owflow 0.6.0 → 0.7.0

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.
Files changed (195) hide show
  1. package/LICENSE +21 -21
  2. package/README.md +448 -283
  3. package/dist/agents/bottleneck-analyzer.md +332 -333
  4. package/dist/agents/code-quality-pragmatist.md +353 -354
  5. package/dist/agents/code-reviewer.md +238 -239
  6. package/dist/agents/codebase-analysis-reporter.md +245 -246
  7. package/dist/agents/docs-operator.md +22 -23
  8. package/dist/agents/e2e-test-verifier.md +447 -448
  9. package/dist/agents/gap-analyzer.md +501 -502
  10. package/dist/agents/implementation-completeness-checker.md +219 -220
  11. package/dist/agents/implementation-planner.md +308 -309
  12. package/dist/agents/information-gatherer.md +690 -691
  13. package/dist/agents/production-readiness-checker.md +278 -279
  14. package/dist/agents/project-analyzer.md +403 -403
  15. package/dist/agents/reality-assessor.md +365 -366
  16. package/dist/agents/research-planner.md +449 -450
  17. package/dist/agents/research-synthesizer.md +402 -403
  18. package/dist/agents/solution-brainstormer.md +256 -257
  19. package/dist/agents/solution-designer.md +371 -372
  20. package/dist/agents/spec-auditor.md +297 -298
  21. package/dist/agents/specification-creator.md +333 -334
  22. package/dist/agents/task-classifier.md +449 -450
  23. package/dist/agents/task-group-implementer.md +283 -284
  24. package/dist/agents/test-suite-runner.md +194 -195
  25. package/dist/agents/user-docs-generator.md +508 -509
  26. package/dist/commands/reviews-code.md +90 -90
  27. package/dist/commands/reviews-pragmatic.md +99 -99
  28. package/dist/commands/reviews-production-readiness.md +113 -113
  29. package/dist/commands/reviews-reality-check.md +110 -110
  30. package/dist/commands/reviews-spec-audit.md +114 -114
  31. package/dist/commands/work.md +280 -280
  32. package/dist/configuration/agents-config.d.ts +2 -0
  33. package/dist/configuration/agents-config.js +8 -44
  34. package/dist/configuration/commands-config.d.ts +23 -0
  35. package/dist/configuration/commands-config.js +17 -17
  36. package/dist/configuration/skills-config.d.ts +2 -0
  37. package/dist/configuration/skills-config.js +3 -3
  38. package/dist/hooks/hooks-diagnostics.d.ts +3 -0
  39. package/dist/hooks/hooks-diagnostics.js +21 -0
  40. package/dist/hooks/hooks-persistence.d.ts +17 -0
  41. package/dist/hooks/hooks-persistence.js +207 -0
  42. package/dist/hooks/hooks-registry.d.ts +6 -0
  43. package/dist/hooks/hooks-registry.js +104 -0
  44. package/dist/hooks/hooks-wrapper.d.ts +25 -0
  45. package/dist/hooks/hooks-wrapper.js +318 -0
  46. package/dist/hooks/internal/before-tool.d.ts +6 -0
  47. package/dist/hooks/internal/before-tool.js +13 -0
  48. package/dist/hooks/internal/session-compaction.d.ts +9 -0
  49. package/dist/hooks/{session-compaction.js → internal/session-compaction.js} +9 -7
  50. package/dist/hooks/runtime/circuit-breaker.d.ts +23 -0
  51. package/dist/hooks/runtime/circuit-breaker.js +39 -0
  52. package/dist/hooks/runtime/failure-policy.d.ts +15 -0
  53. package/dist/hooks/runtime/failure-policy.js +49 -0
  54. package/dist/hooks/runtime/process-executor.d.ts +33 -0
  55. package/dist/hooks/runtime/process-executor.js +147 -0
  56. package/dist/hooks/runtime/status-recorder.d.ts +27 -0
  57. package/dist/hooks/runtime/status-recorder.js +111 -0
  58. package/dist/index.d.ts +7 -0
  59. package/dist/index.js +111 -40
  60. package/dist/skills/agents-md-generator/SKILL.md +223 -223
  61. package/dist/skills/codebase-analyzer/SKILL.md +162 -162
  62. package/dist/skills/codebase-analyzer/references/code-analysis.md +63 -63
  63. package/dist/skills/codebase-analyzer/references/combined.md +31 -31
  64. package/dist/skills/codebase-analyzer/references/context-discovery.md +63 -63
  65. package/dist/skills/codebase-analyzer/references/file-discovery.md +51 -51
  66. package/dist/skills/codebase-analyzer/references/migration-target.md +23 -23
  67. package/dist/skills/codebase-analyzer/references/pattern-mining.md +22 -22
  68. package/dist/skills/dev-analyze/SKILL.md +115 -115
  69. package/dist/skills/dev-bugfix/SKILL.md +452 -452
  70. package/dist/skills/dev-finalize/SKILL.md +118 -118
  71. package/dist/skills/dev-implement/SKILL.md +167 -167
  72. package/dist/skills/dev-plan/SKILL.md +147 -147
  73. package/dist/skills/dev-spec/SKILL.md +182 -182
  74. package/dist/skills/dev-tdd-red/SKILL.md +94 -94
  75. package/dist/skills/dev-verify/SKILL.md +153 -153
  76. package/dist/skills/development/SKILL.md +260 -260
  77. package/dist/skills/diagrams-mermaid/SKILL.md +183 -159
  78. package/dist/skills/diagrams-mermaid/references/reference.md +220 -148
  79. package/dist/skills/docs-manager/SKILL.md +379 -379
  80. package/dist/skills/docs-manager/docs/INDEX.md +199 -199
  81. package/dist/skills/docs-manager/docs/standards/backend/api.md +25 -25
  82. package/dist/skills/docs-manager/docs/standards/backend/migrations.md +22 -22
  83. package/dist/skills/docs-manager/docs/standards/backend/models.md +25 -25
  84. package/dist/skills/docs-manager/docs/standards/backend/queries.md +22 -22
  85. package/dist/skills/docs-manager/docs/standards/frontend/accessibility.md +25 -25
  86. package/dist/skills/docs-manager/docs/standards/frontend/components.md +28 -28
  87. package/dist/skills/docs-manager/docs/standards/frontend/css.md +16 -16
  88. package/dist/skills/docs-manager/docs/standards/frontend/responsive.md +28 -28
  89. package/dist/skills/docs-manager/docs/standards/global/coding-style.md +25 -25
  90. package/dist/skills/docs-manager/docs/standards/global/commenting.md +10 -10
  91. package/dist/skills/docs-manager/docs/standards/global/conventions.md +31 -31
  92. package/dist/skills/docs-manager/docs/standards/global/error-handling.md +22 -22
  93. package/dist/skills/docs-manager/docs/standards/global/minimal-implementation.md +22 -22
  94. package/dist/skills/docs-manager/docs/standards/global/validation.md +28 -28
  95. package/dist/skills/docs-manager/docs/standards/testing/test-writing.md +25 -25
  96. package/dist/skills/docs-manager/references/agents-md-template.md +29 -29
  97. package/dist/skills/docs-manager/references/index-md-template.md +73 -73
  98. package/dist/skills/flow-init/SKILL.md +234 -234
  99. package/dist/skills/flow-init/references/architecture-template.md +45 -45
  100. package/dist/skills/flow-init/references/roadmap-templates.md +93 -93
  101. package/dist/skills/flow-init/references/tech-stack-template.md +70 -70
  102. package/dist/skills/flow-init/references/vision-templates.md +75 -75
  103. package/dist/skills/goal-development/SKILL.md +96 -96
  104. package/dist/skills/goal-migration/SKILL.md +114 -114
  105. package/dist/skills/goal-performance/SKILL.md +126 -126
  106. package/dist/skills/goal-research/SKILL.md +118 -118
  107. package/dist/skills/html-renderer/SKILL.md +173 -173
  108. package/dist/skills/html-renderer/references/index.html +318 -318
  109. package/dist/skills/html-renderer/references/styles.css +388 -388
  110. package/dist/skills/html-renderer/references/tokens.json +104 -104
  111. package/dist/skills/implementation-plan-executor/SKILL.md +378 -378
  112. package/dist/skills/implementation-verifier/SKILL.md +307 -307
  113. package/dist/skills/migration/SKILL.md +268 -268
  114. package/dist/skills/migration-analyze/SKILL.md +126 -126
  115. package/dist/skills/migration-finalize/SKILL.md +161 -161
  116. package/dist/skills/migration-fix/SKILL.md +155 -155
  117. package/dist/skills/migration-implement/SKILL.md +131 -131
  118. package/dist/skills/migration-plan/SKILL.md +131 -131
  119. package/dist/skills/migration-spec/SKILL.md +135 -135
  120. package/dist/skills/migration-spec/references/migration-strategies.md +430 -430
  121. package/dist/skills/migration-target/SKILL.md +134 -134
  122. package/dist/skills/migration-target/references/migration-types.md +489 -489
  123. package/dist/skills/migration-verify/SKILL.md +184 -184
  124. package/dist/skills/orchestrator-framework/SKILL.md +65 -65
  125. package/dist/skills/orchestrator-framework/references/command-namespacing.md +7 -7
  126. package/dist/skills/orchestrator-framework/references/confirm-or-revise-exception.md +20 -20
  127. package/dist/skills/orchestrator-framework/references/delegation-rules.md +54 -54
  128. package/dist/skills/orchestrator-framework/references/dispatcher-handoff.md +27 -27
  129. package/dist/skills/orchestrator-framework/references/fix-loop-contract.md +65 -65
  130. package/dist/skills/orchestrator-framework/references/gate-contract.md +122 -122
  131. package/dist/skills/orchestrator-framework/references/orchestrator-creation-checklist.md +51 -51
  132. package/dist/skills/orchestrator-framework/references/orchestrator-patterns.md +235 -235
  133. package/dist/skills/performance/SKILL.md +267 -267
  134. package/dist/skills/performance-analyze/SKILL.md +129 -129
  135. package/dist/skills/performance-analyze/references/performance-optimization-guide.md +271 -271
  136. package/dist/skills/performance-finalize/SKILL.md +117 -117
  137. package/dist/skills/performance-implement/SKILL.md +114 -114
  138. package/dist/skills/performance-plan/SKILL.md +112 -112
  139. package/dist/skills/performance-spec/SKILL.md +145 -145
  140. package/dist/skills/performance-verify/SKILL.md +164 -164
  141. package/dist/skills/research/SKILL.md +249 -249
  142. package/dist/skills/research-brainstorm/SKILL.md +120 -120
  143. package/dist/skills/research-brainstorm/references/brainstorming-techniques.md +84 -84
  144. package/dist/skills/research-converge/SKILL.md +130 -130
  145. package/dist/skills/research-design/SKILL.md +146 -146
  146. package/dist/skills/research-design/references/design-techniques.md +40 -40
  147. package/dist/skills/research-finalize/SKILL.md +125 -125
  148. package/dist/skills/research-fork/SKILL.md +190 -190
  149. package/dist/skills/research-gather/SKILL.md +133 -133
  150. package/dist/skills/research-plan/SKILL.md +141 -141
  151. package/dist/skills/research-plan/references/research-methodologies.md +710 -710
  152. package/dist/skills/research-quick/SKILL.md +139 -139
  153. package/dist/skills/research-synthesize/SKILL.md +127 -127
  154. package/dist/skills/rule-reviewer/SKILL.md +334 -334
  155. package/dist/skills/standards-discover/SKILL.md +260 -260
  156. package/dist/skills/standards-discover/references/aggregation-strategy.md +76 -76
  157. package/dist/skills/standards-discover/references/code-pattern-prompt.md +68 -68
  158. package/dist/skills/standards-discover/references/config-analyzer-prompt.md +67 -67
  159. package/dist/skills/standards-discover/references/docs-extractor-prompt.md +65 -65
  160. package/dist/skills/standards-discover/references/external-analyzer-prompt.md +75 -75
  161. package/dist/skills/standards-update/SKILL.md +207 -207
  162. package/dist/templates/orchestrator-state-base.yml +17 -17
  163. package/dist/templates/orchestrator-state-development.yml +95 -95
  164. package/dist/templates/orchestrator-state-migration.yml +95 -95
  165. package/dist/templates/orchestrator-state-performance.yml +64 -64
  166. package/dist/templates/orchestrator-state-research.yml +67 -67
  167. package/dist/tools/fork_task.d.ts +17 -0
  168. package/dist/tools/fork_task.js +21 -11
  169. package/dist/tools/verify_template.d.ts +11 -0
  170. package/dist/tools/verify_template.js +32 -17
  171. package/dist/tui/hooks-dialogs.d.ts +20 -0
  172. package/dist/tui/hooks-dialogs.js +181 -0
  173. package/dist/tui/hooks-presenter.d.ts +15 -0
  174. package/dist/tui/hooks-presenter.js +70 -0
  175. package/dist/tui/hooks-sidebar.d.ts +10 -0
  176. package/dist/tui/hooks-sidebar.js +104 -0
  177. package/dist/tui/primitives.d.ts +21 -0
  178. package/dist/tui/primitives.js +47 -0
  179. package/dist/tui.d.ts +12 -0
  180. package/dist/tui.js +129 -0
  181. package/dist/types/hook-types.d.ts +125 -0
  182. package/dist/types/hook-types.js +76 -0
  183. package/dist/types/opencode-types.d.ts +13 -0
  184. package/dist/utils/file-util.d.ts +2 -0
  185. package/dist/utils/file-util.js +6 -6
  186. package/dist/utils/fork-task.d.ts +27 -0
  187. package/dist/utils/fork-task.js +18 -23
  188. package/dist/utils/plugin-info.d.ts +3 -0
  189. package/dist/utils/plugin-info.js +8 -10
  190. package/dist/utils/workflow-paths.d.ts +17 -0
  191. package/dist/utils/workflow-paths.js +18 -0
  192. package/dist/utils/yaml-structure.d.ts +7 -0
  193. package/dist/utils/yaml-structure.js +7 -11
  194. package/package.json +68 -48
  195. package/dist/hooks/before-tool.js +0 -19
@@ -1,153 +1,153 @@
1
- ---
2
- name: owflow:dev-verify
3
- description: Development — verification options prompt, comprehensive implementation verification, and user-driven fix loop.
4
- argument-hint: "[task-path-or-identifier]"
5
- user-invocable: true
6
- ---
7
-
8
- # Dev Verify — Verification & Issue Resolution (options-chosen, verification-done)
9
-
10
- Work phase of the development workflow. Lets the user pick which verification checks run, then delegates comprehensive verification with a fix-then-reverify loop.
11
-
12
- ## Entry Gate
13
-
14
- Resolve the `task-path-or-identifier` argument BEFORE anything else (see [Gate Contract](../orchestrator-framework/references/gate-contract.md)):
15
-
16
- - **Path** (absolute or project-relative) to the task directory — use as-is.
17
- - **Identifier** — exact directory name inside `.owflow/tasks/development/` (e.g., `2026-01-12-my-task`); resolve to its path.
18
- - If the argument is **missing**, the path does **not exist**, or matches **no identifier** → print the blocked block, then STOP (never guess or auto-pick a task):
19
- 1. Steps that must be completed first (in order), each with its command:
20
- - Codebase & gap analysis (`codebase-analysed`, `gap-analysed`) → `/owflow:dev-analyze <task-path>`
21
- - TDD red gate (`tdd-red-proven`) — only when a reproducible defect was detected → `/owflow:dev-tdd-red <task-path>`
22
- - Requirements, specification & audit (`spec-written`, `spec-audited`) → `/owflow:dev-spec <task-path>`
23
- - Implementation planning (`plan-created`) → `/owflow:dev-plan <task-path>`
24
- - Implementation & TDD green gate (`implementation-done`, `tdd-green-proven`) → `/owflow:dev-implement <task-path>`
25
- 2. List available dev-task identifiers (directories under `.owflow/tasks/development/`) to resume from, if any.
26
- 3. Hint: `Run /owflow:development <description> to start a task from scratch, or pass a task path/identifier to resume.`
27
-
28
- ### Prerequisites
29
-
30
- | Required for this skill | Where verified | Produced by |
31
- | ----------------------- | ------------------------------------------------ | ------------------------------------ |
32
- | State file exists | `<task-path>/orchestrator-state.yml` | `/owflow:development <desc>` |
33
- | Implementation done | `implementation-done` in `completed_phases` | `/owflow:dev-implement <task-path>` |
34
-
35
- **Dev-bugfix tasks are verified here too**: a task produced or resumed by `/owflow:dev-bugfix` reaches this skill with `implementation-done` complete but no spec/plan — that is valid; verification does NOT require them. A consecutive dev-bugfix run on a verified task resets the downstream slugs, so the user is routed here for re-verification.
36
-
37
- 1. **Read `orchestrator-state.yml`** from the task path. If missing → mid-pipeline bootstrap ([Missing-state Bootstrap](../orchestrator-framework/references/gate-contract.md), starting slug `options-chosen`): `question` — create a fresh standard development task starting at this step, or decline → print `No development task found at <path>. Run /owflow:development <description> to start a task from scratch.` and STOP.
38
- 2. **Prerequisite check**: `implementation-done` in `completed_phases` (implementation done). If missing → print the blocked block, then STOP:
39
- - Steps that must be completed first: analysis (`codebase-analysed`, `gap-analysed`) → TDD red gate (`tdd-red-proven`, only when a reproducible defect was detected) → specification (`spec-written`) → implementation planning (`plan-created`) → implementation (`implementation-done`).
40
- - `Run /owflow:dev-implement <task-path> first` (or the command for the earliest missing earlier step: `/owflow:dev-analyze`, `/owflow:dev-tdd-red`, `/owflow:dev-spec`, or `/owflow:dev-plan`).
41
- - If no task exists yet: `Run /owflow:development <description> to start a task from scratch.`
42
- 3. **Re-verification**: if `options-chosen` and `verification-done` are already complete and re-running after fixes, confirm scope via `question` (full re-run vs only failed checks).
43
-
44
- ## Execute
45
-
46
- **Read first**: the [Delegation Rules](../orchestrator-framework/references/delegation-rules.md), the [Fix Loop Contract](../orchestrator-framework/references/fix-loop-contract.md), and [Issue Resolution](../orchestrator-framework/references/orchestrator-patterns.md) (Section 6).
47
-
48
- ### Verification Options Prompt (`options-chosen`, inline)
49
-
50
- **Step 1**: Display the verification plan:
51
-
52
- ```
53
- Verification Plan:
54
- Obligatory (always run):
55
- ✓ Completeness check
56
- ✓ Test suite (skipped — passed during implementation; re-enabled after fixes)
57
-
58
- Recommended (adjustable):
59
- ✓ Code review — quality and security analysis
60
- ✓ Pragmatic review — detects over-engineering
61
- ✓ Reality check — validates work solves the problem
62
- ✓ Production readiness — deployment readiness checks
63
-
64
- Conditional:
65
- [✓/—] E2E browser testing — [reason]
66
- [✓/—] User documentation — [reason]
67
- ```
68
-
69
- **Step 2** (3 questions):
70
-
71
- - **Q1** (always): `question` (multi-select) — "Which standard verifications to run?" Options: "Code review (Recommended)", "Pragmatic review (Recommended)", "Reality check (Recommended)", "Production readiness (Recommended)". All pre-selected.
72
- - **Q2** (skip if `options.e2e_enabled: false` and no `--e2e` flag): "Enable E2E browser verification?" — "Yes (Recommended)" / "No, skip".
73
- - **Q3** (skip if `options.user_docs_enabled: false` and no `--user-docs` flag): "Generate user documentation?" — "Yes (Recommended)" / "No, skip".
74
-
75
- Set all chosen `options.*` in state. **Auto-set** `skip_test_suite: true` (full suite passed during implementation; cleared before re-verification if fixes are applied).
76
-
77
- **State write**: append `options-chosen` to `completed_phases`; write chosen `options.*` and `skip_test_suite`; bump `orchestrator.updated`; re-read + `verify_template` (see State Update Convention).
78
-
79
- ### Verification & Issue Resolution (`verification-done`)
80
-
81
- **Step 1**: Skill tool - `implementation-verifier`. Pass: task_path, task_description, chosen verification options, `verification_context` if re-verifying.
82
-
83
- **Step 2**: Display detailed issue breakdown grouped by category and severity:
84
-
85
- ```
86
- Verification Results:
87
- Critical ([N]):
88
- - [category]: [description] — [file:line] [fixable/manual]
89
- Warning ([N]):
90
- - [category]: [description] — [file:line] [fixable/manual]
91
- Info ([N]):
92
- - [description] (listed for awareness, not actionable)
93
- ```
94
-
95
- **Step 3**: Gate on status — `passed` → skip to State Update. `passed_with_issues` or `failed` → fix loop (Step 4).
96
-
97
- **Step 4**: User-driven fix loop (max 3 iterations) — follow the [Fix Loop Contract](../orchestrator-framework/references/fix-loop-contract.md): the three-option question wording, immediate `fixes_applied` writes, `skip_test_suite: false` after fixes, re-invoking `implementation-verifier` on request, and refreshing `reverify_count` / `last_status` / `issues_found` right after each verifier run.
98
-
99
- **Exit conditions**: no critical issues remain → proceed; user explicitly chooses to proceed with issues → proceed with issues logged; max 3 iterations → `question` "Proceed with known issues?" / "Stop workflow". **MUST NOT proceed with unresolved critical issues unless the user explicitly approves.**
100
-
101
- ## State Update Convention (per step)
102
-
103
- Apply after EVERY phase/step above:
104
-
105
- 1. **Write immediately** — update `orchestrator-state.yml` as soon as the step completes, appending ONLY the step slug actually performed plus that step's fields. Never defer writes to the end of the skill.
106
- 2. **Options prompt** — append `options-chosen` to `completed_phases` with the chosen `options.*` and `skip_test_suite` (written right after the options prompt, before verification starts).
107
- 3. **Per verifier run** — update `verification_context.last_status`, `issues_found`, `fixes_applied`, and `reverify_count` immediately after each `implementation-verifier` run and after each fix-loop iteration (per the [Fix Loop Contract](../orchestrator-framework/references/fix-loop-contract.md)'s immediate-write cadence), so an interruption loses nothing.
108
- 4. **Completion** — append `verification-done` to `completed_phases` only at skill exit: status `passed`, or user-approved proceed with issues logged. Bump `orchestrator.updated` on every write.
109
- 5. **Failures** — if `implementation-verifier` itself fails or the workflow stops with unresolved critical issues, do NOT append `verification-done` to `completed_phases`; append it to `orchestrator.failed_phases` and increment `auto_fix_attempts["verification-done"]`.
110
- 6. **Validate** — after every write, re-read the file to confirm values, then run the `verify_template` tool with `filePath: <task-path>/orchestrator-state.yml`, `templateName: orchestrator-state-development.yml`. Fix any reported issue immediately before proceeding.
111
- 7. **Final check** — before the Exit Gate, one consolidated re-read + `verify_template` run to confirm the full state matches everything performed in this session.
112
-
113
- ## Exit Gate
114
-
115
- Present results, get user confirmation, then hand off (see [Gate Contract](../orchestrator-framework/references/gate-contract.md)). Never auto-invoke the next skill.
116
-
117
- ### Results box
118
-
119
- ```markdown
120
- ## ✅ DEV VERIFY COMPLETE — <task name>
121
-
122
- **Overall status** — [✅ passed / ⚠ passed_with_issues / ❌ failed]
123
- **Issues found** — [total] ([critical] C / [warning] W / [info] I)
124
- **Fixed** — [count]
125
- **Remaining** — [by severity]
126
-
127
- **Artifacts**
128
- - `verification/implementation-verification.md`
129
- - `verification/code-review-report.md` [if run]
130
- - `verification/pragmatic-review.md` [if run]
131
- - `verification/reality-check.md` [if run]
132
- - `verification/production-readiness-report.md` [if run]
133
- ```
134
-
135
- ### Results-acceptance question
136
-
137
- Use `question` — "Are these results correct?" with options:
138
-
139
- - **Accept** — verification outcome is good (including approved proceed-with-issues); continue.
140
- - **Adjust** — run additional fixes and/or another verification round (within the fix-loop limits), then re-present the results box.
141
- - **Discuss** — walk through specific findings (issue details, fixability assessment, recommendations) in more depth; then re-ask.
142
- - **Stop here** — print the resume command (`/owflow:dev-verify <task-path>`) and end.
143
-
144
- ### Next steps (after Accept)
145
-
146
- - `→ /owflow:dev-finalize <task-path>` — `required` to close the workflow: conditional E2E verification, optional user documentation, and commit guidance (whether E2E/docs run is decided inside based on task characteristics). Remaining after: none — workflow ends.
147
-
148
- **Other options**:
149
-
150
- - `/owflow:reviews-code <task-path>` / `/owflow:reviews-pragmatic <task-path>` — `optional` — standalone re-runs of individual reviews; do not advance phases
151
- - `/owflow:goal-development <task-path>` — `optional` shortcut: finishes the remaining phases in one loop (finalize)
152
-
153
- Then STOP.
1
+ ---
2
+ name: owflow:dev-verify
3
+ description: Development — verification options prompt, comprehensive implementation verification, and user-driven fix loop.
4
+ argument-hint: "[task-path-or-identifier]"
5
+ user-invocable: true
6
+ ---
7
+
8
+ # Dev Verify — Verification & Issue Resolution (options-chosen, verification-done)
9
+
10
+ Work phase of the development workflow. Lets the user pick which verification checks run, then delegates comprehensive verification with a fix-then-reverify loop.
11
+
12
+ ## Entry Gate
13
+
14
+ Resolve the `task-path-or-identifier` argument BEFORE anything else (see [Gate Contract](../orchestrator-framework/references/gate-contract.md)):
15
+
16
+ - **Path** (absolute or project-relative) to the task directory — use as-is.
17
+ - **Identifier** — exact directory name inside `.owflow/tasks/development/` (e.g., `2026-01-12-my-task`); resolve to its path.
18
+ - If the argument is **missing**, the path does **not exist**, or matches **no identifier** → print the blocked block, then STOP (never guess or auto-pick a task):
19
+ 1. Steps that must be completed first (in order), each with its command:
20
+ - Codebase & gap analysis (`codebase-analysed`, `gap-analysed`) → `/owflow:dev-analyze <task-path>`
21
+ - TDD red gate (`tdd-red-proven`) — only when a reproducible defect was detected → `/owflow:dev-tdd-red <task-path>`
22
+ - Requirements, specification & audit (`spec-written`, `spec-audited`) → `/owflow:dev-spec <task-path>`
23
+ - Implementation planning (`plan-created`) → `/owflow:dev-plan <task-path>`
24
+ - Implementation & TDD green gate (`implementation-done`, `tdd-green-proven`) → `/owflow:dev-implement <task-path>`
25
+ 2. List available dev-task identifiers (directories under `.owflow/tasks/development/`) to resume from, if any.
26
+ 3. Hint: `Run /owflow:development <description> to start a task from scratch, or pass a task path/identifier to resume.`
27
+
28
+ ### Prerequisites
29
+
30
+ | Required for this skill | Where verified | Produced by |
31
+ | ----------------------- | ------------------------------------------------ | ------------------------------------ |
32
+ | State file exists | `<task-path>/orchestrator-state.yml` | `/owflow:development <desc>` |
33
+ | Implementation done | `implementation-done` in `completed_phases` | `/owflow:dev-implement <task-path>` |
34
+
35
+ **Dev-bugfix tasks are verified here too**: a task produced or resumed by `/owflow:dev-bugfix` reaches this skill with `implementation-done` complete but no spec/plan — that is valid; verification does NOT require them. A consecutive dev-bugfix run on a verified task resets the downstream slugs, so the user is routed here for re-verification.
36
+
37
+ 1. **Read `orchestrator-state.yml`** from the task path. If missing → mid-pipeline bootstrap ([Missing-state Bootstrap](../orchestrator-framework/references/gate-contract.md), starting slug `options-chosen`): `question` — create a fresh standard development task starting at this step, or decline → print `No development task found at <path>. Run /owflow:development <description> to start a task from scratch.` and STOP.
38
+ 2. **Prerequisite check**: `implementation-done` in `completed_phases` (implementation done). If missing → print the blocked block, then STOP:
39
+ - Steps that must be completed first: analysis (`codebase-analysed`, `gap-analysed`) → TDD red gate (`tdd-red-proven`, only when a reproducible defect was detected) → specification (`spec-written`) → implementation planning (`plan-created`) → implementation (`implementation-done`).
40
+ - `Run /owflow:dev-implement <task-path> first` (or the command for the earliest missing earlier step: `/owflow:dev-analyze`, `/owflow:dev-tdd-red`, `/owflow:dev-spec`, or `/owflow:dev-plan`).
41
+ - If no task exists yet: `Run /owflow:development <description> to start a task from scratch.`
42
+ 3. **Re-verification**: if `options-chosen` and `verification-done` are already complete and re-running after fixes, confirm scope via `question` (full re-run vs only failed checks).
43
+
44
+ ## Execute
45
+
46
+ **Read first**: the [Delegation Rules](../orchestrator-framework/references/delegation-rules.md), the [Fix Loop Contract](../orchestrator-framework/references/fix-loop-contract.md), and [Issue Resolution](../orchestrator-framework/references/orchestrator-patterns.md) (Section 6).
47
+
48
+ ### Verification Options Prompt (`options-chosen`, inline)
49
+
50
+ **Step 1**: Display the verification plan:
51
+
52
+ ```
53
+ Verification Plan:
54
+ Obligatory (always run):
55
+ ✓ Completeness check
56
+ ✓ Test suite (skipped — passed during implementation; re-enabled after fixes)
57
+
58
+ Recommended (adjustable):
59
+ ✓ Code review — quality and security analysis
60
+ ✓ Pragmatic review — detects over-engineering
61
+ ✓ Reality check — validates work solves the problem
62
+ ✓ Production readiness — deployment readiness checks
63
+
64
+ Conditional:
65
+ [✓/—] E2E browser testing — [reason]
66
+ [✓/—] User documentation — [reason]
67
+ ```
68
+
69
+ **Step 2** (3 questions):
70
+
71
+ - **Q1** (always): `question` (multi-select) — "Which standard verifications to run?" Options: "Code review (Recommended)", "Pragmatic review (Recommended)", "Reality check (Recommended)", "Production readiness (Recommended)". All pre-selected.
72
+ - **Q2** (skip if `options.e2e_enabled: false` and no `--e2e` flag): "Enable E2E browser verification?" — "Yes (Recommended)" / "No, skip".
73
+ - **Q3** (skip if `options.user_docs_enabled: false` and no `--user-docs` flag): "Generate user documentation?" — "Yes (Recommended)" / "No, skip".
74
+
75
+ Set all chosen `options.*` in state. **Auto-set** `skip_test_suite: true` (full suite passed during implementation; cleared before re-verification if fixes are applied).
76
+
77
+ **State write**: append `options-chosen` to `completed_phases`; write chosen `options.*` and `skip_test_suite`; bump `orchestrator.updated`; re-read + `verify_template` (see State Update Convention).
78
+
79
+ ### Verification & Issue Resolution (`verification-done`)
80
+
81
+ **Step 1**: Skill tool - `implementation-verifier`. Pass: task_path, task_description, chosen verification options, `verification_context` if re-verifying.
82
+
83
+ **Step 2**: Display detailed issue breakdown grouped by category and severity:
84
+
85
+ ```
86
+ Verification Results:
87
+ Critical ([N]):
88
+ - [category]: [description] — [file:line] [fixable/manual]
89
+ Warning ([N]):
90
+ - [category]: [description] — [file:line] [fixable/manual]
91
+ Info ([N]):
92
+ - [description] (listed for awareness, not actionable)
93
+ ```
94
+
95
+ **Step 3**: Gate on status — `passed` → skip to State Update. `passed_with_issues` or `failed` → fix loop (Step 4).
96
+
97
+ **Step 4**: User-driven fix loop (max 3 iterations) — follow the [Fix Loop Contract](../orchestrator-framework/references/fix-loop-contract.md): the three-option question wording, immediate `fixes_applied` writes, `skip_test_suite: false` after fixes, re-invoking `implementation-verifier` on request, and refreshing `reverify_count` / `last_status` / `issues_found` right after each verifier run.
98
+
99
+ **Exit conditions**: no critical issues remain → proceed; user explicitly chooses to proceed with issues → proceed with issues logged; max 3 iterations → `question` "Proceed with known issues?" / "Stop workflow". **MUST NOT proceed with unresolved critical issues unless the user explicitly approves.**
100
+
101
+ ## State Update Convention (per step)
102
+
103
+ Apply after EVERY phase/step above:
104
+
105
+ 1. **Write immediately** — update `orchestrator-state.yml` as soon as the step completes, appending ONLY the step slug actually performed plus that step's fields. Never defer writes to the end of the skill.
106
+ 2. **Options prompt** — append `options-chosen` to `completed_phases` with the chosen `options.*` and `skip_test_suite` (written right after the options prompt, before verification starts).
107
+ 3. **Per verifier run** — update `verification_context.last_status`, `issues_found`, `fixes_applied`, and `reverify_count` immediately after each `implementation-verifier` run and after each fix-loop iteration (per the [Fix Loop Contract](../orchestrator-framework/references/fix-loop-contract.md)'s immediate-write cadence), so an interruption loses nothing.
108
+ 4. **Completion** — append `verification-done` to `completed_phases` only at skill exit: status `passed`, or user-approved proceed with issues logged. Bump `orchestrator.updated` on every write.
109
+ 5. **Failures** — if `implementation-verifier` itself fails or the workflow stops with unresolved critical issues, do NOT append `verification-done` to `completed_phases`; append it to `orchestrator.failed_phases` and increment `auto_fix_attempts["verification-done"]`.
110
+ 6. **Validate** — after every write, re-read the file to confirm values, then run the `verify_template` tool with `filePath: <task-path>/orchestrator-state.yml`, `templateName: orchestrator-state-development.yml`. Fix any reported issue immediately before proceeding.
111
+ 7. **Final check** — before the Exit Gate, one consolidated re-read + `verify_template` run to confirm the full state matches everything performed in this session.
112
+
113
+ ## Exit Gate
114
+
115
+ Present results, get user confirmation, then hand off (see [Gate Contract](../orchestrator-framework/references/gate-contract.md)). Never auto-invoke the next skill.
116
+
117
+ ### Results box
118
+
119
+ ```markdown
120
+ ## ✅ DEV VERIFY COMPLETE — <task name>
121
+
122
+ **Overall status** — [✅ passed / ⚠ passed_with_issues / ❌ failed]
123
+ **Issues found** — [total] ([critical] C / [warning] W / [info] I)
124
+ **Fixed** — [count]
125
+ **Remaining** — [by severity]
126
+
127
+ **Artifacts**
128
+ - `verification/implementation-verification.md`
129
+ - `verification/code-review-report.md` [if run]
130
+ - `verification/pragmatic-review.md` [if run]
131
+ - `verification/reality-check.md` [if run]
132
+ - `verification/production-readiness-report.md` [if run]
133
+ ```
134
+
135
+ ### Results-acceptance question
136
+
137
+ Use `question` — "Are these results correct?" with options:
138
+
139
+ - **Accept** — verification outcome is good (including approved proceed-with-issues); continue.
140
+ - **Adjust** — run additional fixes and/or another verification round (within the fix-loop limits), then re-present the results box.
141
+ - **Discuss** — walk through specific findings (issue details, fixability assessment, recommendations) in more depth; then re-ask.
142
+ - **Stop here** — print the resume command (`/owflow:dev-verify <task-path>`) and end.
143
+
144
+ ### Next steps (after Accept)
145
+
146
+ - `→ /owflow:dev-finalize <task-path>` — `required` to close the workflow: conditional E2E verification, optional user documentation, and commit guidance (whether E2E/docs run is decided inside based on task characteristics). Remaining after: none — workflow ends.
147
+
148
+ **Other options**:
149
+
150
+ - `/owflow:reviews-code <task-path>` / `/owflow:reviews-pragmatic <task-path>` — `optional` — standalone re-runs of individual reviews; do not advance phases
151
+ - `/owflow:goal-development <task-path>` — `optional` shortcut: finishes the remaining phases in one loop (finalize)
152
+
153
+ Then STOP.