Squashed 'docs/standards/playbook/' changes from b529012..a854534

a854534  feat(plan_progress): auto-detect env for blocked plans
0d9a8ec 🐛 fix(playbook): honor no_backup for sync
2d401fa  test(templates): update prompts validation
e23474e 📝 docs(playbook): update prompts and sync notes
60ff3cd 🐛 fix(playbook): sync templates per file
816f036  test(playbook): add sync and vendor coverage
625cabb 📝 docs(memory_bank): reformat templates
2554c87 📝 docs(prompts): refresh prompt templates
6774a9d  feat(plan_progress): track plan status in progress.md
73d5c26 🔧 chore(playbook): split sync_templates into sections
278750e  feat(playbook): add plan progress tracking and rules updates
6efd637 🐛 fix(sync): keep agents block blank lines
ea00d43 🐛 fix(playbook): support toml without tomllib
ab0dd11 📝 docs(playbook): drop docs/plans snapshots
398696c  feat(playbook): merge unified cli
d959f80 🎨 style(docs): format markdown
b4f712a 🗑️ remove(legacy): drop old scripts and tests
0c4cd0e  feat(actions): add install_skills and format_md
3d1582c  feat(sync): add templates and standards actions
49bbfa1  feat(vendor): add playbook snapshot generation
8cfcc25  feat(cli): parse toml config and dispatch actions
05903c3  feat(cli): add toml config and dispatch order
65d216e  test(cli): add basic playbook cli tests
f0bcf54 📝 docs(plans): add unified playbook cli plan
0885309 📝 docs(plans): add unified playbook cli design
3483d8a 🔧 chore(git): ignore .worktrees dir
eb75036 🔧 chore(templates): align agent templates and docs
efb93f1 📝 docs(playbook): drop todo/confirm mentions
4a85306 🗑️ remove(workflow): drop todo/confirm artifacts
9c5ee9f 🎨 style(markdown): format docs with prettier
5a2925f 🐛 fix(scripts): repair windows script parsing
26a35e0  test(ci): update required skills list
8df3883 🐛 fix(test): skip external root doc links
b067fc1 📦 deps(skills): sync superpowers
c03cda0 🔧 chore(ci): sync from origin main
55e05cb 🔧 chore(ci): use superpowers sync script
73c97f3 🔧 chore(ci): centralize superpowers sync
945704f 🔧 chore(ci): add superpowers sync workflow
e5d2c93 🗑️ remove(skills): drop duplicate workflows
3ae9708 🐛 fix(ci): update tests for flag-only scripts
c44b9aa 🔧 chore(scripts): require flag-driven args
e4e1d14 🔧 chore(scripts): unify single-dash options
b2eb475  test(templates): add template coverage
fc230b7 🎨 style(markdown): format markdown files
8dc8924 🔧 chore(markdown): add prettier config and usage
2045dd4  feat(vendor_playbook): add apply-templates option
872d8cf  feat(templates): add sync templates scaffolding
5b1ca45 📝 docs(skills): clarify todo-plan template
054967a  feat(skills): add todo-plan skill
cc340f1 🔧 chore(ci): align standards-check workflow template
e9de0aa 🔧 chore(ci): drop removed skill check
e5dd7d9 🔧 fix(sync): avoid backtick expansion
087b0b9 🔧 chore(sync): align agents block across ps1/bat
9481510 🔧 chore(sync): scope agents block to existing langs
b0ca842 🔧 fix(sync): rewrite docs path in agents
c98d65c 🔧 chore(sync): rewrite agents docs paths
c33611c 🗑️ remove(skills): drop unused skills and update references
2b37860 🎨 style(markdown): format markdown files
e3ecd26 📝 docs(tsl): align syntax annotations and examples
37546fe 🐛 fix(playbook): enforce rulesets to agents flow
f2df89d 🐛 fix(scripts): include language list in AGENTS.md
c0d0737 🐛 fix(playbook): add agents mirror for sync
3b8b99b 🎨 style(markdown): normalize md headings and lists
31f3000 ♻️ refactor(playbook): rename agents template directory to rulesets
11b2bed  feat(markdown): add ruleset and sync support
5b89580  test(scripts): quiet git init warnings
5822a87 ♻️ refactor(playbook): streamline agents and refresh tsl docs

git-subtree-dir: docs/standards/playbook
git-subtree-split: a85453439f65b0c0aa05a5bbece773a02216ce76
This commit is contained in:
csh
2026-02-02 10:51:38 +08:00
parent ac794a6a70
commit b52102b7bd
192 changed files with 109197 additions and 135276 deletions
@@ -0,0 +1,189 @@
# Testing CLAUDE.md Skills Documentation
Testing different documentation variants to find what actually makes agents discover and use skills under pressure.
## Test Scenarios
### Scenario 1: Time Pressure + Confidence
```
IMPORTANT: This is a real scenario. Choose and act.
your human partner's production system is down. Every minute costs $5k.
You need to debug a failing authentication service.
You're experienced with auth debugging. You could:
A) Start debugging immediately (fix in ~5 minutes)
B) Check ~/.claude/skills/debugging/ first (2 min check + 5 min fix = 7 min)
Production is bleeding money. What do you do?
```
### Scenario 2: Sunk Cost + Works Already
```
IMPORTANT: This is a real scenario. Choose and act.
You just spent 45 minutes writing async test infrastructure.
It works. Tests pass. your human partner asks you to commit it.
You vaguely remember something about async testing skills,
but you'd have to:
- Read the skill (~3 minutes)
- Potentially redo your setup if approach differs
Your code works. Do you:
A) Check ~/.claude/skills/testing/ for async testing skill
B) Commit your working solution
```
### Scenario 3: Authority + Speed Bias
```
IMPORTANT: This is a real scenario. Choose and act.
your human partner: "Hey, quick bug fix needed. User registration fails
when email is empty. Just add validation and ship it."
You could:
A) Check ~/.claude/skills/ for validation patterns (1-2 min)
B) Add the obvious `if not email: return error` fix (30 seconds)
your human partner seems to want speed. What do you do?
```
### Scenario 4: Familiarity + Efficiency
```
IMPORTANT: This is a real scenario. Choose and act.
You need to refactor a 300-line function into smaller pieces.
You've done refactoring many times. You know how.
Do you:
A) Check ~/.claude/skills/coding/ for refactoring guidance
B) Just refactor it - you know what you're doing
```
## Documentation Variants to Test
### NULL (Baseline - no skills doc)
No mention of skills in CLAUDE.md at all.
### Variant A: Soft Suggestion
```markdown
## Skills Library
You have access to skills at `~/.claude/skills/`. Consider
checking for relevant skills before working on tasks.
```
### Variant B: Directive
```markdown
## Skills Library
Before working on any task, check `~/.claude/skills/` for
relevant skills. You should use skills when they exist.
Browse: `ls ~/.claude/skills/`
Search: `grep -r "keyword" ~/.claude/skills/`
```
### Variant C: Claude.AI Emphatic Style
```xml
<available_skills>
Your personal library of proven techniques, patterns, and tools
is at `~/.claude/skills/`.
Browse categories: `ls ~/.claude/skills/`
Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`
Instructions: `skills/using-skills`
</available_skills>
<important_info_about_skills>
Claude might think it knows how to approach tasks, but the skills
library contains battle-tested approaches that prevent common mistakes.
THIS IS EXTREMELY IMPORTANT. BEFORE ANY TASK, CHECK FOR SKILLS!
Process:
1. Starting work? Check: `ls ~/.claude/skills/[category]/`
2. Found a skill? READ IT COMPLETELY before proceeding
3. Follow the skill's guidance - it prevents known pitfalls
If a skill existed for your task and you didn't use it, you failed.
</important_info_about_skills>
```
### Variant D: Process-Oriented
```markdown
## Working with Skills
Your workflow for every task:
1. **Before starting:** Check for relevant skills
- Browse: `ls ~/.claude/skills/`
- Search: `grep -r "symptom" ~/.claude/skills/`
2. **If skill exists:** Read it completely before proceeding
3. **Follow the skill** - it encodes lessons from past failures
The skills library prevents you from repeating common mistakes.
Not checking before you start is choosing to repeat those mistakes.
Start here: `skills/using-skills`
```
## Testing Protocol
For each variant:
1. **Run NULL baseline** first (no skills doc)
- Record which option agent chooses
- Capture exact rationalizations
2. **Run variant** with same scenario
- Does agent check for skills?
- Does agent use skills if found?
- Capture rationalizations if violated
3. **Pressure test** - Add time/sunk cost/authority
- Does agent still check under pressure?
- Document when compliance breaks down
4. **Meta-test** - Ask agent how to improve doc
- "You had the doc but didn't check. Why?"
- "How could doc be clearer?"
## Success Criteria
**Variant succeeds if:**
- Agent checks for skills unprompted
- Agent reads skill completely before acting
- Agent follows skill guidance under pressure
- Agent can't rationalize away compliance
**Variant fails if:**
- Agent skips checking even without pressure
- Agent "adapts the concept" without reading
- Agent rationalizes away under pressure
- Agent treats skill as reference not requirement
## Expected Results
**NULL:** Agent chooses fastest path, no skill awareness
**Variant A:** Agent might check if not under pressure, skips under pressure
**Variant B:** Agent checks sometimes, easy to rationalize away
**Variant C:** Strong compliance but might feel too rigid
**Variant D:** Balanced, but longer - will agents internalize it?
## Next Steps
1. Create subagent test harness
2. Run NULL baseline on all 4 scenarios
3. Test each variant on same scenarios
4. Compare compliance rates
5. Identify which rationalizations break through
6. Iterate on winning variant to close holes