@dzhechkov/skills-feature-adr 1.3.55 → 1.3.57

package/README.md

@@ -410,9 +410,11 @@ Fixed roles map to fixed stages (`product-vision`→design+QE, `critic`→QE, `b
 open `extra` list adds guidance to any stage. `dz project-skills` prints the who-injected report. Absent ⇒ a
 normal generic run. (See `dz mr-rakes --gen-critic` to auto-generate the `critic` skill from your recurring rakes.)
 
-**Bundled role-default skills (stack-neutral).** This pack ships three depersonalized quality skills you can
-point the roles at — all calibrated by your `architecture/vision.md` (build it with `dz feature-adr-setup`),
-so they carry your project's reality, not a vendor's:
+**Bundled role-default skills (backend-service defaults; principles portable).** This pack ships four
+depersonalized quality skills you can point the roles at — all calibrated by your `architecture/vision.md`
+(build it with `dz feature-adr-setup`), so they carry your project's reality, not a vendor's. The examples
+assume a backend-service stack (async web / RDB / JWT-JWKS / k8s); the *principles* are portable — translate
+the examples for a different stack:
 
 - **`code-critic`** — an independent code-quality reviewer (god-object growth, security invariants, anti-pattern
   detection by intent, honest severity, "low precision costs more than low recall"). Point the **`critic`** role
@@ -422,6 +424,12 @@ so they carry your project's reality, not a vendor's:
 - **`system-grill`** — a Socratic architecture-intuition trainer (predict-before-reveal, honest 🔴/🟡/🟢 journal)
   that generates its curriculum from your `architecture/subsystems.manifest.json` + `map.json` + `vision.md` —
   for a product person to *feel* the system before briefing an agent. Trigger: "погоняй меня по системе".
+- **`code-skills-creator`** — a meta-factory that *produces* a project-tuned `code-impl` + `code-critic` pair.
+  It starts from the two generic bases above and specializes them with your project's own evidence —
+  `dz mr-rakes` recurring code rakes (primary) or a parallel-critic audit (fallback), your god-object freeze
+  table and reuse-map — then generalizes every rake to a *class* of defect (never a bug-list linter). Writes
+  the pair to `architecture/project-{impl,critic}/SKILL.md` (augment-never-clobber). With no evidence it hands
+  back the generic pair unchanged rather than invent mistakes. Trigger: "build a quality bar pair".
 
 ### Adversarial plan-gate at the L/XL checkpoint (needs `dz` ≥ 0.3.117)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dzhechkov/skills-feature-adr",
-  "version": "1.3.55",
+  "version": "1.3.57",
   "description": "Adaptive Feature Development skill pack for Claude Code — 11-step pipeline with Complexity Router (S/M/L/XL), ADR-driven architecture, 15 agentic-qe skills, multi-agent fleet QE. Supports --full-qe, --full-qe-extended, --with-learning, and --knowledge-extractor modes.",
   "bin": {
     "skills-feature-adr": "./bin/cli.js"

package/templates/.claude/workflows/feature-adr.js

@@ -555,6 +555,11 @@ const PROJECT_SKILLS = { type: 'object', additionalProperties: false, required:
 const QE = { type: 'object', additionalProperties: false, required: ['grade', 'gaps', 'codeTestsAdequate', 'docTestsPresent'], properties: { grade: { type: 'string' }, codeTestsAdequate: { type: 'boolean' }, docTestsPresent: { type: 'boolean' }, gaps: { type: 'array', items: { type: 'object', additionalProperties: false, required: ['sev', 'what'], properties: { sev: { type: 'string' }, what: { type: 'string' } } } }, claimCheck: { type: 'object', additionalProperties: false, properties: { findings: { type: 'number' }, high: { type: 'number' }, medium: { type: 'number' } } } } }
 const ADR_TEMPLATE_GUIDE = 'ADR best-practices for Step 3: emit exactly one decision per ADR with the invariant core Title, Status, Context, Decision, Consequences. Template weight is tier-routed: S/M use Nygard/ITD-lightweight form but still include decision drivers, considered options, rationale, consequences, and Confirmation; L/XL use MADR structure plus an NHS Wales Confirmation stanza. Confirmation MUST name verification method, monitoring, success metric, and owner, and its load-bearing safety property MUST be tied to a Step-8 automated test/fitness function. Use status vocabulary proposed/accepted/rejected/deprecated/superseded plus a reversibility clause. Context must be neutral and appear before Decision. Considered Options must include rejected options with symmetric pros/cons. Rationale points must map to stated drivers and explain why losers were rejected. Consequences must include positive and negative outcomes/accepted downsides, follow-up ADR links, an after-action review schedule, and supersession discipline: supersession mints a new ADR and never edits accepted/rejected ADR content in place. Decision must be concrete/testable with exact names, versions, formats, paths, commands, or APIs. Reject explainer-masquerading-as-ADR: a domain overview with no concrete Decision is not an ADR. File names under 03_adr MUST be sequential NNN-{decision-slug}.md with lowercase kebab-case, dateless, ticketless slugs (the auto-001 ADR tracks the feature slug, so the present-tense imperative signal lives in the ADR Title; model-named additional ADRs use imperative slugs). Add a ## Links traceability block (requirements, driving use case, related ADRs) and a one-line provenance note (model-generated, edited for clarity); for a long ADR include a top-of-file table of contents.'
 const ADR_FITNESS_CHECKLIST = 'ADR fitness checklist for Step 8: read every ' + FDIR + '/03_adr/NNN-*.md ADR and fail the QE gate for any miss. Required checks: (1) filename is 03_adr/NNN-{decision-slug}.md where the slug is lowercase kebab-case, imperative, dateless, and ticketless; (2) title is decision-shaped and the ADR records one decision only; (3) Status is non-empty controlled vocabulary proposed/accepted/rejected/deprecated/superseded and includes a reversibility/revisit clause; (4) Context is neutral, problem-first, and appears before Decision; (5) Decision Drivers are stated and ranked/weighted; (6) Considered Options include the chosen and rejected options, each with symmetric pros and cons; (7) Rationale maps each point back to a driver and explains why rejected options lost; (8) Decision is concrete/testable with exact names, versions, formats, paths, commands, or APIs; (9) Consequences include positive and negative outcomes/accepted downsides, follow-up ADR links, and an after-action review schedule; (10) Confirmation names verification method, monitoring, success metric, and owner, then links the load-bearing safety property to an automated test/fitness function; (11) no placeholder text, template hints, raw generation scaffolding, or fake Markdown structure; (12) reject explainer-masquerading-as-ADR: describing a space with no concrete Decision is a blocker; (13) a Related/Links traceability block maps the ADR to its requirements, driving use case, and related ADRs. The ADR Confirmation check is load-bearing: assert the named safety property has a real test by file/name; if absent, grade no better than C and record a blocker gap.'
+// §42 test-discrimination gate (feature step8-discrimination-gate, grounded in cve-bench/evaluate.mjs). Asserting
+// the property HAS a test is presence; this asserts it DISCRIMINATES. Advisory — a false green is a HIGH gap, never
+// an auto-abort (dz's rule: a false gate kills trust). Byte-inlined guidance; the safe worktree/run lives in `dz
+// discrimination-check` (harness-core/src/discrimination-gate.ts).
+const DISCRIMINATION_GATE = '§42 TEST-DISCRIMINATION GATE (run right after asserting the property has a test): the ADR Confirmation names `Required automated check: <test file>` for the load-bearing property. Prove that test DISCRIMINATES, not just that it is green — via Bash run EXACTLY `dz discrimination-check --test <that test file> --base HEAD --json` (the Step-7 feature diff is UNCOMMITTED, so HEAD is the pre-feature base). It runs the property test in an isolated git worktree at HEAD (no feature diff) and reports {aggregate, finding}. Parse it: `NON_DISCRIMINATING` = the test PASSES even without the fix (a false green that would stay green if the property regressed) → record a HIGH gap "property test does not discriminate: <file>" but do NOT drop the grade to a blocker on that alone (advisory — the owner decides). `DISCRIMINATES` (red by assertion) and `DISCRIMINATES_VIA_ERROR` (could not load at base — inferred, note it) both PASS. `CANNOT_ISOLATE` folds into the existing "property untested" finding. Record the verdict in the 08_qe_report.md ADR Fitness section. If `dz discrimination-check` is unavailable, note it and continue — never block on the tool.'
 
 // Step 0: Router + MANDATORY self-learning recall
 phase('Router')
@@ -822,7 +827,7 @@ if (needsCodeLandedBarrier(coderUsed)) {
 // Step 8: QE (brutal-honesty, agentic-qe) + MANDATORY teach
 phase('QE')
 await usageProbe('QE')
-const qePrompt = 'Step 8 (QE - brutal-honesty review, agentic-qe) of /feature-adr for "' + DESC + '" (' + SLUG + '). Adversarially review the SHIPPED code (read it): correctness, edge cases, error handling, and the LOAD-BEARING property the ADR named (ASSERT it has a test - the recurring lesson). Run this ADR gate before final grading: ' + ADR_FITNESS_CHECKLIST + ' Grade A/B/C/D honestly. Assess code-test adequacy + doc-test presence. List CONFIRMED gaps with severity. Write ' + FDIR + '/08_qe_report.md with an ADR Fitness Checklist section showing PASS/FAIL per ADR and evidence for the Confirmation-linked test. MANDATORY SELF-LEARNING STORE (close the loop, never skip): compare every candidate lesson against the Step-0 recalled LEARNED patterns above. Teach ONLY lessons NOT covered by Step-0 recall. On overlap, run `dz teach --reinforce "<recalled pattern id or exact text>" --project ' + BRAIN + '` instead of minting a near-duplicate; if --reinforce is unavailable, skip the duplicate teach and report `reinforced existing pattern <id>` in the QE report. Store every genuinely new lesson in the CANONICAL BRAIN store at `' + BRAIN + '` so it is NOT lost to a target repo you may have cd`d into. Via Bash run EXACTLY `' + DZ_TEACH('<a durable reusable lesson from this feature - a rule/pattern/pitfall, NOT a checkpoint echo>', '<0.7-0.95>', '<area>') + '` for each genuine NEW lesson (1-3 max, high-signal) — the `cd ' + BRAIN + ' &&` prefix + `--project ' + BRAIN + '` pin guarantee the lesson lands in the brain regardless of your CWD. Then run `' + DZ + ' statusline --fa-record --slug ' + SLUG + ' --step "Step 8 QE" --recalled 3 --stored <count taught> --reinforced <count reinforced> --mode ' + MODE + ' --project ' + REPO + '` (run it verbatim via Bash, do not skip). Do NOT teach trivia or invent gaps. AUTHORING-TIME CLAIM-CHECK (Deliverable of claim-check-authoring-time): after writing ' + FDIR + '/08_qe_report.md, run EXACTLY `dz claim-check ' + FDIR + '/08_qe_report.md --json --fail-on none` via Bash, parse the {ok, findings, scanned} JSON, and report claimCheck: {findings: N, high: N, medium: N} (counts by severity) in your return object. TAG EVERY QUANTITATIVE CLAIM you write in the report using the convention the checker recognizes as honest — write "1131 tests pass (MEASURED — `npx vitest run`)", never a bare "1131 tests pass" — and where you QUOTE a forbidden phrase as an example (e.g. the retracted "100% passing" framing), backtick the literal so it reads as code, not an assertion, so your own compliant report scans clean. Return {grade, gaps, codeTestsAdequate, docTestsPresent, claimCheck}.' + ABSOLUTE_PATH_NOTE + landedNote + PS_GUIDANCE('qe')
+const qePrompt = 'Step 8 (QE - brutal-honesty review, agentic-qe) of /feature-adr for "' + DESC + '" (' + SLUG + '). Adversarially review the SHIPPED code (read it): correctness, edge cases, error handling, and the LOAD-BEARING property the ADR named (ASSERT it has a test - the recurring lesson). Run this ADR gate before final grading: ' + ADR_FITNESS_CHECKLIST + ' ' + DISCRIMINATION_GATE + ' Grade A/B/C/D honestly. Assess code-test adequacy + doc-test presence. List CONFIRMED gaps with severity. Write ' + FDIR + '/08_qe_report.md with an ADR Fitness Checklist section showing PASS/FAIL per ADR and evidence for the Confirmation-linked test. MANDATORY SELF-LEARNING STORE (close the loop, never skip): compare every candidate lesson against the Step-0 recalled LEARNED patterns above. Teach ONLY lessons NOT covered by Step-0 recall. On overlap, run `dz teach --reinforce "<recalled pattern id or exact text>" --project ' + BRAIN + '` instead of minting a near-duplicate; if --reinforce is unavailable, skip the duplicate teach and report `reinforced existing pattern <id>` in the QE report. Store every genuinely new lesson in the CANONICAL BRAIN store at `' + BRAIN + '` so it is NOT lost to a target repo you may have cd`d into. Via Bash run EXACTLY `' + DZ_TEACH('<a durable reusable lesson from this feature - a rule/pattern/pitfall, NOT a checkpoint echo>', '<0.7-0.95>', '<area>') + '` for each genuine NEW lesson (1-3 max, high-signal) — the `cd ' + BRAIN + ' &&` prefix + `--project ' + BRAIN + '` pin guarantee the lesson lands in the brain regardless of your CWD. Then run `' + DZ + ' statusline --fa-record --slug ' + SLUG + ' --step "Step 8 QE" --recalled 3 --stored <count taught> --reinforced <count reinforced> --mode ' + MODE + ' --project ' + REPO + '` (run it verbatim via Bash, do not skip). Do NOT teach trivia or invent gaps. AUTHORING-TIME CLAIM-CHECK (Deliverable of claim-check-authoring-time): after writing ' + FDIR + '/08_qe_report.md, run EXACTLY `dz claim-check ' + FDIR + '/08_qe_report.md --json --fail-on none` via Bash, parse the {ok, findings, scanned} JSON, and report claimCheck: {findings: N, high: N, medium: N} (counts by severity) in your return object. TAG EVERY QUANTITATIVE CLAIM you write in the report using the convention the checker recognizes as honest — write "1131 tests pass (MEASURED — `npx vitest run`)", never a bare "1131 tests pass" — and where you QUOTE a forbidden phrase as an example (e.g. the retracted "100% passing" framing), backtick the literal so it reads as code, not an assertion, so your own compliant report scans clean. Return {grade, gaps, codeTestsAdequate, docTestsPresent, claimCheck}.' + ABSOLUTE_PATH_NOTE + landedNote + PS_GUIDANCE('qe')
 // CROSS-MODEL QE (load-bearing): resolveStageModel('qe') derives the OTHER family than the resolved
 // coder when args.models.qe is unset (coder-codex ⇒ opus; coder-Claude ⇒ codex, or opus if codex absent).
 // An explicit args.models.qe wins. A Claude qe spec is merged onto the qe-code-reviewer base (role