@jakkrichm/create-nexus-devflow 2.2.1 → 2.5.0

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 (61) hide show
  1. package/dist/bin/create-nexus-devflow.js +9 -1
  2. package/dist/bin/create-nexus-devflow.js.map +1 -1
  3. package/dist/lib/command-catalog.js +1 -1
  4. package/dist/lib/command-catalog.js.map +1 -1
  5. package/dist/lib/dashboard-page.d.ts +1 -1
  6. package/dist/lib/dashboard-page.js +42 -20
  7. package/dist/lib/dashboard-page.js.map +1 -1
  8. package/dist/lib/dashboard-snapshot.js +16 -12
  9. package/dist/lib/dashboard-snapshot.js.map +1 -1
  10. package/dist/lib/dashboard.js +10 -1
  11. package/dist/lib/dashboard.js.map +1 -1
  12. package/dist/lib/doctor.js +1 -1
  13. package/dist/lib/gatekeeper.d.ts +8 -0
  14. package/dist/lib/gatekeeper.js +15 -3
  15. package/dist/lib/gatekeeper.js.map +1 -1
  16. package/dist/lib/git-status.d.ts +10 -2
  17. package/dist/lib/git-status.js +57 -29
  18. package/dist/lib/git-status.js.map +1 -1
  19. package/dist/lib/swarm-orchestrator.d.ts +4 -1
  20. package/dist/lib/swarm-orchestrator.js +2 -2
  21. package/dist/lib/swarm-orchestrator.js.map +1 -1
  22. package/dist/lib/version-check.js +1 -1
  23. package/dist/lib/workflow-state.js +19 -32
  24. package/dist/lib/workflow-state.js.map +1 -1
  25. package/package.json +1 -1
  26. package/template/.agents/skills/check/SKILL.md +19 -11
  27. package/template/.agents/skills/complete/SKILL.md +47 -36
  28. package/template/.agents/skills/debug/SKILL.md +4 -8
  29. package/template/.agents/skills/devflow/SKILL.md +51 -79
  30. package/template/.agents/skills/feature/SKILL.md +8 -4
  31. package/template/.agents/skills/implement/SKILL.md +12 -8
  32. package/template/.claude/skills/check/SKILL.md +19 -11
  33. package/template/.claude/skills/complete/SKILL.md +47 -36
  34. package/template/.claude/skills/debug/SKILL.md +4 -8
  35. package/template/.claude/skills/devflow/SKILL.md +51 -79
  36. package/template/.claude/skills/feature/SKILL.md +8 -4
  37. package/template/.claude/skills/implement/SKILL.md +12 -8
  38. package/template/AGENTS.md +21 -30
  39. package/template/devflow/build-plan.md +19 -0
  40. package/template/devflow/context/ai-interaction.md +54 -39
  41. package/template/devflow/context/coding-standards.md +17 -6
  42. package/template/devflow/context/findings.md +8 -11
  43. package/template/devflow/context/glossary.md +31 -0
  44. package/template/devflow/reference/build-plan-template.md +65 -0
  45. package/template/devflow/reference/feature-spec-template.md +110 -0
  46. package/template/devflow/reference/project-plan-template.md +128 -0
  47. package/template/devflow/reference/running-id-contract.md +12 -11
  48. package/template/.agents/skills/10-define/SKILL.md +0 -54
  49. package/template/.agents/skills/20-spec/SKILL.md +0 -155
  50. package/template/.agents/skills/30-plan/SKILL.md +0 -220
  51. package/template/.agents/skills/40-execute/SKILL.md +0 -161
  52. package/template/.agents/skills/50-verify/SKILL.md +0 -55
  53. package/template/.agents/skills/60-report/SKILL.md +0 -57
  54. package/template/.agents/skills/70-deliver/SKILL.md +0 -72
  55. package/template/.claude/skills/10-define/SKILL.md +0 -54
  56. package/template/.claude/skills/20-spec/SKILL.md +0 -155
  57. package/template/.claude/skills/30-plan/SKILL.md +0 -220
  58. package/template/.claude/skills/40-execute/SKILL.md +0 -161
  59. package/template/.claude/skills/50-verify/SKILL.md +0 -55
  60. package/template/.claude/skills/60-report/SKILL.md +0 -57
  61. package/template/.claude/skills/70-deliver/SKILL.md +0 -72
@@ -1,161 +0,0 @@
1
- ---
2
- name: 40-execute
3
- description: "[devflow][D] Execute stage in DevFlow 2.0 - execute planned tasks incrementally with evidence and unit tests."
4
- ---
5
- # Phase 40: Execute Code
6
-
7
- Implement and execute the approved plan incrementally. Source code edits are allowed in this phase.
8
-
9
- ## Usage
10
-
11
- ```text
12
- 40-execute {ID}
13
- ```
14
-
15
- ## Markdown-First Contract
16
-
17
- Use `40-execute.md` as the primary execution artifact.
18
- Before writing `40-execute.md`, produce the artifact in Thai (`th`).
19
-
20
- Before execution, confirm the plan is approved in the stage artifacts. Track subtask progress, execution notes, and completion evidence directly in `40-execute.md` and related stage markdown files.
21
-
22
- ## Required Section Content
23
-
24
- Before completing any generated artifact:
25
-
26
- - preserve every heading required by the selected template
27
- - write concrete information under every heading
28
- - when no information exists or the section does not apply, write exactly `-`
29
- - never leave a heading immediately followed by another heading with no body content
30
- - remove template placeholders from the final artifact
31
- - do not invent facts merely to avoid using `-`
32
- - re-read the saved artifact and verify every heading satisfies this rule
33
-
34
- ## Process
35
-
36
- ### Loop Contract
37
-
38
- Run execution as scoped execution loops, one unit at a time.
39
-
40
- - **Intent**: complete the selected planned unit while preserving the spec, plan, and repository conventions.
41
- - **Context**: read `30-plan.md`, `20-spec.md`, relevant checklist items, target files, pattern files, and test decisions before editing.
42
- - **Action**: make the smallest useful change for the current unit, update or create tests when required, run the planned verification, and record the result.
43
- - **Observation**: inspect concrete evidence from diffs, command output, tests, manual checks, and checklist status before claiming progress.
44
- - **Adjustment**: if evidence does not match intent, fix within the current unit, capture the blocker, use `Debug`, or return to `30-plan` or `20-spec` when the work no longer matches the contract.
45
- - **Stop Condition**: stop the unit when the planned change is complete, verification evidence is recorded, deviations are explained, and the next unit or handoff is clear.
46
- - **Handoff**: `40-execute.md` must tell `50-verify` what changed, why it changed, which checks ran, what failed or was skipped, and what residual risk remains.
47
-
48
- ### 1. Get Bearings
49
-
50
- Read:
51
-
52
- - `30-plan.md`
53
- - `20-spec.md`
54
- - `checklists/implementation-checklist.md` when present
55
- - referenced pattern files
56
- - `10-define.md` when the intent needs a quick reminder
57
-
58
- Confirm the current Git branch with `git branch --show-current` and use that branch as the user's chosen working branch. Do not create, switch, or checkout branches automatically.
59
-
60
- Select one scoped unit of work at a time. Do not implement the whole plan as one blob.
61
-
62
- ### 2. Execute One Scoped Unit
63
-
64
- Use the original coder discipline, adapted to 2.0:
65
-
66
- - **STRICT MANDATE (กฎเหล็ก Unit Test)**: ต้องสร้าง/แก้ไข Unit Test ควบคู่กับการแก้ไขโค้ดเสมอ โดยห้ามแก้ไขเฉพาะไฟล์โค้ดหลัก (Production Code) โดยไม่แก้ไขหรือสร้างไฟล์เทสต์ควบคู่กัน
67
- - start each scoped unit by naming its intent, context, expected observation, adjustment route, and stop condition
68
- - read referenced pattern files before editing
69
- - read the test decision from `30-plan.md`
70
- - confirm assumptions, target files, and success criteria before editing
71
- - make the smallest useful code change
72
- - preserve project style
73
- - run the planned verification
74
- - record observation, adjustment, stop condition status, and the result in `40-execute.md`
75
- - update checklist item status, timestamps, and evidence links as work progresses
76
-
77
- If tests are `Required`:
78
-
79
- 1. **TDD Cycle (RED)**: ออกแบบและเขียนตัวเทสต์ให้พังก่อน (หรือเขียนโครงสร้างเทสต์ที่คาดหวังผลลัพธ์ที่ถูกต้อง) ตามแนวทางใน [coding-standards.md](file:///devflow/context/coding-standards.md)
80
- 2. **GREEN**: เขียนโค้ดระบบจริงให้สอดคล้องเพื่อให้เทสต์ผ่าน
81
- 3. **REFACTOR**: ปรับปรุงโครงสร้างโค้ดโดยยังคงรันเทสต์ผ่านอย่างต่อเนื่อง
82
-
83
- ### 3. Recovery
84
-
85
- Use the old recovery discipline when blocked:
86
-
87
- - capture the blocker with evidence
88
- - mark failure only when the current unit truly cannot continue
89
- - recommend `Debug` when root cause analysis is needed
90
- - return to Plan when the work no longer matches the plan
91
-
92
- Use `tdd` for behavior-change implementation loops, `diagnosing-bugs` when a tight repro is needed before a fix, and `codebase-design` when implementation exposes an awkward seam or shallow module.
93
-
94
- ### 4. Finalize Execution
95
-
96
- When the scoped work is complete:
97
-
98
- - summarize the completed units
99
- - list changed files
100
- - record verification performed
101
- - record loop evidence for each completed unit: intent, observation, adjustment, and stop condition
102
- - record deviations, blockers, and manual checks
103
- - make sure checklist statuses match the actual state of the code and tests
104
- - make sure `40-execute.md` is ready for Verify
105
-
106
- ### 5. Manual Review Soft Gate
107
-
108
- If the plan was not clearly approved, warn that execution proceeded under review risk.
109
- When finishing `40-execute.md`:
110
-
111
- - record any deviation from the approved plan explicitly
112
- - set reviewer expectations before `50-verify`
113
- - keep `50-verify` as the next soft recommendation rather than an unconditional jump
114
-
115
- ## Output
116
-
117
- Report:
118
-
119
- - scoped units completed
120
- - files changed
121
- - verification commands run
122
- - test decisions followed or changed, with reasons
123
- - loop evidence and handoff notes for Verify
124
- - blocked items or manual checks
125
- - next command: `50-verify {ID}`
126
-
127
- ## Relationship To DevFlow 2.0
128
-
129
- - Classification: Mainline workflow
130
- - Previous state: `30-plan`
131
- - Next state: `50-verify` when scoped execution is complete
132
- - Common companion commands: `Debug` for blockers, `Preview` for local checks; support skills: `tdd`, `diagnosing-bugs`, and `codebase-design` for behavior changes, root-cause loops, and implementation-time design pressure
133
-
134
- ## Sources
135
-
136
- - `AGENTS.md`
137
- - `docs/workspace-artifacts.md`
138
- - Related commands: `30-plan`, `Debug`, `Preview`, `50-verify`
139
-
140
- ## Next Workflow Recommendation
141
-
142
- - **Primary**: `50-verify {ID}` when the planned work is complete.
143
- - **Why**: Implementation needs independent verification before release or human acceptance.
144
- - **Alternatives**:
145
- - `Debug "{blocker}"` - choose this when execution is blocked by an unexplained failure.
146
- - `30-plan {ID}` - choose this when the plan is incomplete or no longer matches the work.
147
- - `Preview` - choose this when a local runtime or visual check is useful before formal verification.
148
- - `codebase-design` - choose this when the implementation cannot be tested cleanly because the module shape is wrong.
149
-
150
- ## Nexus Event
151
-
152
- - Use `Debug` when the conversation reveals an unexplained blocker, flaky behavior, or root-cause gap.
153
- - Use `Preview` when a runtime, UI, or local interaction check would reduce verification risk.
154
- - Return to `30-plan` when execution drift shows the plan no longer matches reality.
155
-
156
- ## Wiki Update Recommendation
157
-
158
- - **Needed**: `yes` when coding discovers a reusable implementation pattern, gotcha, or context optimization.
159
- - **Scope**: `project` unless the discovery is about DevFlow itself.
160
- - **Reason**: Coding findings are useful only when they are stable enough to help future tasks.
161
- - **Suggested Command**: `Wiki project ingest devflow/runs/{ID}-*40-execute.md`
@@ -1,55 +0,0 @@
1
- ---
2
- name: 50-verify
3
- description: "[devflow][D] Verify stage in DevFlow 2.0 - perform senior QA review, record evidence, and decide pass or return-to-implement."
4
- ---
5
-
6
- # Phase 50: Verify Quality
7
-
8
- Review implementation quality, run multi-lane validation, produce a verification report, and route the task forward or back to implementation.
9
-
10
- ## Usage
11
-
12
- ```text
13
- 50-verify {ID}
14
- ```
15
-
16
- ## Markdown-First Contract
17
-
18
- Use `50-verify.md` as the primary verification artifact.
19
- Use `50-verify-impact.md` as an optional companion artifact when the run changes behavior, touches core logic, crosses integration boundaries, or needs explicit rollback and client impact analysis.
20
-
21
- ## Process & Quality Gates
22
-
23
- ### 1. Senior QA Review & Multi-Lane Verification
24
-
25
- Execute verification across all essential quality dimensions:
26
-
27
- 1. **Lane 1: Typecheck & Static Code Quality**:
28
- - Run typecheck and static analysis (`tsc --noEmit`, `npm run lint`).
29
- 2. **Lane 2: Automated Test Suites (TDD Gate)**:
30
- - Run automated unit and integration tests (`npm test`).
31
- - Confirm 100% test pass rate with zero disabled or skipped tests.
32
- 3. **Lane 3: Scrutinize QA & Edge Cases Review**:
33
- - **Boundary Conditions**: Check empty inputs, 0/1 counts, off-by-one errors.
34
- - **Null / Undefined Safety**: Verify nullish handling and strict type invariants.
35
- - **Error Handling & Propagation**: Verify errors provide actionable diagnostics without swallowing.
36
- 4. **Lane 4: Security & Hygiene Audit**:
37
- - **Secrets Check**: Ensure no hardcoded credentials or API keys exist.
38
- - **Input Sanitization**: Ensure parameterized queries and validated inputs.
39
- 5. **Lane 5: Findings Ledger State Machine (`findings.md`)**:
40
- - Inspect `devflow/context/findings.md`.
41
- - **P0/P1 HARD GATE**: Any Finding of severity `P0` or `P1` in `open` or `fixed` status unconditionally blocks pass.
42
- 6. **Lane 6: Manual Scenario Proof**:
43
- - Provide clear manual verification instructions: "Where to go", "What to run/click", "What to expect".
44
-
45
- ### 2. Decision & Route
46
-
47
- - **Pass**: Route to `60-report {ID}`.
48
- - **Fail**: Route back to `40-execute {ID}` with exact failure evidence and remediation steps.
49
-
50
- ## Output
51
-
52
- Report:
53
- - QA verdict across all verification lanes
54
- - Evidence commands and outputs
55
- - Next command: `60-report {ID}` (if pass) or `40-execute {ID}` (if fail)
@@ -1,57 +0,0 @@
1
- ---
2
- name: 60-report
3
- description: "[devflow][D] Report stage in DevFlow 2.0 - produce standardized markdown summary report with retrospective lessons learned."
4
- argument-hint: "{running-id or workspace path}"
5
- ---
6
-
7
- # Phase 60: Report
8
-
9
- $ARGUMENTS
10
-
11
- Produce the final human-friendly summary of the full running flow in Markdown (`60-report.md`) with retrospective lessons learned, findings summary, and release digest.
12
-
13
- ## Usage
14
-
15
- ```text
16
- 60-report {running-id or workspace path}
17
- ```
18
-
19
- ## Markdown-First Contract
20
-
21
- Write the primary stage artifact to:
22
-
23
- ```text
24
- devflow/context/current-run/60-report.md
25
- ```
26
-
27
- > [!IMPORTANT]
28
- > **No Auto-Generated HTML**: ห้ามสร้างไฟล์ `60-report.html` แบบอัตโนมัติในขั้นตอนนี้! ระบบจะสร้างเฉพาะ `60-report.md` เท่านั้น หากต้องการดู HTML Report ให้เรียกคำสั่งแยก: `/report:html`
29
-
30
- ## Process
31
-
32
- ### 1. Gather Full Run Context & Verification Evidence
33
- Read all relevant stage artifacts:
34
- - `10-define.md`
35
- - `20-spec.md`
36
- - `30-plan.md`
37
- - `40-execute.md`
38
- - `50-verify.md`
39
-
40
- ### 2. Retrospective Lessons Learned & Gotchas (Insight Extraction)
41
- Extract durable insights from the completed run:
42
- - **Reusable Patterns**: Design choices or implementations that future runs should mirror.
43
- - **Gotchas & Pitfalls**: Unforeseen issues or quirks encountered during execution.
44
- - **Unresolved Follow-ups**: Route any residual out-of-scope ideas to `devflow/ideas.md`.
45
-
46
- ### 3. Produce Standardized Report (`60-report.md`)
47
- Structure the report in **Thai (`th`)**:
48
- 1. **Executive Summary**: ปัญหาและแนวทางแก้ไข
49
- 2. **Delivery Scope**: รายการฟีเจอร์และคอมโพเนนต์ที่ส่งมอบ
50
- 3. **Verification Evidence Snapshot**: ผลการทดสอบทุก Lane
51
- 4. **Retrospective & Lessons Learned**: บทเรียนและข้อควรระวัง
52
- 5. **Manual Try Guide**: ขั้นตอนสำหรับมนุษย์ทดสอบระบบ
53
-
54
- ## Next Workflow Recommendation
55
-
56
- - **Primary**: `70-deliver {ID}`
57
- - **Optional Standalone HTML**: `/report:html`
@@ -1,72 +0,0 @@
1
- ---
2
- name: 70-deliver
3
- description: "[devflow][D] Deliver stage in DevFlow 2.0 - package verified work for delivery, archive run to categorized history, git merge, PR, or deployment."
4
- argument-hint: "{running-id or workspace path}"
5
- ---
6
-
7
- # Phase 70: Deliver
8
-
9
- $ARGUMENTS
10
-
11
- Package approved work for delivery after the report stage has captured the final verified story. Archives the active run from `devflow/context/current-run/` to `devflow/history/{features|fixes|rollbacks}/{xxx-slug}/`, updates `HISTORY.md` and `CHANGELOG.md`, executes pre-flight smoke checks, performs conventional git commit & merge, and closes the run.
12
-
13
- ## Usage
14
-
15
- ```text
16
- 70-deliver {id or workspace path}
17
- ```
18
-
19
- ## Markdown-First Contract
20
-
21
- Write the primary stage artifact to:
22
-
23
- ```text
24
- devflow/context/current-run/70-deliver.md
25
- ```
26
-
27
- ## Process & Quality Gates
28
-
29
- ### 0. Step 0 Safety Pass & Findings Ledger Gate
30
-
31
- Before packaging, merging, or delivering:
32
-
33
- 1. **Findings Ledger Blockers**:
34
- - Inspect `devflow/context/findings.md`.
35
- - No Finding of severity `P0` or `P1` in `open` or `fixed` status is permitted.
36
- - `fixed` still blocks release until reviewed and closed in `50-verify`.
37
- 2. **Pre-flight & Deployment Smoke Validation**:
38
- - Verify environment variables and configuration parameters.
39
- - Run production build or package smoke check (`npm run build` or `npm run test:package`).
40
- - Validate that clean state exists with no untracked experimental files.
41
- 3. **2-Stage Approval Separation**:
42
- - Consent to merge into `main` is strictly separate from consent to `git push` to remote or deploy.
43
-
44
- ### 1. Changelog & SemVer Version Bump
45
-
46
- 1. Calculate next version according to **Semantic Versioning (SemVer)**:
47
- - `Major`: Breaking architectural changes, removed public APIs
48
- - `Minor`: New backward-compatible features added
49
- - `Patch`: Bug fixes, optimizations, documentation
50
- 2. Append new release entry to `CHANGELOG.md` in [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) format (`Added`, `Changed`, `Fixed`, `Removed`, `Security`).
51
-
52
- ### 2. Conventional Commit & Git Merge
53
-
54
- 1. Stage all release and tracking files.
55
- 2. Commit with conventional format: `chore(release): release {version}` or `feat({scope}): {summary}`.
56
- 3. Squash-merge to base branch (`main`) with explicit user approval.
57
-
58
- ### 3. Archive Run Folder to Categorized History
59
-
60
- 1. Determine Category (`features`, `fixes`, `rollbacks`).
61
- 2. Move directory `devflow/context/current-run/` ➔ `devflow/history/{category}/{xxx-slug}/`.
62
- 3. Clean resolved findings (`closed`, `accepted`, `invalid`) from `devflow/context/findings.md` and append to the release notes.
63
- 4. Append entry to `devflow/history/HISTORY.md` linking to `history/{category}/{xxx-slug}/60-report.md`.
64
-
65
- ### 4. Update Workspace State
66
-
67
- Set `devflow/context/current-stage.md` to:
68
- - `Active Discovery ID`: `None`
69
- - `Active Running ID`: `None (Idle)`
70
- - `Current Stage`: `Idle (Ready for new run)`
71
- - `Last Completed Run`: `{ID} ({YYYY-MM-DD})`
72
- - `Last Updated`: `{YYYY-MM-DD}`