메뉴
Provide repo coding standards. Triggers: "standards", "provide repo coding standards.", "standards skill".
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Dispatch fresh-context refuters (model-agnostic; multi-model opt-in) to attack a completion claim at the shared-trunk pawl before landing. Triggers: pre-land validation, refute.
Dispatch fresh-context refuters (model-agnostic; multi-model opt-in) to attack a completion claim at the shared-trunk pawl before landing. Triggers: pre-land validation, refute.
Run pre mortem.
Stress-test plans before work. Use when: a plan is drafted but not yet executed and you want to surface failure modes, risks, and what would prove it wrong before committing.
Repair skill hygiene. Triggers: "heal-skill", "heal skill", "repair skill hygiene.".
Repair skill hygiene. Triggers: "heal-skill", "heal skill", "repair skill hygiene.".
| name | standards |
| description | Provide repo coding standards. Triggers: "standards", "provide repo coding standards.", "standards skill". |
Language-specific coding standards loaded on-demand by other skills.
This is a library skill - it doesn't run standalone but provides standards references that other skills load based on file types being processed.
| Standard | Reference | Loaded By |
|---|---|---|
| Skill Structure | references/skill-structure.md | vibe (skill audits), doc (skill creation) |
| Python | references/python.md | vibe, implement, complexity |
| Go | references/go.md | vibe, implement, complexity |
| Rust | references/rust.md | vibe, implement, complexity |
| TypeScript | references/typescript.md | vibe, implement |
| JavaScript | references/javascript.md | vibe, implement |
| Shell | references/shell.md | vibe, implement |
| YAML | references/yaml.md | vibe |
| JSON | references/json.md | vibe |
| Markdown | references/markdown.md | vibe, doc |
| SQL Safety | references/sql-safety-checklist.md | vibe, pre-mortem (when DB code detected) |
| LLM Trust Boundaries | references/llm-trust-boundary-checklist.md | vibe, pre-mortem (when LLM code detected) |
| Race Conditions | references/race-condition-checklist.md | vibe, pre-mortem (when concurrent code detected) |
| Codex Skills | references/codex-skill.md | vibe (when skills-codex/ or converter files detected) |
| Behavioral Discipline | references/behavioral-discipline.md | implement, review, vibe, pre-mortem |
| Test Pyramid | references/test-pyramid.md | plan, pre-mortem, implement, crank, validation, post-mortem |
| SKILL.md Tier-Caps | references/skill-tier-caps.md | vibe (skill line-cap audits), doc, plan |
| External-Source Attribution | references/external-source-attribution.md | doc (when absorbing external corpora), heal-skill |
Skills declare standards as a dependency:
skills:
- standards
Then load the appropriate reference based on file type:
# Pseudo-code for standard loading
if file.endswith('.py'):
load('standards/references/python.md')
elif file.endswith('.go'):
load('standards/references/go.md')
elif file.endswith('.rs'):
load('standards/references/rust.md')
# etc.
Specialized checklists for high-risk code patterns. Loaded automatically by $validate and $pre-mortem when matching code patterns are detected:
| Checklist | Trigger Pattern | Risk Area |
|---|---|---|
sql-safety-checklist.md | SQL queries, ORM calls, migration files, database/sql, sqlalchemy, prisma | Injection, migration safety, N+1, transactions |
llm-trust-boundary-checklist.md | anthropic, openai imports, prompt templates, *llm*/*prompt* files | Prompt injection, output validation, cost control |
race-condition-checklist.md | Goroutines, threads, asyncio, sync.Mutex, shared file I/O | Shared state, file races, database races |
codex-skill.md | Files under skills-codex/, convert.sh, skills-codex-overrides/ | Codex API conformance, prohibited primitives, tool mapping |
behavioral-discipline.md | Execution, review, or plan-validation tasks with ambiguity or broad blast radius | Hidden assumptions, overbuilding, drive-by edits, weak verification |
Skills detect triggers via file content patterns and import statements. Each checklist's "When to Apply" section defines exact detection rules.
For comprehensive audits, skills can load extended standards from
vibe/references/*-standards.md which contain full compliance catalogs.
| Standard | Size | Use Case |
|---|---|---|
| Tier 1 (this skill) | ~5KB each | Normal validation |
| Tier 2 (vibe/references) | ~15-20KB each | Deep audits, --deep flag |
| Domain checklists | ~3-5KB each | Triggered by code pattern detection |
Skills that use standards:
$validate - Loads based on changed file types$implement - Loads for files being modified$review - Loads for change-quality and blast-radius checks$doc - Loads markdown standards$review - Loads for root cause analysis$refactor - Loads for refactoring recommendationsUser says: $validate (detects changed Python files)
What happens:
auth.py in changesetstandards/references/python.md automaticallyResult: Python code validated against language-specific standards without manual reference loading.
User says: $implement ag-xyz-123 (issue modifies Go files)
What happens:
server.go in implementation scopestandards/references/go.md for contextResult: Go code generated conforming to standards, reducing post-implementation vibe findings.
| Problem | Cause | Solution |
|---|---|---|
| Standards not loaded | File type not detected or standards skill missing | Check file extension matches reference; verify standards in dependencies |
| Wrong standard loaded | File type misidentified (e.g., .sh as .bash) | Manually specify standard; update file type detection logic |
| Deep standards missing | Vibe needs extended catalog, not found | Check vibe/references/*-standards.md exists; use --deep flag |
| Standard conflicts | Multiple languages in same changeset | Load all relevant standards; prioritize by primary language |