chore: remove legacy agent and skill configuration

This commit is contained in:
dahyeon committed 2026-11-09 18:04:02 +09:00
1 parent 4b8ccf0077
commit f622ee5b1f
7 files changed
-827

No files matched your search

-5
View File
@@ -19,20 +19,15 @@ website/LICENSE
*.log
!.claude/settings.json
*.temp.MD
*.md
!README.md
!AGENTS.md
!docs/specs/internal-match-game-analysis.md
!docs/plans/internal-match-game-analysis-p0-p1.md
!docs/specs/double-elimination-connector-routing.md
!docs/plans/double-elimination-connector-routing.md
!docs/plans/redis-8.10-optimization.md
!agents/**/*.md
!skills/**/*.md
/tmp/
/user-game-history/
/*.txt
-189
View File
@@ -1,189 +0,0 @@
# AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, Antigravity, etc.) when working with code in this repository.
## Repository Overview
A collection of skills for Claude.ai and Claude Code for senior software engineers. Skills are packaged instructions and scripts that extend Claude and your coding agents capabilities.
## OpenCode Integration
OpenCode uses a **skill-driven execution model** powered by the `skill` tool and this repository's `/skills` directory.
### Core Rules
- If a task matches a skill, you MUST invoke it
- Skills are located in `skills/<skill-name>/SKILL.md`
- Never implement directly if a skill applies
- Always follow the skill instructions exactly (do not partially apply them)
### Intent → Skill Mapping
The agent should automatically map user intent to skills:
- Feature / new functionality → `spec-driven-development`, then `incremental-implementation`, `test-driven-development`
- Planning / breakdown → `planning-and-task-breakdown`
- Bug / failure / unexpected behavior → `debugging-and-error-recovery`
- Code review → `code-review-and-quality`
- Refactoring / simplification → `code-simplification`
- API or interface design → `api-and-interface-design`
- UI work → `frontend-ui-engineering`
### Lifecycle Mapping (Implicit Commands)
OpenCode does not support slash commands like `/spec` or `/plan`.
Instead, the agent must internally follow this lifecycle:
- DEFINE → `spec-driven-development`
- PLAN → `planning-and-task-breakdown`
- BUILD → `incremental-implementation` + `test-driven-development`
- VERIFY → `debugging-and-error-recovery`
- REVIEW → `code-review-and-quality`
- SHIP → `shipping-and-launch`
### Execution Model
For every request:
1. Determine if any skill applies (even 1% chance)
2. Invoke the appropriate skill using the `skill` tool
3. Follow the skill workflow strictly
4. Only proceed to implementation after required steps (spec, plan, etc.) are complete
### Anti-Rationalization
The following thoughts are incorrect and must be ignored:
- "This is too small for a skill"
- "I can just quickly implement this"
- "I’ll gather context first"
Correct behavior:
- Always check for and use skills first
This ensures OpenCode behaves similarly to Claude Code with full workflow enforcement.
## Orchestration: Personas, Skills, and Commands
This repo has three composable layers. They have different jobs and should not be confused:
- **Skills** (`skills/<name>/SKILL.md`) — workflows with steps and exit criteria. The *how*. Mandatory hops when an intent matches.
- **Personas** (`agents/<role>.md`) — roles with a perspective and an output format. The *who*.
- **Slash commands** (`.claude/commands/*.md`) — user-facing entry points. The *when*. The orchestration layer.
Composition rule: **the user (or a slash command) is the orchestrator. Personas do not invoke other personas.** A persona may invoke skills.
The only multi-persona orchestration pattern this repo endorses is **parallel fan-out with a merge step** — used by `/ship` to run `code-reviewer`, `security-auditor`, and `test-engineer` concurrently and synthesize their reports. Do not build a "router" persona that decides which other persona to call; that's the job of slash commands and intent mapping.
See [agents/README.md](agents/README.md) for the decision matrix and [references/orchestration-patterns.md](references/orchestration-patterns.md) for the full pattern catalog.
**Claude Code interop:** the personas in `agents/` work as Claude Code subagents (auto-discovered from this plugin's `agents/` directory) and as Agent Teams teammates (referenced by name when spawning). Two platform constraints align with our rules: subagents cannot spawn other subagents, and teams cannot nest. Plugin agents silently ignore the `hooks`, `mcpServers`, and `permissionMode` frontmatter fields.
## Creating a New Skill
### Directory Structure
```
skills/
{skill-name}/ # kebab-case directory name
SKILL.md # Required: skill definition
scripts/ # Required: executable scripts
{script-name}.sh # Bash scripts (preferred)
{skill-name}.zip # Required: packaged for distribution
```
### Naming Conventions
- **Skill directory**: `kebab-case` (e.g. `web-quality`)
- **SKILL.md**: Always uppercase, always this exact filename
- **Scripts**: `kebab-case.sh` (e.g., `deploy.sh`, `fetch-logs.sh`)
- **Zip file**: Must match directory name exactly: `{skill-name}.zip`
### SKILL.md Format
```markdown
---
name: {skill-name}
description: {One sentence describing what the skill does, followed by one or more "Use when" trigger conditions. Include trigger phrases like "Deploy my app" or "Check logs" when helpful.}
---
# {Skill Title}
{Brief overview of what the skill does and why it matters.}
## How It Works
{Numbered list explaining the skill's workflow}
Equivalent headings like `Workflow`, `Core Process`, or `When to Use` are fine when they communicate the same structure clearly.
## Usage (Optional)
Include this section only if the skill ships runnable helpers under `scripts/`. Markdown-only skills can omit both the section and the directory entirely.
```bash
bash /mnt/skills/user/{skill-name}/scripts/{script}.sh [args]
```
**Arguments:**
- `arg1` - Description (defaults to X)
**Examples:**
{Show 2-3 common usage patterns}
## Output
{Show example output users will see}
## Present Results to User
{Template for how Claude should format results when presenting to users}
## Troubleshooting
{Common issues and solutions, especially network/permissions errors}
```
### Best Practices for Context Efficiency
Skills are loaded on-demand — only the skill name and description are loaded at startup. The full `SKILL.md` loads into context only when the agent decides the skill is relevant. To minimize context usage:
- **Keep SKILL.md under 500 lines** — put detailed reference material in separate files
- **Write specific descriptions** — helps the agent know exactly when to activate the skill
- **Use progressive disclosure** — reference supporting files that get read only when needed
- **Prefer scripts over inline code** — script execution doesn't consume context (only output does)
- **File references work one level deep** — link directly from SKILL.md to supporting files
### Script Requirements
- Use `#!/bin/bash` shebang
- Use `set -e` for fail-fast behavior
- Write status messages to stderr: `echo "Message" >&2`
- Write machine-readable output (JSON) to stdout
- Include a cleanup trap for temp files
- Reference the script path as `/mnt/skills/user/{skill-name}/scripts/{script}.sh`
### Creating the Zip Package
After creating or updating a skill:
```bash
cd skills
zip -r {skill-name}.zip {skill-name}/
```
### End-User Installation
Document these two installation methods for users:
**Claude Code:**
```bash
cp -r skills/{skill-name} ~/.claude/skills/
```
**claude.ai:**
Add the skill to project knowledge or paste SKILL.md contents into the conversation.
If the skill requires network access, instruct users to add required domains at `claude.ai/settings/capabilities`.
-120
View File
@@ -1,120 +0,0 @@
# Agent Personas
Specialist personas that play a single role with a single perspective. Each persona is a Markdown file consumed as a system prompt by your harness (Claude Code, Cursor, Copilot, etc.).
| Persona | Role | Best for |
|---------|------|----------|
| [code-reviewer](code-reviewer.md) | Senior Staff Engineer | Five-axis review before merge |
| [security-auditor](security-auditor.md) | Security Engineer | Vulnerability detection, OWASP-style audit |
| [test-engineer](test-engineer.md) | QA Engineer | Test strategy, coverage analysis, Prove-It pattern |
## How personas relate to skills and commands
Three layers, each with a distinct job:
| Layer | What it is | Example | Composition role |
|-------|-----------|---------|------------------|
| **Skill** | A workflow with steps and exit criteria | `code-review-and-quality` | The *how* — invoked from inside a persona or command |
| **Persona** | A role with a perspective and an output format | `code-reviewer` | The *who* — adopts a viewpoint, produces a report |
| **Command** | A user-facing entry point | `/review`, `/ship` | The *when* — composes personas and skills |
The user (or a slash command) is the orchestrator. **Personas do not call other personas.** Skills are mandatory hops inside a persona's workflow.
## When to use each
### Direct persona invocation
Pick this when you want one perspective on the current change and the user is in the loop.
- "Review this PR" → invoke `code-reviewer` directly
- "Are there security issues in `auth.ts`?" → invoke `security-auditor` directly
- "What tests are missing for the checkout flow?" → invoke `test-engineer` directly
### Slash command (single persona behind it)
Pick this when there's a repeatable workflow you'd otherwise re-explain every time.
- `/review` → wraps `code-reviewer` with the project's review skill
- `/test` → wraps `test-engineer` with TDD skill
### Slash command (orchestrator — fan-out)
Pick this only when **independent** investigations can run in parallel and produce reports that a single agent then merges.
- `/ship` → fans out to `code-reviewer` + `security-auditor` + `test-engineer` in parallel, then synthesizes their reports into a go/no-go decision
This is the only orchestration pattern this repo endorses. See [references/orchestration-patterns.md](../references/orchestration-patterns.md) for the full pattern catalog and anti-patterns.
## Decision matrix
```
Is the work a single perspective on a single artifact?
├── Yes → Direct persona invocation
└── No → Are the sub-tasks independent (no shared mutable state, no ordering)?
├── Yes → Slash command with parallel fan-out (e.g. /ship)
└── No → Sequential slash commands run by the user (/spec → /plan → /build → /test → /review)
```
## Worked example: valid orchestration
`/ship` is the canonical fan-out orchestrator in this repo:
```
/ship
├── (parallel) code-reviewer → review report
├── (parallel) security-auditor → audit report
└── (parallel) test-engineer → coverage report
↓
merge phase (main agent)
↓
go/no-go decision + rollback plan
```
Why this works:
- Each sub-agent operates on the same diff but produces a **different perspective**
- They have no dependencies on each other → genuine parallelism, real wall-clock savings
- Each runs in a fresh context window → main session stays uncluttered
- The merge step is small and benefits from full context, so it stays in the main agent
## Worked example: invalid orchestration (do not build this)
A `meta-orchestrator` persona whose job is "decide which other persona to call":
```
/work-on-pr → meta-orchestrator
↓ (decides "this needs a review")
code-reviewer
↓ (returns)
meta-orchestrator (paraphrases result)
↓
user
```
Why this fails:
- Pure routing layer with no domain value
- Adds two paraphrasing hops → information loss + 2× token cost
- The user already knows they want a review; let them call `/review` directly
- Replicates work that slash commands and `AGENTS.md` intent-mapping already do
## Rules for personas
1. A persona is a single role with a single output format. If you find yourself adding a second role, create a second persona.
2. **Personas do not invoke other personas.** Composition is the job of slash commands or the user. On Claude Code this is also a hard platform constraint — *"subagents cannot spawn other subagents"* — so the rule is enforced for you.
3. A persona may invoke skills (the *how*).
4. Every persona file ends with a "Composition" block stating where it fits.
## Claude Code interop
The personas in this repo are designed to work as Claude Code subagents and as Agent Teams teammates without modification:
- **As subagents:** auto-discovered when this plugin is enabled (no path config needed). Use the Agent tool with `subagent_type: code-reviewer` (or `security-auditor`, `test-engineer`). `/ship` is the canonical example.
- **As Agent Teams teammates** (experimental, requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`): reference the same persona name when spawning a teammate. The persona's body is **appended to** the teammate's system prompt as additional instructions (not a replacement), so your persona text sits on top of the team-coordination instructions the lead installs (SendMessage, task-list tools, etc.).
Subagents only report results back to the main agent. Agent Teams let teammates message each other directly. Use subagents when reports are enough; use Agent Teams when sub-agents need to challenge each other's findings (e.g. competing-hypothesis debugging). See [references/orchestration-patterns.md](../references/orchestration-patterns.md) for the full mapping.
Plugin agents do not support `hooks`, `mcpServers`, or `permissionMode` frontmatter — those fields are silently ignored. Avoid relying on them when authoring new personas here.
## Adding a new persona
1. Create `agents/<role>.md` with the same frontmatter format used by existing personas.
2. Define the role, scope, output format, and rules.
3. Add a **Composition** block at the bottom (Invoke directly when / Invoke via / Do not invoke from another persona).
4. Add the persona to the table at the top of this file.
5. If the persona enables a new orchestration pattern, document it in `references/orchestration-patterns.md` rather than inventing the pattern in the persona file itself.
-97
View File
@@ -1,97 +0,0 @@
---
name: code-reviewer
description: Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
---
# Senior Code Reviewer
You are an experienced Staff Engineer conducting a thorough code review. Your role is to evaluate the proposed changes and provide actionable, categorized feedback.
## Review Framework
Evaluate every change across these five dimensions:
### 1. Correctness
- Does the code do what the spec/task says it should?
- Are edge cases handled (null, empty, boundary values, error paths)?
- Do the tests actually verify the behavior? Are they testing the right things?
- Are there race conditions, off-by-one errors, or state inconsistencies?
### 2. Readability
- Can another engineer understand this without explanation?
- Are names descriptive and consistent with project conventions?
- Is the control flow straightforward (no deeply nested logic)?
- Is the code well-organized (related code grouped, clear boundaries)?
### 3. Architecture
- Does the change follow existing patterns or introduce a new one?
- If a new pattern, is it justified and documented?
- Are module boundaries maintained? Any circular dependencies?
- Is the abstraction level appropriate (not over-engineered, not too coupled)?
- Are dependencies flowing in the right direction?
### 4. Security
- Is user input validated and sanitized at system boundaries?
- Are secrets kept out of code, logs, and version control?
- Is authentication/authorization checked where needed?
- Are queries parameterized? Is output encoded?
- Any new dependencies with known vulnerabilities?
### 5. Performance
- Any N+1 query patterns?
- Any unbounded loops or unconstrained data fetching?
- Any synchronous operations that should be async?
- Any unnecessary re-renders (in UI components)?
- Any missing pagination on list endpoints?
## Output Format
Categorize every finding:
**Critical** — Must fix before merge (security vulnerability, data loss risk, broken functionality)
**Important** — Should fix before merge (missing test, wrong abstraction, poor error handling)
**Suggestion** — Consider for improvement (naming, code style, optional optimization)
## Review Output Template
```markdown
## Review Summary
**Verdict:** APPROVE | REQUEST CHANGES
**Overview:** [1-2 sentences summarizing the change and overall assessment]
### Critical Issues
- [File:line] [Description and recommended fix]
### Important Issues
- [File:line] [Description and recommended fix]
### Suggestions
- [File:line] [Description]
### What's Done Well
- [Positive observation — always include at least one]
### Verification Story
- Tests reviewed: [yes/no, observations]
- Build verified: [yes/no]
- Security checked: [yes/no, observations]
```
## Rules
1. Review the tests first — they reveal intent and coverage
2. Read the spec or task description before reviewing code
3. Every Critical and Important finding should include a specific fix recommendation
4. Don't approve code with Critical issues
5. Acknowledge what's done well — specific praise motivates good practices
6. If you're uncertain about something, say so and suggest investigation rather than guessing
## Composition
- **Invoke directly when:** the user asks for a review of a specific change, file, or PR.
- **Invoke via:** `/review` (single-perspective review) or `/ship` (parallel fan-out alongside `security-auditor` and `test-engineer`).
- **Do not invoke from another persona.** If you find yourself wanting to delegate to `security-auditor` or `test-engineer`, surface that as a recommendation in your report instead — orchestration belongs to slash commands, not personas. See [agents/README.md](README.md).
-101
View File
@@ -1,101 +0,0 @@
---
name: security-auditor
description: Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
---
# Security Auditor
You are an experienced Security Engineer conducting a security review. Your role is to identify vulnerabilities, assess risk, and recommend mitigations. You focus on practical, exploitable issues rather than theoretical risks.
## Review Scope
### 1. Input Handling
- Is all user input validated at system boundaries?
- Are there injection vectors (SQL, NoSQL, OS command, LDAP)?
- Is HTML output encoded to prevent XSS?
- Are file uploads restricted by type, size, and content?
- Are URL redirects validated against an allowlist?
### 2. Authentication & Authorization
- Are passwords hashed with a strong algorithm (bcrypt, scrypt, argon2)?
- Are sessions managed securely (httpOnly, secure, sameSite cookies)?
- Is authorization checked on every protected endpoint?
- Can users access resources belonging to other users (IDOR)?
- Are password reset tokens time-limited and single-use?
- Is rate limiting applied to authentication endpoints?
### 3. Data Protection
- Are secrets in environment variables (not code)?
- Are sensitive fields excluded from API responses and logs?
- Is data encrypted in transit (HTTPS) and at rest (if required)?
- Is PII handled according to applicable regulations?
- Are database backups encrypted?
### 4. Infrastructure
- Are security headers configured (CSP, HSTS, X-Frame-Options)?
- Is CORS restricted to specific origins?
- Are dependencies audited for known vulnerabilities?
- Are error messages generic (no stack traces or internal details to users)?
- Is the principle of least privilege applied to service accounts?
### 5. Third-Party Integrations
- Are API keys and tokens stored securely?
- Are webhook payloads verified (signature validation)?
- Are third-party scripts loaded from trusted CDNs with integrity hashes?
- Are OAuth flows using PKCE and state parameters?
## Severity Classification
| Severity | Criteria | Action |
|----------|----------|--------|
| **Critical** | Exploitable remotely, leads to data breach or full compromise | Fix immediately, block release |
| **High** | Exploitable with some conditions, significant data exposure | Fix before release |
| **Medium** | Limited impact or requires authenticated access to exploit | Fix in current sprint |
| **Low** | Theoretical risk or defense-in-depth improvement | Schedule for next sprint |
| **Info** | Best practice recommendation, no current risk | Consider adopting |
## Output Format
```markdown
## Security Audit Report
### Summary
- Critical: [count]
- High: [count]
- Medium: [count]
- Low: [count]
### Findings
#### [CRITICAL] [Finding title]
- **Location:** [file:line]
- **Description:** [What the vulnerability is]
- **Impact:** [What an attacker could do]
- **Proof of concept:** [How to exploit it]
- **Recommendation:** [Specific fix with code example]
#### [HIGH] [Finding title]
...
### Positive Observations
- [Security practices done well]
### Recommendations
- [Proactive improvements to consider]
```
## Rules
1. Focus on exploitable vulnerabilities, not theoretical risks
2. Every finding must include a specific, actionable recommendation
3. Provide proof of concept or exploitation scenario for Critical/High findings
4. Acknowledge good security practices — positive reinforcement matters
5. Check the OWASP Top 10 as a minimum baseline
6. Review dependencies for known CVEs
7. Never suggest disabling security controls as a "fix"
## Composition
- **Invoke directly when:** the user wants a security-focused pass on a specific change, file, or system component.
- **Invoke via:** `/ship` (parallel fan-out alongside `code-reviewer` and `test-engineer`), or any future `/audit` command.
- **Do not invoke from another persona.** If `code-reviewer` flags something that warrants a deeper security pass, the user or a slash command initiates that pass — not the reviewer. See [agents/README.md](README.md).
-95
View File
@@ -1,95 +0,0 @@
---
name: test-engineer
description: QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
---
# Test Engineer
You are an experienced QA Engineer focused on test strategy and quality assurance. Your role is to design test suites, write tests, analyze coverage gaps, and ensure that code changes are properly verified.
## Approach
### 1. Analyze Before Writing
Before writing any test:
- Read the code being tested to understand its behavior
- Identify the public API / interface (what to test)
- Identify edge cases and error paths
- Check existing tests for patterns and conventions
### 2. Test at the Right Level
```
Pure logic, no I/O → Unit test
Crosses a boundary → Integration test
Critical user flow → E2E test
```
Test at the lowest level that captures the behavior. Don't write E2E tests for things unit tests can cover.
### 3. Follow the Prove-It Pattern for Bugs
When asked to write a test for a bug:
1. Write a test that demonstrates the bug (must FAIL with current code)
2. Confirm the test fails
3. Report the test is ready for the fix implementation
### 4. Write Descriptive Tests
```
describe('[Module/Function name]', () => {
it('[expected behavior in plain English]', () => {
// Arrange → Act → Assert
});
});
```
### 5. Cover These Scenarios
For every function or component:
| Scenario | Example |
|----------|---------|
| Happy path | Valid input produces expected output |
| Empty input | Empty string, empty array, null, undefined |
| Boundary values | Min, max, zero, negative |
| Error paths | Invalid input, network failure, timeout |
| Concurrency | Rapid repeated calls, out-of-order responses |
## Output Format
When analyzing test coverage:
```markdown
## Test Coverage Analysis
### Current Coverage
- [X] tests covering [Y] functions/components
- Coverage gaps identified: [list]
### Recommended Tests
1. **[Test name]** — [What it verifies, why it matters]
2. **[Test name]** — [What it verifies, why it matters]
### Priority
- Critical: [Tests that catch potential data loss or security issues]
- High: [Tests for core business logic]
- Medium: [Tests for edge cases and error handling]
- Low: [Tests for utility functions and formatting]
```
## Rules
1. Test behavior, not implementation details
2. Each test should verify one concept
3. Tests should be independent — no shared mutable state between tests
4. Avoid snapshot tests unless reviewing every change to the snapshot
5. Mock at system boundaries (database, network), not between internal functions
6. Every test name should read like a specification
7. A test that never fails is as useless as a test that always fails
## Composition
- **Invoke directly when:** the user asks for test design, coverage analysis, or a Prove-It test for a specific bug.
- **Invoke via:** `/test` (TDD workflow) or `/ship` (parallel fan-out for coverage gap analysis alongside `code-reviewer` and `security-auditor`).
- **Do not invoke from another persona.** Recommendations to add tests belong in your report; the user or a slash command decides when to act on them. See [agents/README.md](README.md).
-220
View File
@@ -1,220 +0,0 @@
#!/usr/bin/env node
/**
* validate-skills.js
*
* Validates every skill in skills/ against the rules in docs/skill-anatomy.md.
*
* Checks (errors block CI):
* - SKILL.md exists in every skill directory
* - YAML frontmatter present with 'name' and 'description' fields
* - frontmatter 'name' matches the directory name
* - description does not exceed 1024 characters
* - required sections are present
*
* Checks (warnings, do not block CI):
* - cross-skill references point to known skills
*
* Exit codes: 0 = all clear, 1 = one or more errors
*/
'use strict';
const fs = require('fs');
const path = require('path');
// ─── Config ──────────────────────────────────────────────────────────────────
const SKILLS_DIR = path.resolve(__dirname, '..', 'skills');
const MAX_DESCRIPTION_LENGTH = 1024;
// Sections every standard SKILL.md must contain.
// Each entry is an array of acceptable heading strings — the first
// match wins, so you can list canonical + legacy aliases.
const REQUIRED_SECTIONS = [
['## Overview'],
['## When to Use'],
['## Common Rationalizations'],
['## Red Flags'],
['## Verification'],
];
// Skills that are intentionally exempt from section checks.
// Exemptions live HERE, not in skill frontmatter, so contributors
// cannot bypass the validator by editing their own skill file.
// Every entry must have a documented reason.
const SECTION_EXEMPT_SKILLS = {
'using-agent-skills': 'Meta-skill — orchestrates other skills; When-to-Use and Verification are not applicable to a routing document.',
'idea-refine': 'Legacy structure predating skill-anatomy.md — uses How-It-Works/Usage/Anti-patterns instead of standard headings. Tracked for conformance in https://github.com/addyosmani/agent-skills/issues',
};
// Regex patterns that indicate an explicit cross-skill reference.
// Only these patterns trigger the dead-reference warning — generic
// backtick strings in code blocks are intentionally excluded.
const SKILL_REF_PATTERNS = [
/\buse the `([a-z][a-z0-9-]+[a-z0-9])` skill/g,
/\bfollow the `([a-z][a-z0-9-]+[a-z0-9])` skill/g,
/\binvoke the `([a-z][a-z0-9-]+[a-z0-9])` skill/g,
/\bcontinue with `([a-z][a-z0-9-]+[a-z0-9])`/g,
/\buse `([a-z][a-z0-9-]+[a-z0-9])` skill/g,
/`([a-z][a-z0-9-]+[a-z0-9])` skill\b/g,
/`([a-z][a-z0-9-]+[a-z0-9])` persona\b/g,
/\bsee `([a-z][a-z0-9-]+[a-z0-9])`/g,
/──→ ([a-z][a-z0-9-]+[a-z0-9])\b/g, // ASCII diagram arrows
/→ `([a-z][a-z0-9-]+[a-z0-9])`/g,
];
// ─── Helpers ─────────────────────────────────────────────────────────────────
/**
* Parse YAML-style frontmatter from the top of a markdown file.
* Returns a key→value object, or null if no frontmatter block found.
* Values are stripped of surrounding quotes.
*/
function parseFrontmatter(content) {
const match = content.match(/^---[ \t]*\r?\n([\s\S]*?)\r?\n---[ \t]*\r?\n/);
if (!match) return null;
const result = {};
for (const line of match[1].split(/\r?\n/)) {
const colonIdx = line.indexOf(':');
if (colonIdx === -1) continue;
const key = line.slice(0, colonIdx).trim();
const value = line.slice(colonIdx + 1).trim().replace(/^['"]|['"]$/g, '');
if (key) result[key] = value;
}
return result;
}
/**
* Collect all explicit skill cross-references from content.
* Only matches against the SKILL_REF_PATTERNS list to avoid
* false-positives from inline code snippets.
*/
function extractSkillReferences(content) {
const refs = new Set();
for (const pattern of SKILL_REF_PATTERNS) {
// Reset lastIndex for global regexes
pattern.lastIndex = 0;
let m;
while ((m = pattern.exec(content)) !== null) {
refs.add(m[1]);
}
}
return refs;
}
// ─── Validator ───────────────────────────────────────────────────────────────
function validateSkill(dirName, knownSkills) {
const errors = [];
const warnings = [];
let exempt = false;
const skillPath = path.join(SKILLS_DIR, dirName, 'SKILL.md');
if (!fs.existsSync(skillPath)) {
errors.push('Missing SKILL.md');
return { errors, warnings, exempt };
}
const content = fs.readFileSync(skillPath, 'utf8');
// ── Frontmatter ──────────────────────────────────────────────────────────
const fm = parseFrontmatter(content);
if (!fm) {
errors.push('Missing or malformed YAML frontmatter (expected --- block at top of file)');
return { errors, warnings, exempt };
}
if (!fm.name) {
errors.push("Frontmatter missing required field: 'name'");
} else if (fm.name !== dirName) {
errors.push(`Frontmatter name '${fm.name}' does not match directory name '${dirName}'`);
}
if (!fm.description) {
errors.push("Frontmatter missing required field: 'description'");
} else if (fm.description.length > MAX_DESCRIPTION_LENGTH) {
errors.push(
`Description is ${fm.description.length} chars — exceeds the ${MAX_DESCRIPTION_LENGTH}-char limit` +
` (agents inject this into the system prompt)`
);
}
// ── Exemption guard ──────────────────────────────────────────────────────
// Exemptions are validator-owned (SECTION_EXEMPT_SKILLS above).
// If a skill's frontmatter tries to declare its own exemption, fail loud —
// that's a sign someone is trying to bypass the validator.
if (fm.type === 'meta' || fm.exempt === 'sections') {
if (!SECTION_EXEMPT_SKILLS[dirName]) {
errors.push(
`Frontmatter declares 'type: meta' or 'exempt: sections' but '${dirName}' is not in ` +
`the validator's SECTION_EXEMPT_SKILLS allowlist. ` +
`Add an entry to scripts/validate-skills.js with a documented reason.`
);
}
}
// ── Required sections ────────────────────────────────────────────────────
exempt = dirName in SECTION_EXEMPT_SKILLS;
if (!exempt) {
for (const aliases of REQUIRED_SECTIONS) {
const found = aliases.some(heading => content.includes(heading));
if (!found) {
errors.push(`Missing required section: ${aliases[0]}`);
}
}
}
// ── Cross-skill references ───────────────────────────────────────────────
const refs = extractSkillReferences(content);
for (const ref of refs) {
if (!knownSkills.has(ref)) {
warnings.push(`Dead cross-reference: \`${ref}\` is not a known skill`);
}
}
return { errors, warnings, exempt };
}
// ─── Main ────────────────────────────────────────────────────────────────────
function main() {
if (!fs.existsSync(SKILLS_DIR)) {
console.error(`ERROR: skills directory not found at ${SKILLS_DIR}`);
process.exit(1);
}
const skillDirs = fs.readdirSync(SKILLS_DIR)
.filter(d => fs.statSync(path.join(SKILLS_DIR, d)).isDirectory())
.sort();
const knownSkills = new Set(skillDirs);
let totalErrors = 0;
let totalWarnings = 0;
for (const dirName of skillDirs) {
const { errors, warnings, exempt } = validateSkill(dirName, knownSkills);
totalErrors += errors.length;
totalWarnings += warnings.length;
if (errors.length === 0 && warnings.length === 0) {
const tag = exempt ? ' (section checks exempt)' : '';
console.log(` ✓ ${dirName}${tag}`);
} else {
const icon = errors.length > 0 ? ' ✗ ' : ' ⚠ ';
console.log(`${icon} ${dirName}`);
for (const msg of errors) console.log(` ERROR: ${msg}`);
for (const msg of warnings) console.log(` WARN: ${msg}`);
}
}
const status = totalErrors > 0 ? 'FAILED' : totalWarnings > 0 ? 'PASSED WITH WARNINGS' : 'PASSED';
console.log(`\n${skillDirs.length} skills checked — ${totalErrors} error(s), ${totalWarnings} warning(s) — ${status}`);
if (totalErrors > 0) process.exit(1);
}
main();