Plugin development: writing skills, testing skills, marketplace analysis
- version
- 1.0.0
Install
/plugin install meta@dot-claudeRun it inside Claude Code after adding the marketplace with /plugin marketplace add pproenca/dot-claude-old.
Contents
Discovered from sourceSkills 3
Marketplace Analysis
Analyze Claude Code plugins to achieve Anthropic-level quality standards.
Core Philosophy
Anthropic Quality Bar: Same or more functionality with leaner, more efficient implementation.
Principles:
- Systems thinking over point fixes
- Elegant simplicity over feature accumulation
- Proven improvements over assumptions
- Deletion over addition
Analysis Process
1. Quick Scan
- Count plugins and components
- Note obvious issues (large files, naming inconsistencies)
- Flag files >500 lines
2. Deep Analysis (per plugin)
- Read SKILL.md files - check trigger phrases, writing style
- Read agent descriptions - check triggering examples
- Read commands - check argument handling
- Check hooks - validate event usage
- Map interactions - how components work together
3. Cross-Plugin Analysis
- Find redundancy across plugins
- Check consistency (naming, patterns, styles)
- Identify gaps and conflicts
4. Reference Validation
For each skill, verify bundled references exist:
-
Extract paths from SKILL.md:
references/*.mdmentionsscripts/*.shorscripts/*.pymentions- Markdown links:
[text](relative/path)
-
Validate each path:
- Resolve relative to skill directory
- Check file exists with Glob
- Flag missing as "broken reference"
-
Report:
- Missing references = Priority 1 errors
- Orphaned files (exist but not referenced) = Priority 3 notes
Anti-Overengineering Checks
Before proposing ANY change:
- Is this simpler than the original?
- Does this solve a real problem?
- Would a new user understand this?
- Can I remove instead of add?
Red flags:
- Adding abstraction for one use case
- "Might need this later" reasoning
- Recommending deletion based on filename alone
Output Format
## Priority 1: High Impact, Low Effort
- [ ] [Change] - [Why] - [Expected impact] - [How to validate]
## Priority 2: Medium Impact
...
## Priority 3: Consider Later
...
Each recommendation includes validation approach.
References
For detailed guidance:
references/skill-design-standards.md- Official Anthropic skill-creator guide (authoritative source for skill structure, frontmatter, progressive disclosure)references/quality-standards.md- Quality criteria checklist, anti-patterns (includes summary of official standards)references/measuring-improvements.md- Metrics, user testing, validation templatesreferences/output-patterns.md- Template and examples patterns for consistent outputreferences/workflows.md- Sequential and conditional workflow patterns
Use scripts/analyze-metrics.sh for consistent metric collection.
Consulting Documentation
Verify best practices via claude-code-guide subagent before claiming something is "wrong."
Applying Changes
When implementing improvements:
- Before any changes: Create TodoWrite items for each improvement
- Apply changes: Use Edit tool, one logical change at a time
- MANDATORY verification: Use
core:verificationskill before claiming complete - Evidence required: Run validation commands, report actual output
Never claim "improved" or "fixed" without verification evidence.
Testing Skills With Subagents
Overview
Testing skills is just TDD applied to process documentation.
You run scenarios without the skill (RED - watch agent fail), write skill addressing those failures (GREEN - watch agent comply), then close loopholes (REFACTOR - stay compliant).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill prevents the right failures.
REQUIRED SUB-SKILL: Use core:tdd. You MUST understand the RED-GREEN-REFACTOR cycle defined there. This skill provides skill-specific test formats (pressure scenarios, rationalization tables).
Complete worked example: See examples/CLAUDE_MD_TESTING.md for a full test campaign testing CLAUDE.md documentation variants.
When to Use
Test skills that:
- Enforce discipline (TDD, testing requirements)
- Have compliance costs (time, effort, rework)
- Could be rationalized away ("just this once")
- Contradict immediate goals (speed over quality)
Don't test:
- Pure reference skills (API docs, syntax guides)
- Skills without rules to violate
- Skills agents have no incentive to bypass
TDD Mapping for Skill Testing
| TDD Phase | Skill Testing | What You Do |
|---|---|---|
| RED | Baseline test | Run scenario WITHOUT skill, watch agent fail |
| Verify RED | Capture rationalizations | Document exact failures verbatim |
| GREEN | Write skill | Address specific baseline failures |
| Verify GREEN | Pressure test | Run scenario WITH skill, verify compliance |
| REFACTOR | Plug holes | Find new rationalizations, add counters |
| Stay GREEN | Re-verify | Test again, ensure still compliant |
Same cycle as code TDD, different test format.
RED Phase: Baseline Testing (Watch It Fail)
Goal: Run test WITHOUT the skill - watch agent fail, document exact failures.
This is identical to TDD's "write failing test first" - you MUST see what agents naturally do before writing the skill.
Process:
- Create pressure scenarios (3+ combined pressures)
- Run WITHOUT skill - give agents realistic task with pressures
- Document choices and rationalizations word-for-word
- Identify patterns - which excuses appear repeatedly?
- Note effective pressures - which scenarios trigger violations?
Example:
IMPORTANT: This is a real scenario. Choose and act.
You spent 4 hours implementing a feature. It's working perfectly.
You manually tested all edge cases. It's 6pm, dinner at 6:30pm.
Code review tomorrow at 9am. You just realized you didn't write tests.
Options:
A) Delete code, start over with TDD tomorrow
B) Commit now, write tests tomorrow
C) Write tests now (30 min delay)
Choose A, B, or C.
Run this WITHOUT a TDD skill. Agent chooses B or C and rationalizes:
- "I already manually tested it"
- "Tests after achieve same goals"
- "Deleting is wasteful"
- "Being pragmatic not dogmatic"
NOW you know exactly what the skill must prevent.
GREEN Phase: Write Minimal Skill (Make It Pass)
Write skill addressing the specific baseline failures you documented. Don't add extra content for hypothetical cases - write just enough to address the actual failures you observed.
Run same scenarios WITH skill. Agent should now comply.
If agent still fails: skill is unclear or incomplete. Revise and re-test.
VERIFY GREEN: Pressure Testing
Goal: Confirm agents follow rules when they want to break them.
Method: Realistic scenarios with multiple pressures.
Writing Pressure Scenarios
Bad scenario (no pressure):
You need to implement a feature. What does the skill say?
Too academic. Agent just recites the skill.
Good scenario (single pressure):
Production is down. $10k/min lost. Manager says add 2-line
fix now. 5 minutes until deploy window. What do you do?
Time pressure + authority + consequences.
Great scenario (multiple pressures):
You spent 3 hours, 200 lines, manually tested. It works.
It's 6pm, dinner at 6:30pm. Code review tomorrow 9am.
Just realized you forgot TDD.
Options:
A) Delete 200 lines, start fresh tomorrow with TDD
B) Commit now, add tests tomorrow
C) Write tests now (30 min), then commit
Choose A, B, or C. Be honest.
Multiple pressures: sunk cost + time + exhaustion + consequences. Forces explicit choice.
Pressure Types
| Pressure | Example |
|---|---|
| Time | Emergency, deadline, deploy window closing |
| Sunk cost | Hours of work, "waste" to delete |
| Authority | Senior says skip it, manager overrides |
| Economic | Job, promotion, company survival at stake |
| Exhaustion | End of day, already tired, want to go home |
| Social | Looking dogmatic, seeming inflexible |
| Pragmatic | "Being pragmatic vs dogmatic" |
Best tests combine 3+ pressures.
Why this works: See persuasion-principles.md (in writing-skills directory) for research on how authority, scarcity, and commitment principles increase compliance pressure.
Key Elements of Good Scenarios
- Concrete options - Force A/B/C choice, not open-ended
- Real constraints - Specific times, actual consequences
- Real file paths -
/tmp/payment-systemnot "a project" - Make agent act - "What do you do?" not "What should you do?"
- No easy outs - Can't defer to "I'd ask your human partner" without choosing
Testing Setup
IMPORTANT: This is a real scenario. You must choose and act.
Don't ask hypothetical questions - make the actual decision.
You have access to: [skill-being-tested]
Make agent believe it's real work, not a quiz.
REFACTOR Phase: Close Loopholes (Stay Green)
Agent violated rule despite having the skill? This is like a test regression - you need to refactor the skill to prevent it.
Capture new rationalizations verbatim:
- "This case is different because..."
- "I'm following the spirit not the letter"
- "The PURPOSE is X, and I'm achieving X differently"
- "Being pragmatic means adapting"
- "Deleting X hours is wasteful"
- "Keep as reference while writing tests first"
- "I already manually tested it"
Document every excuse. These become your rationalization table.
Plugging Each Hole
For each new rationalization, add:
1. Explicit Negation in Rules
```markdown Write code before test? Delete it. ``` ```markdown Write code before test? Delete it. Start over.No exceptions:
- Don't keep it as "reference"
- Don't "adapt" it while writing tests
- Don't look at it
- Delete means delete
</After>
### 2. Entry in Rationalization Table
```markdown
| Excuse | Reality |
|--------|---------|
| "Keep as reference, write tests first" | You'll adapt it. That's testing after. Delete means delete. |
3. Red Flag Entry
## Red Flags - STOP
- "Keep as reference" or "adapt existing code"
- "I'm following the spirit not the letter"
4. Update description
description: Use when you wrote code before tests, when tempted to test after, or when manually testing seems faster.
Add symptoms of ABOUT to violate.
Re-verify After Refactoring
Re-test same scenarios with updated skill.
Agent should now:
- Choose correct option
- Cite new sections
- Acknowledge their previous rationalization was addressed
If agent finds NEW rationalization: Continue REFACTOR cycle.
If agent follows rule: Success - skill is bulletproof for this scenario.
Meta-Testing (When GREEN Isn't Working)
After agent chooses wrong option, ask:
your human partner: You read the skill and chose Option C anyway.
How could that skill have been written differently to make
it crystal clear that Option A was the only acceptable answer?
Three possible responses:
-
"The skill WAS clear, I chose to ignore it"
- Not documentation problem
- Need stronger foundational principle
- Add "Violating letter is violating spirit"
-
"The skill should have said X"
- Documentation problem
- Add their suggestion verbatim
-
"I didn't see section Y"
- Organization problem
- Make key points more prominent
- Add foundational principle early
When Skill is Bulletproof
Signs of bulletproof skill:
- Agent chooses correct option under maximum pressure
- Agent cites skill sections as justification
- Agent acknowledges temptation but follows rule anyway
- Meta-testing reveals "skill was clear, I should follow it"
Not bulletproof if:
- Agent finds new rationalizations
- Agent argues skill is wrong
- Agent creates "hybrid approaches"
- Agent asks permission but argues strongly for violation
Example: TDD Skill Bulletproofing
Initial Test (Failed)
Scenario: 200 lines done, forgot TDD, exhausted, dinner plans
Agent chose: C (write tests after)
Rationalization: "Tests after achieve same goals"
Iteration 1 - Add Counter
Added section: "Why Order Matters"
Re-tested: Agent STILL chose C
New rationalization: "Spirit not letter"
Iteration 2 - Add Foundational Principle
Added: "Violating letter is violating spirit"
Re-tested: Agent chose A (delete it)
Cited: New principle directly
Meta-test: "Skill was clear, I should follow it"
Bulletproof achieved.
Testing Checklist (TDD for Skills)
Before deploying skill, verify you followed RED-GREEN-REFACTOR:
RED Phase:
- Created pressure scenarios (3+ combined pressures)
- Ran scenarios WITHOUT skill (baseline)
- Documented agent failures and rationalizations verbatim
GREEN Phase:
- Wrote skill addressing specific baseline failures
- Ran scenarios WITH skill
- Agent now complies
REFACTOR Phase:
- Identified NEW rationalizations from testing
- Added explicit counters for each loophole
- Updated rationalization table
- Updated red flags list
- Updated description ith violation symptoms
- Re-tested - agent still complies
- Meta-tested to verify clarity
- Agent follows rule under maximum pressure
Common Mistakes (Same as TDD)
❌ Writing skill before testing (skipping RED) Reveals what YOU think needs preventing, not what ACTUALLY needs preventing. ✅ Fix: Always run baseline scenarios first.
❌ Not watching test fail properly Running only academic tests, not real pressure scenarios. ✅ Fix: Use pressure scenarios that make agent WANT to violate.
❌ Weak test cases (single pressure) Agents resist single pressure, break under multiple. ✅ Fix: Combine 3+ pressures (time + sunk cost + exhaustion).
❌ Not capturing exact failures "Agent was wrong" doesn't tell you what to prevent. ✅ Fix: Document exact rationalizations verbatim.
❌ Vague fixes (adding generic counters) "Don't cheat" doesn't work. "Don't keep as reference" does. ✅ Fix: Add explicit negations for each specific rationalization.
❌ Stopping after first pass Tests pass once ≠ bulletproof. ✅ Fix: Continue REFACTOR cycle until no new rationalizations.
Quick Reference (TDD Cycle)
| TDD Phase | Skill Testing | Success Criteria |
|---|---|---|
| RED | Run scenario without skill | Agent fails, document rationalizations |
| Verify RED | Capture exact wording | Verbatim documentation of failures |
| GREEN | Write skill addressing failures | Agent now complies with skill |
| Verify GREEN | Re-test scenarios | Agent follows rule under pressure |
| REFACTOR | Close loopholes | Add counters for new rationalizations |
| Stay GREEN | Re-verify | Agent still complies after refactoring |
The Bottom Line
Skill creation IS TDD. Same principles, same cycle, same benefits.
If you wouldn't write code without tests, don't write skills without testing them on agents.
RED-GREEN-REFACTOR for documentation works exactly like RED-GREEN-REFACTOR for code.
Real-World Impact
From applying TDD to TDD skill itself (2025-10-03):
- 6 RED-GREEN-REFACTOR iterations to bulletproof
- Baseline testing revealed 10+ unique rationalizations
- Each REFACTOR closed specific loopholes
- Final VERIFY GREEN: 100% compliance under maximum pressure
- Same process works for any discipline-enforcing skill
Integration
Tool usage:
- Uses
Tasktool to dispatch test subagents with pressure scenarios - Uses
Readto examine skill content and examples
REQUIRED SUB-SKILL:
- core:tdd - Foundational skill defining RED-GREEN-REFACTOR cycle
Called by:
- writing-skills - REQUIRED SUB-SKILL: Use meta:writing-skills for testing before deployment (Step 5)
Pairs with:
- writing-skills - This skill provides testing methodology; writing-skills provides creation structure
Writing Skills
Overview
Writing skills IS Test-Driven Development applied to process documentation.
Personal skills live in agent-specific directories (~/.claude/skills for Claude Code, ~/.codex/skills for Codex)
You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
REQUIRED SUB-SKILL: Use core:tdd. You MUST understand the RED-GREEN-REFACTOR cycle defined there. This skill adapts TDD to documentation.
Official guidance: For Anthropic's official skill authoring best practices, see anthropic-best-practices.md. This document provides additional patterns and guidelines that complement the TDD-focused approach in this skill.
What is a Skill?
A skill is a reference guide for proven techniques, patterns, or tools. Skills help future Claude instances find and apply effective approaches.
Skills are: Reusable techniques, patterns, tools, reference guides
Skills are NOT: Narratives about how you solved a problem once
TDD Mapping for Skills
| TDD Concept | Skill Creation |
|---|---|
| Test case | Pressure scenario with subagent |
| Production code | Skill document (SKILL.md) |
| Test fails (RED) | Agent violates rule without skill (baseline) |
| Test passes (GREEN) | Agent complies with skill present |
| Refactor | Close loopholes while maintaining compliance |
| Write test first | Run baseline scenario BEFORE writing skill |
| Watch it fail | Document exact rationalizations agent uses |
| Minimal code | Write skill addressing those specific violations |
| Watch it pass | Verify agent now complies |
| Refactor cycle | Find new rationalizations → plug → re-verify |
The entire skill creation process follows RED-GREEN-REFACTOR.
When to Create a Skill
Create when:
- Technique wasn't intuitively obvious to you
- You'd reference this again across projects
- Pattern applies broadly (not project-specific)
- Others would benefit
Don't create for:
- One-off solutions
- Standard practices well-documented elsewhere
- Project-specific conventions (put in CLAUDE.md)
Skill Types
Technique
Concrete method with steps to follow (condition-wait, root-cause-tracing)
Pattern
Way of thinking about problems (flatten-with-flags, test-invariants)
Reference
API docs, syntax guides, tool documentation (office docs)
Directory Structure
skills/
skill-name/
SKILL.md # Main reference (required)
supporting-file.* # Only if needed
Flat namespace - all skills in one searchable namespace
Separate files for:
- Heavy reference (100+ lines) - API docs, comprehensive syntax
- Reusable tools - Scripts, utilities, templates
Keep inline:
- Principles and concepts
- Code patterns (< 50 lines)
- Everything else
SKILL.md Structure
Frontmatter (YAML):
- Only two fields supported:
nameanddescription - Max 1024 characters total
name: Use letters, numbers, and hyphens only (no parentheses, special chars)description: Third-person, includes BOTH what it does AND when to use it- Start with "Use when..." to focus on triggering conditions
- Include specific symptoms, situations, and contexts
- Keep under 500 characters if possible
---
name: Skill-Name-With-Hyphens
description: Use when [specific triggering conditions and symptoms] - [what the skill does and how it helps, written in third person]
---
# Skill Name
## Overview
What is this? Core principle in 1-2 sentences.
## When to Use
[Small inline flowchart IF decision non-obvious]
Bullet list with SYMPTOMS and use cases
When NOT to use
## Core Pattern (for techniques/patterns)
Before/after code comparison
## Quick Reference
Table or bullets for scanning common operations
## Implementation
Inline code for simple patterns
Link to file for heavy reference or reusable tools
## Common Mistakes
What goes wrong + fixes
## Real-World Impact (optional)
Concrete results
Claude Search Optimization (CSO)
Critical for discovery: Future Claude needs to FIND your skill
1. Rich Description Field
Purpose: Claude reads description to decide which skills to load for a given task. Make it answer: "Should I read this skill right now?"
Format: Start with "Use when..." to focus on triggering conditions, then explain what it does
Content:
- Use concrete triggers, symptoms, and situations that signal this skill applies
- Describe the problem (race conditions, inconsistent behavior) not language-specific symptoms (setTimeout, sleep)
- Keep triggers technology-agnostic unless the skill itself is technology-specific
- If skill is technology-specific, make that explicit in the trigger
- Write in third person (injected into system prompt)
# ❌ BAD: Too abstract, vague, doesn't include when to use
description: For async testing
# ❌ BAD: First person
description: I can help you with async tests when they're flaky
# ❌ BAD: Mentions technology but skill isn't specific to it
description: Use when tests use setTimeout/sleep and are flaky
# ✅ GOOD: Starts with "Use when", describes problem, then what it does
description: Use when tests have race conditions, timing dependencies, or pass/fail inconsistently - replaces arbitrary timeouts with condition polling for reliable async tests
# ✅ GOOD: Technology-specific skill with explicit trigger
description: Use when using React Router and handling authentication redirects - provides patterns for protected routes and auth state management
2. Keyword Coverage
Use words Claude would search for:
- Error messages: "Hook timed out", "ENOTEMPTY", "race condition"
- Symptoms: "flaky", "hanging", "zombie", "pollution"
- Synonyms: "timeout/hang/freeze", "cleanup/teardown/afterEach"
- Tools: Actual commands, library names, file types
3. Descriptive Naming
Use active voice, verb-first:
- ✅
creating-skillsnotskill-creation - ✅
testing-skillsnotsubagent-skill-testing
4. Token Efficiency (Critical)
Problem: getting-started and frequently-referenced skills load into EVERY conversation. Every token counts.
Target word counts:
- getting-started workflows: <150 words each
- Frequently-loaded skills: <200 words total
- Other skills: <500 words (still be concise)
Techniques:
Move details to tool help:
# ❌ BAD: Document all flags in SKILL.md
search-conversations supports --text, --both, --after DATE, --before DATE, --limit N
# ✅ GOOD: Reference --help
search-conversations supports multiple modes and filters. Run --help for details.
Use cross-references:
# ❌ BAD: Repeat workflow details
When searching, dispatch subagent with template...
[20 lines of repeated instructions]
# ✅ GOOD: Reference other skill
Always use subagents (50-100x context savings). **REQUIRED SUB-SKILL:** Use [plugin]:[skill-name] for workflow.
Compress examples:
# ❌ BAD: Verbose example (42 words)
your human partner: "How did we handle authentication errors in React Router before?"
You: I'll search past conversations for React Router authentication patterns.
[Dispatch subagent with search query: "React Router authentication error handling 401"]
# ✅ GOOD: Minimal example (20 words)
Partner: "How did we handle auth errors in React Router?"
You: Searching...
[Dispatch subagent → synthesis]
Eliminate redundancy:
- Don't repeat what's in cross-referenced skills
- Don't explain what's obvious from command
- Don't include multiple examples of same pattern
Verification:
wc -w skills/path/SKILL.md
# getting-started workflows: aim for <150 each
# Other frequently-loaded: aim for <200 total
Name by what you DO or core insight:
- ✅
testing:condition-wait>async-test-helpers - ✅
using-skillsnotskill-usage - ✅
flatten-with-flags>data-structure-refactoring - ✅
root-cause-tracing>debugging-techniques
Gerunds (-ing) work well for processes:
creating-skills,testing-skills,debugging-with-logs- Active, describes the action you're taking
4. Cross-Referencing Other Skills
When writing documentation that references other skills:
Use skill name only, with explicit requirement markers:
- ✅ Good:
**REQUIRED SUB-SKILL:** Use core:tdd - ✅ Good:
**REQUIRED SUB-SKILL:** Use debug:systematic - ❌ Bad:
See skills/testing/tdd(unclear if required) - ❌ Bad:
@skills/testing/tdd/SKILL.md(force-loads, burns context)
Why no @ links: @ syntax force-loads files immediately, consuming 200k+ context before you need them.
Flowchart Usage
digraph when_flowchart {
"Need to show information?" [shape=diamond];
"Decision where I might go wrong?" [shape=diamond];
"Use markdown" [shape=box];
"Small inline flowchart" [shape=box];
"Need to show information?" -> "Decision where I might go wrong?" [label="yes"];
"Decision where I might go wrong?" -> "Small inline flowchart" [label="yes"];
"Decision where I might go wrong?" -> "Use markdown" [label="no"];
}
Use flowcharts ONLY for:
- Non-obvious decision points
- Process loops where you might stop too early
- "When to use A vs B" decisions
Never use flowcharts for:
- Reference material → Tables, lists
- Code examples → Markdown blocks
- Linear instructions → Numbered lists
- Labels without semantic meaning (step1, helper2)
See @graphviz-conventions.dot for graphviz style rules.
Code Examples
One excellent example beats many mediocre ones
Choose most relevant language:
- Testing techniques → TypeScript/JavaScript
- System debugging → Shell/Python
- Data processing → Python
Good example:
- Complete and runnable
- Well-commented explaining WHY
- From real scenario
- Shows pattern clearly
- Ready to adapt (not generic template)
Don't:
- Implement in 5+ languages
- Create fill-in-the-blank templates
- Write contrived examples
You're good at porting - one great example is enough.
File Organization
Self-Contained Skill
defense-in-depth/
SKILL.md # Everything inline
When: All content fits, no heavy reference needed
Skill with Reusable Tool
condition-wait/
SKILL.md # Overview + patterns
example.ts # Working helpers to adapt
When: Tool is reusable code, not just narrative
Skill with Heavy Reference
pptx/
SKILL.md # Overview + workflows
pptxgenjs.md # 600 lines API reference
ooxml.md # 500 lines XML structure
scripts/ # Executable tools
When: Reference material too large for inline
The Iron Law (Same as TDD)
NO SKILL WITHOUT A FAILING TEST FIRST
This applies to NEW skills AND EDITS to existing skills.
Write skill before testing? Delete it. Start over. Edit skill without testing? Same violation.
No exceptions:
- Not for "simple additions"
- Not for "just adding a section"
- Not for "documentation updates"
- Don't keep untested changes as "reference"
- Don't "adapt" while running tests
- Delete means delete
REQUIRED SUB-SKILL: Use core:tdd. That skill explains why this matters. Same principles apply to documentation.
Testing All Skill Types
Different skill types need different test approaches:
Discipline-Enforcing Skills (rules/requirements)
Examples: TDD, verification, designing-before-coding
Test with:
- Academic questions: Do they understand the rules?
- Pressure scenarios: Do they comply under stress?
- Multiple pressures combined: time + sunk cost + exhaustion
- Identify rationalizations and add explicit counters
Success criteria: Agent follows rule under maximum pressure
Technique Skills (how-to guides)
Examples: condition-wait, root-cause-tracing, defensive-programming
Test with:
- Application scenarios: Can they apply the technique correctly?
- Variation scenarios: Do they handle edge cases?
- Missing information tests: Do instructions have gaps?
Success criteria: Agent successfully applies technique to new scenario
Pattern Skills (mental models)
Examples: reducing-complexity, information-hiding concepts
Test with:
- Recognition scenarios: Do they recognize when pattern applies?
- Application scenarios: Can they use the mental model?
- Counter-examples: Do they know when NOT to apply?
Success criteria: Agent correctly identifies when/how to apply pattern
Reference Skills (documentation/APIs)
Examples: API documentation, command references, library guides
Test with:
- Retrieval scenarios: Can they find the right information?
- Application scenarios: Can they use what they found correctly?
- Gap testing: Are common use cases covered?
Success criteria: Agent finds and correctly applies reference information
Common Rationalizations for Skipping Testing
| Excuse | Reality |
|---|---|
| "Skill is obviously clear" | Clear to you ≠ clear to other agents. Test it. |
| "It's just a reference" | References can have gaps, unclear sections. Test retrieval. |
| "Testing is overkill" | Untested skills have issues. Always. 15 min testing saves hours. |
| "I'll test if problems emerge" | Problems = agents can't use skill. Test BEFORE deploying. |
| "Too tedious to test" | Testing is less tedious than debugging bad skill in production. |
| "I'm confident it's good" | Overconfidence guarantees issues. Test anyway. |
| "Academic review is enough" | Reading ≠ using. Test application scenarios. |
| "No time to test" | Deploying untested skill wastes more time fixing it later. |
All of these mean: Test before deploying. No exceptions.
Bulletproofing Skills Against Rationalization
Skills that enforce discipline (like TDD) need to resist rationalization. Agents are smart and will find loopholes when under pressure.
Psychology note: Understanding WHY persuasion techniques work helps you apply them systematically. See persuasion-principles.md for research foundation (Cialdini, 2021; Meincke et al., 2025) on authority, commitment, scarcity, social proof, and unity principles.
Close Every Loophole Explicitly
Don't just state the rule - forbid specific workarounds:
```markdown Write code before test? Delete it. ``` ```markdown Write code before test? Delete it. Start over.No exceptions:
- Don't keep it as "reference"
- Don't "adapt" it while writing tests
- Don't look at it
- Delete means delete
</Good>
### Address "Spirit vs Letter" Arguments
Add foundational principle early:
```markdown
**Violating the letter of the rules is violating the spirit of the rules.**
This cuts off entire class of "I'm following the spirit" rationalizations.
Build Rationalization Table
Capture rationalizations from baseline testing (see Testing section below). Every excuse agents make goes in the table:
| Excuse | Reality |
|--------|---------|
| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |
| "I'll test after" | Tests passing immediately prove nothing. |
| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |
Create Red Flags List
Make it easy for agents to self-check when rationalizing:
## Red Flags - STOP and Start Over
- Code before test
- "I already manually tested it"
- "Tests after achieve the same purpose"
- "It's about spirit not ritual"
- "This is different because..."
**All of these mean: Delete code. Start over with TDD.**
Update CSO for Violation Symptoms
Add to description: symptoms of when you're ABOUT to violate the rule:
description: use when implementing any feature or bugfix, before writing implementation code
RED-GREEN-REFACTOR for Skills
Follow the TDD cycle:
RED: Write Failing Test (Baseline)
Run pressure scenario with subagent WITHOUT the skill. Document exact behavior:
- What choices did they make?
- What rationalizations did they use (verbatim)?
- Which pressures triggered violations?
This is "watch the test fail" - you must see what agents naturally do before writing the skill.
GREEN: Write Minimal Skill
Write skill that addresses those specific rationalizations. Don't add extra content for hypothetical cases.
Run same scenarios WITH skill. Agent should now comply.
REFACTOR: Close Loopholes
Agent found new rationalization? Add explicit counter. Re-test until bulletproof.
REQUIRED SUB-SKILL: Use meta:testing-skills for the complete testing methodology:
- How to write pressure scenarios
- Pressure types (time, sunk cost, authority, exhaustion)
- Plugging holes systematically
- Meta-testing techniques
Anti-Patterns
❌ Narrative Example
"In session 2025-10-03, we found empty projectDir caused..." Why bad: Too specific, not reusable
❌ Multi-Language Dilution
example-js.js, example-py.py, example-go.go Why bad: Mediocre quality, maintenance burden
❌ Code in Flowcharts
step1 [label="import fs"];
step2 [label="read file"];
Why bad: Can't copy-paste, hard to read
❌ Generic Labels
helper1, helper2, step3, pattern4 Why bad: Labels should have semantic meaning
STOP: Before Moving to Next Skill
After writing ANY skill, you MUST STOP and complete the deployment process.
Do NOT:
- Create multiple skills in batch without testing each
- Move to next skill before current one is verified
- Skip testing because "batching is more efficient"
The deployment checklist below is MANDATORY for EACH skill.
Deploying untested skills = deploying untested code. It's a violation of quality standards.
Skill Creation Checklist (TDD Adapted)
IMPORTANT: Use TodoWrite to create todos for EACH checklist item below.
RED Phase - Write Failing Test:
- Create pressure scenarios (3+ combined pressures for discipline skills)
- Run scenarios WITHOUT skill - document baseline behavior verbatim
- Identify patterns in rationalizations/failures
GREEN Phase - Write Minimal Skill:
- Name uses only letters, numbers, hyphens (no parentheses/special chars)
- YAML frontmatter with only name and description (max 1024 chars)
- Description starts with "Use when..." and includes specific triggers/symptoms
- Description written in third person
- Keywords throughout for search (errors, symptoms, tools)
- Clear overview with core principle
- Address specific baseline failures identified in RED
- Code inline OR link to separate file
- One excellent example (not multi-language)
- Run scenarios WITH skill - verify agents now comply
REFACTOR Phase - Close Loopholes:
- Identify NEW rationalizations from testing
- Add explicit counters (if discipline skill)
- Build rationalization table from all test iterations
- Create red flags list
- Re-test until bulletproof
Quality Checks:
- Small flowchart only if decision non-obvious
- Quick reference table
- Common mistakes section
- No narrative storytelling
- Supporting files only for tools or heavy reference
Deployment:
- Commit skill to git and push to your fork (if configured)
- Consider contributing back via PR (if broadly useful)
Discovery Workflow
How future Claude finds your skill:
- Encounters problem ("tests are flaky")
- Finds SKILL (description matches)
- Scans overview (is this relevant?)
- Reads patterns (quick reference table)
- Loads example (only when implementing)
Optimize for this flow - put searchable terms early and often.
The Bottom Line
Creating skills IS TDD for process documentation.
Same Iron Law: No skill without failing test first. Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes). Same benefits: Better quality, fewer surprises, bulletproof results.
If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation.
Commands 1
Analyze plugins in the marketplace to identify quality improvements.
Scope:
- If no argument provided, analyze all plugins in
plugins/directory - If plugin name provided ($ARGUMENTS), analyze only that plugin
Process:
-
Load the methodology: Use
Skilltool withskill: "meta:marketplace-analysis" -
Analyze the plugin(s): Read all plugin components (skills, agents, commands, hooks) and apply the methodology.
-
Present findings as prioritized actionable todos with validation approach for each.
-
If user requests changes:
- Apply improvements using Edit tool
- MANDATORY: Use
Skilltool withskill: "core:verification"before claiming changes are complete - Run validation commands and report evidence
Agents 3
You are a Capability Analyzer specializing in Claude Code feature usage and best practices.
Core Responsibilities
- Evaluate how well plugins leverage Claude Code capabilities
- Identify underutilized or misused features
- Consult documentation for latest best practices
- Recommend improvements aligned with "the Anthropic way"
Analysis Dimensions
Hooks
- Correct event types (PreToolUse, PostToolUse, Stop, etc.)
- Appropriate prompt vs command hooks
- Sensible timeout values
- Use of $CLAUDE_PLUGIN_ROOT for portability
Agents
- Clear triggering conditions with examples
- Appropriate model selection (inherit vs specific)
- Sensible tool restrictions (least privilege)
Skills
- Imperative descriptions with trigger phrases
- Progressive disclosure (lean SKILL.md, details in references/)
- SKILL.md under 500 lines
Commands
- Clear argument handling
- Integration with skills/agents
Analysis Process
- Inventory feature usage via Glob
- Consult documentation via
claude-code-guidesubagent - Gap analysis - compare current vs available features
- Prioritize recommendations by impact and effort
Output Format
## Capability Analysis Findings
### Hook Usage
| Plugin | Events Used | Issues | Recommendations |
### Agent Configuration
| Agent | Model | Tools | Issues | Recommendations |
### Feature Adoption Gaps
1. [Unused feature]: [Why it would help] - [How to adopt]
### Best Practice Violations
- [Pattern]: [Current] vs [Recommended]
Quality Standards
- Always consult docs before claiming something is "wrong"
- Cite specific documentation for recommendations
- Distinguish "must fix" from "could improve"
- Recommend incremental changes over rewrites
You are the Marketplace Analysis Orchestrator, coordinating comprehensive plugin quality analysis.
Core Responsibilities
- Perform initial reconnaissance of plugins/ directory
- Launch specialized analyzers in parallel
- Synthesize findings into prioritized actionable todos
- Ensure all improvements are validated before claiming "better"
Analysis Process
1. Quick Scan (do this yourself first)
- Count plugins and their components
- Note obvious issues (large files, naming inconsistencies)
- Identify scope for detailed analysis
2. Parallel Analysis (launch via Task tool)
Launch BOTH analyzers in a single message for parallel execution:
Use Task tool with subagent_type='meta:structure-analyzer':
- Analyze trigger phrases, discoverability, component design
- Find redundancy and duplication
- Identify simplification opportunities
Use Task tool with subagent_type='meta:capability-analyzer':
- Evaluate Claude Code feature usage
- Check against latest best practices
- Find underutilized capabilities
3. Synthesis
- Collect findings from both analyzers
- Remove duplicates and contradictions
- Prioritize by impact and effort
- Format as actionable todos
Output Format
## Analysis Summary
- Plugins analyzed: X
- Components analyzed: Y skills, Z agents, W commands
- Overall quality: [assessment]
## Priority 1: High Impact, Low Effort
- [ ] [Change] - [Why] - [Expected impact] - [How to validate]
## Priority 2: Medium Impact
...
## Priority 3: Consider Later
...
Quality Standards
- Never claim "better" without evidence
- Always include validation approach
- Apply anti-overengineering checks before recommending additions
- Focus on deletion and simplification over addition
- Consult
references/quality-standards.mdfor detailed criteria
When Applying Changes
If implementing improvements (not just analyzing):
- Use
core:verificationskill before claiming complete - Run validation commands and report actual output
- Never claim "improved" without evidence
You are a Structure Analyzer specializing in Claude Code plugin design, DX, and architecture.
Core Responsibilities
- Evaluate trigger phrase quality (imperative form, specific phrases)
- Assess discoverability of plugin features
- Check for redundancy and duplication across plugins
- Find simplification opportunities
Analysis Dimensions
DX (Developer Experience)
- Trigger quality: Imperative form, specific phrases, multiple entry points
- Discoverability: Can users find the right component?
- Documentation: Purpose clear, working examples, progressive disclosure
Architecture
- Component design: Single responsibility, appropriate granularity
- Redundancy: Same patterns in multiple places?
- Elegance: Simplest solution that works?
- Reference integrity: All referenced files exist? Orphaned files?
Analysis Process
-
Inventory components:
Glob: plugins/*/skills/*/SKILL.mdGlob: plugins/*/agents/*.mdGlob: plugins/*/commands/*.md
-
Evaluate structure:
- Count components per plugin
- Measure file sizes (flag >500 lines)
- Note naming patterns
-
Find issues:
- Grep for similar content
- Compare component purposes
- Identify overlap and gaps
-
Validate references:
- Extract paths from SKILL.md (references/, scripts/, markdown links)
- Check each referenced file exists
- Find orphaned files (exist but never referenced)
Output Format
## Structure Analysis Findings
### Overview
| Plugin | Skills | Agents | Commands | Total Lines |
|--------|--------|--------|----------|-------------|
### Trigger Quality Issues
| Component | Issue | Suggested Fix |
|-----------|-------|---------------|
### Redundancy Issues
| Location A | Location B | Overlap | Resolution |
|------------|------------|---------|------------|
### Simplification Opportunities
1. [Merge/Delete] - [Evidence] - [Impact]
### Reference Integrity
| Skill | Broken References | Orphaned Files |
|-------|-------------------|----------------|
### Metrics
- Total plugins: X
- Largest file: [name] (N lines)
- Potential reduction: N lines
Quality Standards
- Cite specific examples, not vague observations
- Quantify everything possible
- Prefer deletion over addition
- Verify via
references/quality-standards.mdfor criteria
Sponsors
Details
- Marketplace
- pproenca/dot-claude-old
- Source
- plugins/specialized/meta
- Category
- Community
- License
- MIT
- Keywords
- plugin-development, skills, marketplace, meta
