play-skill-authoring

name	play-skill-authoring
description	Explicit-invocation workflow for TDD-style skill authoring with subagent pressure scenarios for baseline testing and loophole closure. Use only when the user explicitly invokes `play-skill-authoring` or an owning workflow explicitly requires skill-authoring verification.
codex_sidecar	{"policy":{"allow_implicit_invocation":false}}

Writing Skills

Invocation Policy

This workflow is explicit-invocation-only. Do not select it from ordinary discussion, review-shaped text, possible behavior-change wording, or implementation-adjacent language. Run it only when the user explicitly invokes play-skill-authoring or when an owning workflow explicitly hands off to play-skill-authoring.

Overview

Writing skills IS Test-Driven Development applied to process documentation.

Personal skills live in each target's configured skills directory; shared source skills belong in the repository skills/ tree

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.

When dispatching pressure-scenario subagents, use subagent-lifecycle for the controller-local lifecycle ledger, target lifecycle capability classification, cleanup gate before spawns, target-honest cleanup outcomes, and slot-limit recovery. Capture each pressure-scenario subagent's prompt, baseline/pass result, observed rationalizations, and pressure conditions before closing or superseding the session.

REQUIRED BACKGROUND: You MUST understand play-tdd before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation.

Official guidance: For Anthropic's official skill authoring best practices, see references/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 agents 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 the repository's agent guidance file)
• Mechanical constraints (if it's enforceable with regex/validation, automate it—save documentation for judgment calls)

Skill Types

Technique

Concrete method with steps to follow (condition-based-waiting, 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:

1. Heavy reference (100+ lines) - API docs, comprehensive syntax
2. Reusable tools - Scripts, utilities, templates

Keep inline:

• Principles and concepts
• Code patterns (< 50 lines)
• Everything else

SKILL.md Structure

Frontmatter (YAML):

• Authoritative schema for this repo: docs/specs/skills.md and SkillSourceSchema in src/config/schema.ts. Frontmatter is .strict() — unknown top-level keys are rejected.
• Upstream agentskills.io/specification is supplementary; fields it lists that are not in SkillSourceSchema will fail validation here.
• Two required fields: name and description.
• name: lowercase letters, digits, and hyphens only; 2–64 chars (the regex's two boundary chars plus {0,62} middle); matches ^[a-z0-9][a-z0-9-]{0,62}[a-z0-9]$.
• description: ≤ 1024 chars; no < or >; third-person; names what the skill does and when to use it.
  • Lead with the capability — a third-person declarative clause naming what the skill does.
  • Follow with "Use when…" — concrete triggers, symptoms, artifacts, or user phrases.
  • Do not encode procedural detail (step counts, ordered sequences, decision branches). That belongs in the body; see SSO section below for rationale.
  • For sibling-prone skills, add "Do not use when…" or a contrastive cue.
  • Keep under 500 chars if possible. Authoritative spec: docs/specs/skills.md § Description style.

---
name: skill-name-with-hyphens
description: <Capability — what the skill does>. Use when <triggering conditions, symptoms, artifacts, or user phrases>.
---

# 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

Skill Search Optimization (SSO)

Critical for discovery: Future agents need to FIND your skill

1. Rich Description Field

Purpose: Both Claude and Codex pre-load the description into context and use it to decide whether to read the skill body for a given task. The description has to do two jobs at once: name the capability so it can be picked over siblings, and name the trigger so it fires at the right moment.

Format: name what the skill does, then when to use it. Third person.

description: <Capability — what the skill does>. Use when <triggering conditions, symptoms, artifacts, user phrases>.

Why both halves:

• What disambiguates this skill from siblings with overlapping triggers. In a 100-skill catalog, "Use when reviewing code" matches three skills; "Multi-agent review of uncommitted local changes. Use when reviewing a branch before a PR…" matches one.
• When ensures the skill fires at the right moment, with concrete user-visible symptoms (error messages, file extensions, phrases) rather than abstract notions.

This matches what Anthropic's official skill-authoring guide and the anthropics/skills repo prescribe, and what Codex's skill-creator skill prescribes. The shared description is rendered into both targets — what+when is the only style safe across the pipeline.

Examples:

# ❌ Trigger-only — omits the "what", can't disambiguate from sibling skills
description: Use when implementing any feature or bugfix.

# ❌ First/second person
description: I can help you with async tests when they're flaky.

# ❌ Vague — no concrete triggers
description: Helps with documents.

# ❌ Technology-specific symptom for a non-technology-specific skill
description: Race-condition fixes. Use when tests use setTimeout/sleep and are flaky.

# ✅ What + when, third person
description: Test-driven development discipline for tests-before-implementation. Use when implementing any feature or bugfix, before writing implementation code.

# ✅ What + when, problem-domain triggers
description: Async test stabilization technique using condition-based waiting. Use when tests have race conditions, timing dependencies, or pass/fail inconsistently.

# ✅ Technology-specific skill with explicit trigger
description: Authentication redirect handling for React Router. Use when working with React Router authentication flows or when redirects misbehave after login.

Caveat: don't bake the procedure into the description

The description must name capability and trigger. It must not summarize the procedure — step counts, stage names, decision branches — because the model can read a procedural one-liner and skip the body that owns the actual logic.

This is a typed risk, not a blanket ban: name what the skill is for, not how it works.

# ❌ Procedural — encodes "two-stage review" into the description
description: Dispatches a subagent per task with spec-then-quality review between tasks. Use when executing plans.

# ✅ Capability + trigger; the procedure stays in the body
description: Executes an implementation plan by dispatching a fresh subagent per independent task. Use when running a written plan whose tasks have no shared state.

Red flag — rewrite if the description contains:

• A count: "two reviews", "three stages", "five steps".
• An ordered sequence: "first… then…", "before X, after Y".
• A branching word: "when X do Y, otherwise Z".
• First or second person: "I", "you", "we".

Content rules:

• Third person — no "I", "you", "we".
• Start the what clause with a declarative verb ("Executes…", "Reviews…", "Generates…") — not "This skill…".
• Lead the when clause with "Use when…".
• Use concrete, searchable triggers — error messages, file extensions, user phrases — not abstract categories.
• Describe the problem domain (race conditions, inconsistent behavior), not language-specific symptoms (setTimeout, sleep), unless the skill itself is technology-specific.
• For sibling-prone skills, add "Do not use when…" or a contrastive cue.
• ≤ 500 chars when possible (1024 hard cap, no < / >).

2. Keyword Coverage

Use words an agent 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-skills not skill-creation
• ✅ condition-based-waiting not async-test-helpers

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: Use [other-skill-name] for workflow.

Compress examples:

# ❌ BAD: Verbose example (42 words)

the user: "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:

• ✅ condition-based-waiting > async-test-helpers
• ✅ using-skills not skill-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 play-tdd
• ✅ Good: **REQUIRED BACKGROUND:** You MUST understand play-debug
• ❌ Bad: See skills/testing/test-driven-development (unclear if required)
• ❌ Bad: @skills/testing/test-driven-development/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 references/graphviz-conventions.dot for graphviz style rules.

Visualizing for the user: Use scripts/render-graphs.js to render a skill's flowcharts to SVG:

./scripts/render-graphs.js ../some-skill           # Each diagram separately
./scripts/render-graphs.js ../some-skill --combine # All diagrams in one SVG

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-based-waiting/
  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 Rule (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 BACKGROUND: The play-tdd 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-before-completion, 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-based-waiting, 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 references/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 SSO for Violation Symptoms

Add to the Use when… clause: symptoms of when the rule is ABOUT to be violated. The capability half stays the same; the trigger half names the moments where discipline tends to slip.

description: Test-driven development discipline for tests-before-implementation. 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.

Testing methodology: See references/testing-skills-with-subagents.md 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 is lowercase letters, digits, and hyphens; 2–64 chars (regex in the Frontmatter section above)
• YAML frontmatter with required name and description (authoritative schema in docs/specs/skills.md)
• Description names what the skill does (third-person declarative clause: "Executes…", "Reviews…", "Generates…")
• Description names when to use it ("Use when…" with concrete triggers — symptoms, artifacts, user phrases, error messages)
• Description is third person — no "I", "you", "we"
• Description does NOT encode procedural detail (no step counts, ordered sequences "first…then…", or decision branches)
• Sibling-prone skill? Description includes "Do not use when…" or a contrastive cue against the nearest sibling
• Description ≤ 500 chars (1024 hard cap), contains no < or >
• Keywords throughout the body 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:

• Run devcanon validate to verify skill structure
• Commit skill to git and push to your fork (if configured)
• Consider contributing back via PR (if broadly useful)

Discovery Workflow

How future agents find your skill:

1. Encounters problem ("tests are flaky")
2. Finds SKILL (description matches)
3. Scans overview (is this relevant?)
4. Reads patterns (quick reference table)
5. 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 rule: 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.