
92
|
-
### 7. Limitations and judgment
|
|
93
|
-
|
|
94
|
-
State remaining evidence limitations, then answer whether the effort is moving
|
|
95
|
-
toward the goal and why. Use one of:
|
|
96
|
-
|
|
97
|
-
- **complete** — every requirement is proven and no in-scope work remains;
|
|
98
|
-
- **on track** — incomplete, with no current blocking contradiction;
|
|
99
|
-
- **at risk** — progress exists, but a named unresolved risk threatens the goal;
|
|
100
|
-
- **blocked** — a named blocker prevents meaningful progress; or
|
|
101
|
-
- **not started** — no implementation evidence exists.
|
|
102
|
-
|
|
103
|
-
Close with the next decision or evidence-gathering point. Do not suggest starting
|
|
104
|
-
explicitly excluded work.
|
|
105
|
-
|
|
106
|
-
## Read-only rule
|
|
107
|
-
|
|
108
|
-
Producing the report does not authorize ticket comments, issue state changes,
|
|
109
|
-
branch updates, evidence regeneration, baseline updates, or new external
|
|
110
|
-
messages. Ask separately before any such mutation.
|
|
@@ -1,111 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: gap-analysis
|
|
3
|
-
description: Verify a targeted plan is complete and validated — every task done, the Test
|
|
4
|
-
Matrix backed by real tracking tags in tests, and code fully traced to spec (flagging
|
|
5
|
-
underspecified code with no owning requirement). Optional semantic review checks that
|
|
6
|
-
intent↔test↔code actually agree. Emits a quire-validated SpecReview artifact to
|
|
7
|
-
reviews/YY-MM-DD-<slug>.md.
|
|
8
|
-
---
|
|
9
|
-
|
|
10
|
-
# Gap Analysis
|
|
11
|
-
|
|
12
|
-
Use this skill as a **post-implementation verification gate** for one targeted plan.
|
|
13
|
-
It answers three questions and, on request, a fourth:
|
|
14
|
-
|
|
15
|
-
1. **Is the plan done?** Every `Task` in the targeted plan bundle is `status: done`.
|
|
16
|
-
2. **Is the Test Matrix real?** Every Test Case in the matrix is backed by an actual test
|
|
17
|
-
carrying a matching **tracking tag** (`TC-xxx`, `FR-xxx-AC-x`) in the test code.
|
|
18
|
-
3. **Is anything unspecified?** Code/behavior exists with **no owning** StR/US/FR/NFR
|
|
19
|
-
(the reverse, code→spec gap).
|
|
20
|
-
4. **(optional) Does intent match reality?** For each requirement↔test↔code triple — does
|
|
21
|
-
the test validate the requirement's *intent*, does the test actually exercise the code,
|
|
22
|
-
and does the code match the requirement's intent.
|
|
23
|
-
|
|
24
|
-
The result is a single **quire-validated `SpecReview`** document (`analysis: gap-analysis`)
|
|
25
|
-
written to `reviews/YY-MM-DD-<slug>.md`, with a **Verdict** (PASS / CONDITIONAL / FAIL)
|
|
26
|
-
and a validated **Findings** table.
|
|
27
|
-
|
|
28
|
-
## When to use
|
|
29
|
-
|
|
30
|
-
- After `implement-plan` (or any implementation effort) to confirm a plan is genuinely
|
|
31
|
-
complete and verified before closing it.
|
|
32
|
-
- To audit drift between spec, tests, and code for an existing component.
|
|
33
|
-
- As a release/merge gate that produces a durable, traceable review artifact.
|
|
34
|
-
|
|
35
|
-
This skill is **read-only over the codebase** — it inspects and reports; it does not fix
|
|
36
|
-
code, edit the plan, or change the matrix. Its only write is the SpecReview artifact.
|
|
37
|
-
|
|
38
|
-
## Inputs
|
|
39
|
-
|
|
40
|
-
- A target **plan bundle** `plan/<Plan-id>-<slug>/` (the user may name it; otherwise pick).
|
|
41
|
-
- The component **spec** (`spec/spec.md` for `org`/`name`) and **Test Matrix**
|
|
42
|
-
(`spec/matrix.md` or `spec/tests.md`).
|
|
43
|
-
- The **source** and **test** trees of the component.
|
|
44
|
-
|
|
45
|
-
## Steps
|
|
46
|
-
|
|
47
|
-
0. **[Target selection](references/step-1-target-selection.md)**: Resolve the plan bundle,
|
|
48
|
-
spec root, Test Matrix, and `org`/`component` for `ix://` URIs.
|
|
49
|
-
1. **[Plan completion](references/step-2-plan-completion.md)**: Assert every `Task` is
|
|
50
|
-
`done`; report incomplete/blocked tasks and stale `plan.md` checkboxes.
|
|
51
|
-
2. **[Matrix verification](references/step-3-matrix-verification.md)**: Run
|
|
52
|
-
`quire coverage --scope <root> --json` and interpret the report — unbacked rows, status
|
|
53
|
-
lies, untracked tests, and the backed/total rollup. The reconciliation is the engine's;
|
|
54
|
-
the severity and the verdict stay here. A repo whose module set declares no
|
|
55
|
-
`traceability:` model falls back to a grep index, declared as such.
|
|
56
|
-
3. **[Underspecified code](references/step-4-underspecified-code.md)**: Find code/behavior
|
|
57
|
-
with no owning requirement (reverse gap), plus stubs masquerading as complete.
|
|
58
|
-
4. **[Semantic review](references/step-5-semantic-review.md)** *(OPTIONAL — ask first)*:
|
|
59
|
-
Judge intent↔test↔code agreement per requirement. Skip unless the user opts in.
|
|
60
|
-
5. **[SpecReview artifact](references/step-6-specreview-artifact.md)**: Write and validate
|
|
61
|
-
the `SpecReview` to `reviews/YY-MM-DD-<slug>.md`.
|
|
62
|
-
|
|
63
|
-
All steps required except Step 4, which is gated on user choice.
|
|
64
|
-
|
|
65
|
-
> **`--scope` is the repository root, and must be passed explicitly.** Since quire-cli
|
|
66
|
-
> v0.16.0 (quire-rs CR-045) the command derives **two roots** from it and never
|
|
67
|
-
> interchanges them: spec documents are read from `<repo>/spec` only, trace tags from
|
|
68
|
-
> the source tree at `<repo>` excluding `spec/`. A repo with no `spec/` exits with a
|
|
69
|
-
> diagnostic naming the missing document root rather than scanning the whole tree, and a
|
|
70
|
-
> matrix outside `spec/` (a fixture, a `plan/` copy) mints nothing. A relative glob
|
|
71
|
-
> resolves under `--scope` only in scoped mode (no `--module`); with `--module` it
|
|
72
|
-
> resolves against the process working directory, and an omitted `--scope` defaults to
|
|
73
|
-
> `.` — so a run launched from a parent directory validates the **wrong tree** and exits
|
|
74
|
-
> 0 for whatever it matched. Check `quire --version` ≥ 0.16.0 before relying on any of
|
|
75
|
-
> this; ≤ 0.15.0 has the pre-split traversal semantics.
|
|
76
|
-
|
|
77
|
-
## The optional semantic review
|
|
78
|
-
|
|
79
|
-
Steps 1–3 are mechanical and cheap. Step 4 is an expensive, judgment-heavy LLM pass.
|
|
80
|
-
**Before running it**, ask the user explicitly (e.g. with a yes/no choice):
|
|
81
|
-
|
|
82
|
-
> Run the optional semantic review (intent↔test↔code)? It's slower but verifies that tests
|
|
83
|
-
> actually validate requirement intent and exercise real code.
|
|
84
|
-
|
|
85
|
-
If yes, fan the work out (one subagent per FR or per area) for thoroughness. If no, note in
|
|
86
|
-
the SpecReview's Coverage section that semantic review was skipped.
|
|
87
|
-
|
|
88
|
-
## Output
|
|
89
|
-
|
|
90
|
-
A `SpecReview` (`spec-artifacts-process` archetype) at `<project_root>/reviews/YY-MM-DD-<slug>.md`:
|
|
91
|
-
|
|
92
|
-
- Frontmatter `type: SpecReview`, `analysis: gap-analysis`, `id: SR-NNN`, `scope`,
|
|
93
|
-
`review_set: subset`, and `relationships:` (`reviews` → the plan, `references` → the matrix).
|
|
94
|
-
- Body: `## Summary`, `## Verdict` (PASS/CONDITIONAL/FAIL), `## Findings`
|
|
95
|
-
(validated table `ID | Severity | Summary | Refs`), `## Coverage` (rollup).
|
|
96
|
-
|
|
97
|
-
> **Note:** `reviews/` is at the **repo root** by deliberate choice for this skill, not
|
|
98
|
-
> `spec/reviews/`. quire validation is path-agnostic, so this is fine.
|
|
99
|
-
|
|
100
|
-
Validate before finishing:
|
|
101
|
-
|
|
102
|
-
```
|
|
103
|
-
quire validate --scope <project_root> "reviews/**/*.md"
|
|
104
|
-
```
|
|
105
|
-
|
|
106
|
-
## Verdict rule
|
|
107
|
-
|
|
108
|
-
- **FAIL** — any incomplete/blocked task, any matrix Test Case with no backing tagged test,
|
|
109
|
-
or any `high`-severity finding.
|
|
110
|
-
- **CONDITIONAL** — only `medium`/`low` findings (e.g. untracked tests, minor drift).
|
|
111
|
-
- **PASS** — no gaps; record the single `FND-001 | low | No gaps found | -` row.
|
|
@@ -1,53 +0,0 @@
|
|
|
1
|
-
# Step 1: Target Selection
|
|
2
|
-
|
|
3
|
-
**Goal**: Resolve exactly what this run audits — one plan bundle, its spec, its Test
|
|
4
|
-
Matrix — and the `ix://` identity used in the output artifact.
|
|
5
|
-
|
|
6
|
-
## Process
|
|
7
|
-
|
|
8
|
-
### 1. Resolve the target plan
|
|
9
|
-
|
|
10
|
-
Mirror `spec-to-plan/references/step-0-plan-selection.md`:
|
|
11
|
-
|
|
12
|
-
1. **Named in context?** If the user passed a plan id (`Plan-002`) or one was established
|
|
13
|
-
earlier this session, use it.
|
|
14
|
-
2. **Otherwise discover.** Glob `plan/*/plan.md`, read each frontmatter `id`/`title`/`status`,
|
|
15
|
-
and present the list:
|
|
16
|
-
|
|
17
|
-
```
|
|
18
|
-
Plans available to gap-analyze:
|
|
19
|
-
- Plan-001 electron-hello core app (active)
|
|
20
|
-
- Plan-002 packaging & distribution (active)
|
|
21
|
-
```
|
|
22
|
-
|
|
23
|
-
Ask which one. One run targets **one** bundle.
|
|
24
|
-
|
|
25
|
-
### 2. Locate the spec and Test Matrix
|
|
26
|
-
|
|
27
|
-
- **Spec root.** Single-repo: `spec/`. Multi-repo: `specs/<category>/<component>/spec/`.
|
|
28
|
-
- **`org` / `component`.** Read from `spec/spec.md` frontmatter (`org`, `name`). These build
|
|
29
|
-
the `ix://<org>/<component>/<id>` URIs used in the SpecReview `relationships:`.
|
|
30
|
-
- **Test Matrix.** Look for `spec/matrix.md` first, then `spec/tests.md` (both names are in
|
|
31
|
-
use across the ecosystem). Note its frontmatter `id` (e.g. `TestMatrix-001` / `TM-001`)
|
|
32
|
-
for the `references` edge.
|
|
33
|
-
- **Requirements.** Note the requirement files under `spec/functional/`,
|
|
34
|
-
`spec/non-functional/`, `spec/usecase/`, `spec/stakeholder/` — Steps 3 and 4 trace against
|
|
35
|
-
these ids.
|
|
36
|
-
- **Source / test trees.** Identify where implementation and tests live (e.g. `src/` +
|
|
37
|
-
`tests/`, or language-specific layout). Used in Steps 2–4.
|
|
38
|
-
|
|
39
|
-
### 3. Hand off
|
|
40
|
-
|
|
41
|
-
State explicitly, so later steps and the artifact agree:
|
|
42
|
-
|
|
43
|
-
- target bundle path (e.g. `plan/Plan-002-packaging-distribution/`)
|
|
44
|
-
- spec root, matrix path + id
|
|
45
|
-
- `ix://<org>/<component>` prefix
|
|
46
|
-
- where source and tests live
|
|
47
|
-
|
|
48
|
-
## Notes
|
|
49
|
-
|
|
50
|
-
- If there is **no** plan bundle, stop and tell the user — gap-analysis audits a plan; it
|
|
51
|
-
does not invent one (use `spec-to-plan` first).
|
|
52
|
-
- If there is **no** Test Matrix, Step 2 a/Plan checks still run, but record a `high`
|
|
53
|
-
finding that the matrix is missing and Step 3 cannot verify coverage.
|
|
@@ -1,49 +0,0 @@
|
|
|
1
|
-
# Step 2: Plan Completion
|
|
2
|
-
|
|
3
|
-
**Goal**: Confirm every unit of work in the targeted plan is actually finished.
|
|
4
|
-
|
|
5
|
-
## The Task contract
|
|
6
|
-
|
|
7
|
-
Tasks in the bundle are frontmatter-typed (`type: Task`). The machine contract
|
|
8
|
-
(see `quoin/skills/spec-to-plan/SKILL.md`):
|
|
9
|
-
|
|
10
|
-
```yaml
|
|
11
|
-
---
|
|
12
|
-
id: Task-001
|
|
13
|
-
type: Task
|
|
14
|
-
status: not_started | in_progress | blocked | done
|
|
15
|
-
track: A | B | C | S | J | <gate-name>
|
|
16
|
-
priority: P0 | P1 | P2 | P3
|
|
17
|
-
relationships:
|
|
18
|
-
- { target: "ix://org/component/Task-000", type: depends_on }
|
|
19
|
-
- { target: "ix://org/component/FR-002", type: references } # requirement ownership
|
|
20
|
-
- { target: "ix://org/component/TC-004", type: verifies } # test-case trace
|
|
21
|
-
---
|
|
22
|
-
```
|
|
23
|
-
|
|
24
|
-
## Process
|
|
25
|
-
|
|
26
|
-
1. **Enumerate tasks.** Read every `plan/<Plan-id>-<slug>/tasks/Task-*.md`.
|
|
27
|
-
2. **Assert completion.** For each task, check `status`:
|
|
28
|
-
- `done` → OK.
|
|
29
|
-
- `not_started` / `in_progress` / `blocked` → **finding**. Severity:
|
|
30
|
-
- `high` if `priority: P0`/`P1` or it is on the critical path (`track: A`/`S`).
|
|
31
|
-
- `medium` otherwise. `blocked` → note the blocker (its unmet `depends_on`).
|
|
32
|
-
3. **Check dependency sanity.** Flag a `done` task whose `depends_on` target is **not**
|
|
33
|
-
`done` (out-of-order completion) as a `medium` finding.
|
|
34
|
-
4. **Cross-check `plan.md` checkboxes.** `plan.md` mirrors requirements/tests as
|
|
35
|
-
`- [ ]` / `- [x]`. Flag (`low`) any checkbox state that contradicts task status
|
|
36
|
-
(e.g. an unchecked requirement whose owning task is `done`, or vice-versa) — the plan
|
|
37
|
-
doc is drifting from its tasks.
|
|
38
|
-
5. **Record the rollup.** Count tasks `done` / total — feeds the SpecReview `## Coverage`.
|
|
39
|
-
|
|
40
|
-
## Output of this step
|
|
41
|
-
|
|
42
|
-
A list of findings (incomplete tasks, out-of-order completion, checkbox drift) with their
|
|
43
|
-
`Refs` (the Task id, and the requirement/TC it owns) for the SpecReview Findings table, plus
|
|
44
|
-
the tasks-done/total count.
|
|
45
|
-
|
|
46
|
-
## Notes
|
|
47
|
-
|
|
48
|
-
- Do not edit task files or `plan.md` — gap-analysis only reports. If the user wants the
|
|
49
|
-
plan reconciled, that's `spec-to-plan` (update flow) or `implement-plan`.
|
|
@@ -1,147 +0,0 @@
|
|
|
1
|
-
# Step 3: Test-Matrix Verification
|
|
2
|
-
|
|
3
|
-
**Goal**: Prove the Test Matrix is *real* — every Test Case it claims is backed by an actual
|
|
4
|
-
test in the suite, identified by a matching **tracking tag** in the test code. This is the
|
|
5
|
-
heart of gap-analysis: a matrix row marked ✅ means nothing unless a tagged test exists.
|
|
6
|
-
|
|
7
|
-
**This step no longer greps.** `quire coverage` computes the reconciliation deterministically
|
|
8
|
-
and reports it; this skill interprets the report and owns the judgement. Severity and verdict
|
|
9
|
-
stay here — the command reports and does not judge (quire-rs FR-050-CON-1).
|
|
10
|
-
|
|
11
|
-
## The matrix shape
|
|
12
|
-
|
|
13
|
-
Built by `spec-matrix` (`quoin/skills/spec-matrix/SKILL.md`). Key tables:
|
|
14
|
-
|
|
15
|
-
- **Test Case Summary** — `Test ID | Title | Type | Priority | Traces To | Status`, where
|
|
16
|
-
`Test ID` = `TC-xxx`, `Traces To` = `FR-XXX-AC-X` etc., `Status` ∈ `✅ ❌ 🚧 ⛔` (`⚠️` retired — partial work is `🚧`).
|
|
17
|
-
- **Per-requirement coverage** — StR/US/FR/NFR → AC → TC → Status tables.
|
|
18
|
-
|
|
19
|
-
What each column *means* is not this skill's knowledge either: the active module declares it
|
|
20
|
-
under `traceability:`, and `quire coverage` reads the same declaration the matrix contract is
|
|
21
|
-
validated against, so the two cannot drift.
|
|
22
|
-
|
|
23
|
-
## Run the rollup
|
|
24
|
-
|
|
25
|
-
```
|
|
26
|
-
quire coverage --scope <project_root> --json
|
|
27
|
-
```
|
|
28
|
-
|
|
29
|
-
`--scope` is the repository root, and stays so. Since quire-cli v0.16.0 (quire-rs CR-045)
|
|
30
|
-
the command derives **two roots** from it and never interchanges them: spec documents are
|
|
31
|
-
read from `<project_root>/spec` only, and trace tags from the source tree at
|
|
32
|
-
`<project_root>` excluding `spec/`. This invocation needs no second flag — but a project
|
|
33
|
-
whose `spec/` directory is missing now exits with a diagnostic naming the missing document
|
|
34
|
-
root instead of silently scanning the whole repository, and a matrix outside `spec/` (a
|
|
35
|
-
fixture, a `plan/` copy) mints nothing.
|
|
36
|
-
|
|
37
|
-
**Check the version before relying on any of that.** The "since v0.16.0" premise is not
|
|
38
|
-
enforced anywhere — nothing probes it, and a user on ≤ 0.15.0 silently gets the pre-split
|
|
39
|
-
traversal semantics, where the walk covers the whole repository and a matrix outside
|
|
40
|
-
`spec/` mints. One line, before the first invocation:
|
|
41
|
-
|
|
42
|
-
```bash
|
|
43
|
-
quire --version # expect >= 0.16.0; on an older build the roots are not split
|
|
44
|
-
```
|
|
45
|
-
|
|
46
|
-
If it is older, say so in `## Coverage` rather than reading the report as if the split
|
|
47
|
-
applied.
|
|
48
|
-
|
|
49
|
-
Do **not** pass `--strict`. Whether a gap blocks is this skill's verdict rule (Step 6), not
|
|
50
|
-
the command's exit code.
|
|
51
|
-
|
|
52
|
-
The report carries exactly the findings this step produces:
|
|
53
|
-
|
|
54
|
-
| Report field | What it is |
|
|
55
|
-
| --- | --- |
|
|
56
|
-
| `unbacked_rows` | A declared reference row whose trace targets have no backing `verifies` relation. Each carries `reference`, `document`, `row_id`, `target_ids`. |
|
|
57
|
-
| `status_lies` | A row whose status classes as `complete` while nothing backs it. Adds the authored `status` string. |
|
|
58
|
-
| `untracked_symbols` | A test carrying a trace tag that resolves to no declared row. Carries `path`, `symbol`, `trace_id`. |
|
|
59
|
-
| `no_symbol_rows` | An unbacked row whose **declared verification method mints no source symbol** — an eval, an inspection, a demonstration (quire-rs FR-050-AC-16 / CR-041). Carries `reference`, `document`, `row_id`, `test_type`, `target_ids`. **Read this before triaging `unbacked_rows`**: a row listed here is exempt from `status_lies` by its own method, and reporting it as an unbacked-row finding asserts something impossible. Absent from the JSON entirely when the module declares no `no_source_symbol` vocabulary. |
|
|
60
|
-
| `criteria` | Per-document acceptance-criteria property counts (quire-rs FR-050-AC-13 / CR-028): `document`, `archetype`, `criteria`, `property_shaped`, `by_property`. Data for the `spec-correctness` handoff, never a verdict — a low property-shaped share describes a corpus, it does not fail one. Absent when the corpus binds no criteria. |
|
|
61
|
-
| `groups` | Per minting document: `document`, `target`, `backed`, `total`. |
|
|
62
|
-
| `diagnostics` | Declarations that selected nothing and why (quire-rs FR-050-AC-19 / CR-054): an unreadable declared `document:`, an archetype no document has when the model minted nothing, or a model with no trace targets. Absent when every declaration selected. A non-empty list means the numbers below it are measuring less than you think. |
|
|
63
|
-
| `totals` | `backed` / `total` across the bundle, plus `criteria` / `property_shaped` when the corpus binds criteria. |
|
|
64
|
-
|
|
65
|
-
## Reconcile, producing findings
|
|
66
|
-
|
|
67
|
-
| Report field | Finding | Severity |
|
|
68
|
-
| --- | --- | --- |
|
|
69
|
-
| `unbacked_rows` | Matrix overclaims coverage — the row names a criterion or test id nothing backs | `high` |
|
|
70
|
-
| `status_lies` | The row asserts `✅` over nothing. A subset of the above, and the worse half | `high` |
|
|
71
|
-
| `untracked_symbols` | A tagged test pointing at a row that does not exist — a stale tag, or a matrix that dropped a row | `medium` |
|
|
72
|
-
| Marker drift | Matrix `Status` inconsistent with a real run (`🚧` on a passing tagged test) | `low` |
|
|
73
|
-
|
|
74
|
-
`Refs` for each finding is the `row_id` and `document` the report gives, or `path::symbol`
|
|
75
|
-
for an untracked symbol. Do not re-derive them.
|
|
76
|
-
|
|
77
|
-
Marker drift is the one judgement the report cannot make — it needs the suite to have
|
|
78
|
-
actually run (step 4 below).
|
|
79
|
-
|
|
80
|
-
## Two ways the report can mislead, and how to read it
|
|
81
|
-
|
|
82
|
-
- **`totals.total == 0` is not full coverage.** It means the declared model matched nothing
|
|
83
|
-
in this scope — no minting document was found. Recent `quire` prints `no rows matched`
|
|
84
|
-
rather than a percentage and fails `--strict` (quire-rs FR-050-AC-14); an older build
|
|
85
|
-
printed `0/0 rows backed (100%)` and exited 0. Treat a zero denominator as **no data**,
|
|
86
|
-
say so in `## Coverage`, and fall back (below). It is not a `PASS`.
|
|
87
|
-
- **An empty `unbacked_rows` proves nothing on its own.** It lists *reference rows* — cells
|
|
88
|
-
that point at trace ids. A repo whose module declares no such references has an empty list
|
|
89
|
-
regardless of how many tests are tagged. Read `groups` / `totals` alongside it.
|
|
90
|
-
|
|
91
|
-
## Fallback: a repo on an older module set
|
|
92
|
-
|
|
93
|
-
`quire coverage` exits non-zero with a distinct diagnostic when no active module declares a
|
|
94
|
-
`traceability:` model (FR-050-AC-9). That is a real repo state, not an error to swallow —
|
|
95
|
-
`spec-artifacts-process` only began declaring the model at the release carrying FR-004.
|
|
96
|
-
|
|
97
|
-
When the command refuses, or reports a zero denominator, fall back to the grep index below
|
|
98
|
-
and **say which path ran** in the SpecReview's `## Coverage` section:
|
|
99
|
-
|
|
100
|
-
```
|
|
101
|
-
Reconciliation: quire coverage (module spec-artifacts-process 0.11.0)
|
|
102
|
-
Reconciliation: grep fallback — no active module declares a traceability model
|
|
103
|
-
```
|
|
104
|
-
|
|
105
|
-
A finding derived from the fallback is weaker and should be read as such: grep matches a tag
|
|
106
|
-
wherever it sits in a file, including places the engine will not bind it. In quoin, ~15 tags
|
|
107
|
-
sat above a `describe(` block, which registers no symbol — greppable, and invisible to the
|
|
108
|
-
engine (agent-ix/quoin#61). **Never present a grep count as a coverage figure** without
|
|
109
|
-
naming it as a fallback.
|
|
110
|
-
|
|
111
|
-
### The fallback index
|
|
112
|
-
|
|
113
|
-
Grep the test tree across `.py` / `.ts` / `.rs` for every form:
|
|
114
|
-
|
|
115
|
-
| Form | Example |
|
|
116
|
-
| --- | --- |
|
|
117
|
-
| Docstring AC trace | `FR-007-AC-01` inside a test docstring `Description:` block |
|
|
118
|
-
| Docstring `Trace:` | `Trace: FR-001` |
|
|
119
|
-
| Module docstring | `"""Tests for FR-017: Context Management."""` |
|
|
120
|
-
| Test-case id comment / name | `# TC-041`, or a test whose name maps to `TC-041` |
|
|
121
|
-
|
|
122
|
-
Build `{tag → [test file :: test name]}`, then reconcile against the matrix by hand for the
|
|
123
|
-
same four finding kinds.
|
|
124
|
-
|
|
125
|
-
## Optionally run the suite
|
|
126
|
-
|
|
127
|
-
If the user wants execution evidence rather than static reconciliation, run `make test` and
|
|
128
|
-
note failures and skips against matrix rows. This is what turns marker drift from a guess
|
|
129
|
-
into a finding. Don't block on it if the environment can't run tests; say so.
|
|
130
|
-
|
|
131
|
-
## Rollup
|
|
132
|
-
|
|
133
|
-
`totals.backed` / `totals.total` feeds `## Coverage`, with the per-document breakdown from
|
|
134
|
-
`groups` where it helps. Report the numbers the tool produced — do not recompute them, and
|
|
135
|
-
do not quote a figure from an earlier run whose provenance you cannot state.
|
|
136
|
-
|
|
137
|
-
## Output of this step
|
|
138
|
-
|
|
139
|
-
Findings (unbacked rows, status lies, untracked tests, marker drift) with `Refs` from the
|
|
140
|
-
report, the backed/total count, and which reconciliation path ran.
|
|
141
|
-
|
|
142
|
-
## Notes
|
|
143
|
-
|
|
144
|
-
- A backed row proves *traceability*, not *correctness* — whether the test is a good test is
|
|
145
|
-
Step 4 (underspecified/stub) and Step 5 (semantic). Keep this step about presence + trace.
|
|
146
|
-
- The command performs no network or service I/O and executes none of the code it reads
|
|
147
|
-
(FR-050-CON-2, FR-051-CON-1), so it is safe to run in any repo.
|
|
@@ -1,92 +0,0 @@
|
|
|
1
|
-
# Step 4: Underspecified Code (reverse gap)
|
|
2
|
-
|
|
3
|
-
**Goal**: Find the *reverse* gap — code and behavior that exist with **no owning
|
|
4
|
-
requirement**, plus stubs that masquerade as complete. Steps 2–3 verify spec→code/test
|
|
5
|
-
coverage; this step verifies code→spec, catching scope that was implemented but never
|
|
6
|
-
specified.
|
|
7
|
-
|
|
8
|
-
This reference is the authoritative, self-contained reverse-gap procedure. Do not
|
|
9
|
-
consult a private repository, user-home path, or separately installed skill for the
|
|
10
|
-
detection heuristics below.
|
|
11
|
-
|
|
12
|
-
## A. Untraced behavior (code with no requirement)
|
|
13
|
-
|
|
14
|
-
1. **Inventory the surface.** List the component's real behaviors — public
|
|
15
|
-
functions/methods, CLI commands/flags, HTTP endpoints, events, config knobs.
|
|
16
|
-
2. **Trace each to a requirement.** A behavior is *traced* if it maps to an StR/US/FR/NFR
|
|
17
|
-
(via the matrix `Traces To`, a requirement that describes it, or a Task `references`
|
|
18
|
-
edge that owns it).
|
|
19
|
-
3. **Flag the untraced.** Behavior with no owning requirement → finding:
|
|
20
|
-
- `high` if it is user-visible or security/data-affecting (an endpoint, a CLI command, a
|
|
21
|
-
destructive operation) — unspecified surface area.
|
|
22
|
-
- `medium` for internal-but-meaningful logic with no requirement.
|
|
23
|
-
- `low` for trivial helpers/glue.
|
|
24
|
-
`Refs` = the code location (`path::symbol`).
|
|
25
|
-
|
|
26
|
-
## B. Implied requirements from code patterns
|
|
27
|
-
|
|
28
|
-
Map suspicious patterns to the requirement that *should* exist using the table below:
|
|
29
|
-
|
|
30
|
-
| Code pattern | Missing requirement type |
|
|
31
|
-
| --- | --- |
|
|
32
|
-
| Defensive code (try/catch, null guards) | Robustness (NFR) |
|
|
33
|
-
| Ambiguous identity/equality logic | Integrity (StR) |
|
|
34
|
-
| Side effects / IO in core logic | Determinism (StR) |
|
|
35
|
-
| Recursion / unbounded structures | Topology / limits (NFR) |
|
|
36
|
-
| Unmapped constraints | Traceability (FR/StR/NFR) |
|
|
37
|
-
|
|
38
|
-
Each unstated-but-implemented constraint → `medium` finding.
|
|
39
|
-
|
|
40
|
-
## C. Stubs masquerading as complete
|
|
41
|
-
|
|
42
|
-
Scan **source** (not just tests) for hollow implementations the plan/matrix may report as
|
|
43
|
-
done:
|
|
44
|
-
|
|
45
|
-
| Stub | Detect | Severity |
|
|
46
|
-
| --- | --- | --- |
|
|
47
|
-
| Tiny file (≤5 lines, excl. `__init__`) | line count | high |
|
|
48
|
-
| `pass` / placeholder return (`{}`, `[]`, `""`, `None`, `"not implemented"`) body | grep/AST | high |
|
|
49
|
-
| Protocol/ABC-only with no concrete impl | structure | high |
|
|
50
|
-
| Re-export-only module | structure | medium (may be intentional) |
|
|
51
|
-
| Trivially-covered stub (≤5 lines @ 100% cov) | coverage + size | medium |
|
|
52
|
-
|
|
53
|
-
A stub behind a `done` task or a ✅ matrix row is a `high` finding (false completion).
|
|
54
|
-
|
|
55
|
-
Inspect test files as well as source. A passing test can still be a stub:
|
|
56
|
-
|
|
57
|
-
| Test stub | Detect | Severity |
|
|
58
|
-
| --- | --- | --- |
|
|
59
|
-
| Empty body or unconditional skip | `pass`, empty callback, or skip without a tracked reason | high |
|
|
60
|
-
| No behavioral assertion | no assertion, rejection, snapshot, or observable-effect check | high |
|
|
61
|
-
| Weak-only assertion | only existence/type checks for behavior with a stronger contract | high |
|
|
62
|
-
| Mock-everything | all meaningful collaborators replaced so production behavior is never exercised | high |
|
|
63
|
-
| Import-only smoke test | verifies only that a module imports | medium |
|
|
64
|
-
|
|
65
|
-
Do not flag an abstract declaration, generated file, intentional compatibility re-export,
|
|
66
|
-
or a test whose assertion is expressed through the repository's harness merely because it
|
|
67
|
-
matches a textual pattern. Confirm the behavior is hollow before recording a finding.
|
|
68
|
-
|
|
69
|
-
## D. Coverage inflation
|
|
70
|
-
|
|
71
|
-
Treat coverage as evidence only after checking what the covered lines do:
|
|
72
|
-
|
|
73
|
-
- A source file with five or fewer substantive lines and 100% coverage can still be a
|
|
74
|
-
trivially covered stub.
|
|
75
|
-
- A test that mocks a source module which is itself hollow is circular evidence, not
|
|
76
|
-
implementation coverage.
|
|
77
|
-
- A threshold dominated by imports, declarations, or re-exports does not establish that
|
|
78
|
-
the promised behavior exists.
|
|
79
|
-
|
|
80
|
-
Record these as `high` when they support a `done` task or ✅ matrix claim, otherwise
|
|
81
|
-
`medium`. Cite both the hollow source and the test or coverage artifact.
|
|
82
|
-
|
|
83
|
-
## Output of this step
|
|
84
|
-
|
|
85
|
-
Findings for untraced behavior, implied-but-missing requirements, source/test stubs, and
|
|
86
|
-
coverage inflation, each with `Refs` = concrete code/test location. Include counts of
|
|
87
|
-
inventoried behaviors, untraced behaviors, source stubs, and test stubs in `## Coverage`.
|
|
88
|
-
|
|
89
|
-
## Notes
|
|
90
|
-
|
|
91
|
-
- This is the bridge to better specs: untraced behavior usually means a requirement should
|
|
92
|
-
be authored (`/specify`) — but gap-analysis only **reports** it; it does not author specs.
|
|
@@ -1,51 +0,0 @@
|
|
|
1
|
-
# Step 5: Semantic Review (OPTIONAL)
|
|
2
|
-
|
|
3
|
-
**Goal**: Go beyond presence and traceability to *meaning* — for each requirement↔test↔code
|
|
4
|
-
triple, judge whether they actually agree. This is the expensive, judgment-heavy pass.
|
|
5
|
-
|
|
6
|
-
## Gate first
|
|
7
|
-
|
|
8
|
-
**Do not run this step unless the user opts in.** Ask explicitly:
|
|
9
|
-
|
|
10
|
-
> Run the optional semantic review (intent↔test↔code)? It's slower but verifies tests truly
|
|
11
|
-
> validate requirement intent and exercise real code, and that code matches intent.
|
|
12
|
-
|
|
13
|
-
If declined, skip and note "semantic review: skipped" in the SpecReview `## Coverage`.
|
|
14
|
-
|
|
15
|
-
## What to judge (per requirement)
|
|
16
|
-
|
|
17
|
-
For each requirement (FR/US/StR) in scope, with its tagged test(s) (from Step 3) and the
|
|
18
|
-
code it governs (from Step 4), assess three axes:
|
|
19
|
-
|
|
20
|
-
1. **(a) Test validates intent** — does the test actually check the *behavior the
|
|
21
|
-
requirement describes*, including its acceptance criteria, or only an incidental/trivial
|
|
22
|
-
aspect? A test tagged `FR-007-AC-1` that asserts something unrelated to AC-1 fails here.
|
|
23
|
-
2. **(b) Test exercises the code** — does the test run the real implementation, or is it
|
|
24
|
-
hollow? Reuse Step 4's **test-stub / coverage-inflation** heuristics: no assertions,
|
|
25
|
-
weak-only assertions (`is not None`, `isinstance`),
|
|
26
|
-
mock-everything (no real code path), import-only, circular-mock-of-a-stub.
|
|
27
|
-
3. **(c) Code matches intent** — does the implementation actually do what the requirement
|
|
28
|
-
says (semantics, edge cases, error behavior), or has it drifted?
|
|
29
|
-
|
|
30
|
-
Each failing axis → a finding:
|
|
31
|
-
- `high` — test does not validate intent **or** does not exercise code (false confidence),
|
|
32
|
-
or code contradicts the requirement.
|
|
33
|
-
- `medium` — partial validation, meaningful edge cases unchecked, minor drift.
|
|
34
|
-
|
|
35
|
-
`Refs` = `FR-xxx` + test path + `path::symbol`.
|
|
36
|
-
|
|
37
|
-
## How to run it (thoroughness)
|
|
38
|
-
|
|
39
|
-
Fan out for breadth and independence — **one subagent per FR (or per cohesive area)**, each
|
|
40
|
-
returning a structured verdict per axis. Then aggregate the findings. This keeps each
|
|
41
|
-
judgment focused and lets many run concurrently. For a small scope, a single pass is fine.
|
|
42
|
-
|
|
43
|
-
## Output of this step
|
|
44
|
-
|
|
45
|
-
Per-requirement semantic findings (axis a/b/c failures) with `Refs`, plus a note for
|
|
46
|
-
`## Coverage` that semantic review ran and over how many requirements.
|
|
47
|
-
|
|
48
|
-
## Notes
|
|
49
|
-
|
|
50
|
-
- Keep verdicts evidence-based: quote the requirement clause, the assertion, and the code
|
|
51
|
-
line that justify the finding. Avoid speculative "looks wrong" calls.
|