dev-playbooks 1.5.1 → 1.5.2
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 +16 -5
- package/package.json +1 -1
- package/skills/Skills-Usage-Guide.md +48 -0
package/README.md
CHANGED
|
@@ -81,11 +81,21 @@ npx dev-playbooks@latest init
|
|
|
81
81
|
|
|
82
82
|
### Install targets
|
|
83
83
|
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
84
|
+
During initialization, you can choose the Skills installation scope:
|
|
85
|
+
|
|
86
|
+
| Scope | Description | Path Example |
|
|
87
|
+
|-------|-------------|--------------|
|
|
88
|
+
| **Project** (default) | Available only in this project | `.claude/skills/devbooks-*` |
|
|
89
|
+
| **Global** | Shared across all projects | `~/.claude/skills/devbooks-*` |
|
|
90
|
+
|
|
91
|
+
```bash
|
|
92
|
+
# Interactive selection
|
|
93
|
+
dev-playbooks init
|
|
94
|
+
|
|
95
|
+
# Non-interactive
|
|
96
|
+
dev-playbooks init --tools claude --scope project # Project-level
|
|
97
|
+
dev-playbooks init --tools claude --scope global # Global
|
|
98
|
+
```
|
|
89
99
|
|
|
90
100
|
### Quick integration
|
|
91
101
|
|
|
@@ -194,6 +204,7 @@ Run devbooks-archiver skill for change add-oauth2
|
|
|
194
204
|
|-------|-------------|
|
|
195
205
|
| devbooks-entropy-monitor | System entropy metrics |
|
|
196
206
|
| devbooks-brownfield-bootstrap | Brownfield project bootstrap |
|
|
207
|
+
| devbooks-convergence-audit | Convergence audit (anti-deception design) |
|
|
197
208
|
|
|
198
209
|
---
|
|
199
210
|
|
package/package.json
CHANGED
|
@@ -344,6 +344,54 @@ If you are not using DevBooks, replace `dev-playbooks/specs` / `dev-playbooks/ch
|
|
|
344
344
|
|
|
345
345
|
---
|
|
346
346
|
|
|
347
|
+
## `devbooks-test-reviewer` (Test Reviewer) [New]
|
|
348
|
+
|
|
349
|
+
- Purpose: review test quality in `tests/` (coverage, boundary conditions, readability, maintainability); output review comments only; do not modify code.
|
|
350
|
+
- When to use:
|
|
351
|
+
- After Test Owner completes tests, an independent quality review is needed
|
|
352
|
+
- You want to find coverage gaps, missing boundary conditions, and maintainability issues
|
|
353
|
+
- Copy-paste prompt:
|
|
354
|
+
```text
|
|
355
|
+
You are Test Reviewer. Explicitly use `devbooks-test-reviewer`.
|
|
356
|
+
Review test quality only (coverage/boundary conditions/readability/maintainability); do not modify code.
|
|
357
|
+
Inputs: `tests/**` + `dev-playbooks/changes/<change-id>/verification.md` (if present)
|
|
358
|
+
Output: coverage gaps / missing boundary conditions / maintainability risks / improvement suggestions.
|
|
359
|
+
```
|
|
360
|
+
|
|
361
|
+
---
|
|
362
|
+
|
|
363
|
+
## `devbooks-convergence-audit` (Convergence Auditor) [New]
|
|
364
|
+
|
|
365
|
+
- Purpose: evaluate DevBooks workflow convergence using "evidence-first, distrust declarations" principle; detect "Sisyphus anti-pattern" and "false completion". Actively verify rather than trust document assertions.
|
|
366
|
+
- Anti-confusion design: never trust any assertion in documents (Status: Done, AC checked, etc.); must confirm through verifiable evidence.
|
|
367
|
+
- When to use:
|
|
368
|
+
- You want to evaluate true workflow convergence (not document claims)
|
|
369
|
+
- You suspect a change package is "false completion" or has "stale evidence"
|
|
370
|
+
- You want to detect Sisyphus trap (repeated rework without convergence)
|
|
371
|
+
- Copy-paste prompt:
|
|
372
|
+
```text
|
|
373
|
+
You are Convergence Auditor. Explicitly use `devbooks-convergence-audit`.
|
|
374
|
+
First read: `dev-playbooks/project.md` (if present)
|
|
375
|
+
Goal: perform a convergence audit on a specified change package.
|
|
376
|
+
|
|
377
|
+
Execute with anti-confusion principles:
|
|
378
|
+
1) Read all documents under `dev-playbooks/changes/<change-id>/`
|
|
379
|
+
2) Verify each "declaration" (Status=Done, AC checked, etc.) against evidence
|
|
380
|
+
3) Actually run tests for verification (if possible)
|
|
381
|
+
4) Output: declaration vs evidence comparison table + trustworthiness score + confusion detection results
|
|
382
|
+
|
|
383
|
+
Change package: <change-id>
|
|
384
|
+
truth-root: dev-playbooks/specs
|
|
385
|
+
change-root: dev-playbooks/changes
|
|
386
|
+
```
|
|
387
|
+
- Trustworthiness scoring:
|
|
388
|
+
- 90-100: ✅ Trustworthy convergence, continue current workflow
|
|
389
|
+
- 70-89: ⚠️ Partially trustworthy, needs additional verification
|
|
390
|
+
- 50-69: 🟠 Questionable, parts need rework
|
|
391
|
+
- < 50: 🔴 Untrustworthy (Sisyphus trap), needs full review
|
|
392
|
+
|
|
393
|
+
---
|
|
394
|
+
|
|
347
395
|
## Generating SCIP Index (Manual)
|
|
348
396
|
|
|
349
397
|
If you need graph-based code understanding (call graph, impact analysis, symbol references), you can generate a SCIP index manually:
|