review-skill-format
Acerca de
Esta habilidad valida archivos SKILL.md según el estándar agentskills.io verificando el frontmatter YAML, las secciones requeridas y el formato. Úsela para revisar habilidades nuevas o modificadas antes de fusionar, auditar lotes de habilidades o validar envíos de pull requests. Realiza verificaciones automáticas de cumplimiento para garantizar la calidad.
Instalación rápida
Claude Code
Recomendadonpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/review-skill-formatCopia y pega este comando en Claude Code para instalar esta habilidad
Documentación
Review Skill Format
Validate SKILL.md file against agentskills.io open standard. This skill checks YAML frontmatter completeness, required section presence, procedure step format (Expected/On failure blocks), line count limits, registry synchronization. Use this before merging any new or modified skill.
When Use
- New skill authored and needs format validation before merge
- Existing skill modified and needs re-validation
- Performing batch audit of all skills in a domain
- Verifying skill created by
create-skillmeta-skill - Reviewing contributor skill submission in a pull request
Inputs
- Required: Path to SKILL.md file (e.g.,
skills/setup-vault/SKILL.md) - Optional: Strictness level (
lenientorstrict, default:strict) - Optional: Whether to check registry sync (default: yes)
Steps
Step 1: Verify File Exists and Read Content
Confirm SKILL.md file exists at expected path. Read its full content.
# Verify file exists
test -f skills/<skill-name>/SKILL.md && echo "EXISTS" || echo "MISSING"
# Count lines
wc -l < skills/<skill-name>/SKILL.md
Got: File exists and content readable. Line count displayed.
If fail: File does not exist? Check path for typos. Verify skill directory exists with ls skills/<skill-name>/. Directory missing? Skill not created yet — use create-skill first.
Step 2: Check YAML Frontmatter Fields
Parse YAML frontmatter block (between --- delimiters). Verify all required and recommended fields present.
Required fields:
name— matches directory name (kebab-case)description— under 1024 characters, starts with verblicense— typicallyMITallowed-tools— comma-separated or space-separated tool list
Recommended metadata fields:
metadata.author— author namemetadata.version— semantic version stringmetadata.domain— one of domains listed inskills/_registry.ymlmetadata.complexity— one of:basic,intermediate,advancedmetadata.language— primary language ormultimetadata.tags— comma-separated, 3-6 tags, includes domain name
# Check required frontmatter fields exist
head -30 skills/<skill-name>/SKILL.md | grep -q '^name:' && echo "name: OK" || echo "name: MISSING"
head -30 skills/<skill-name>/SKILL.md | grep -q '^description:' && echo "description: OK" || echo "description: MISSING"
head -30 skills/<skill-name>/SKILL.md | grep -q '^license:' && echo "license: OK" || echo "license: MISSING"
head -30 skills/<skill-name>/SKILL.md | grep -q '^allowed-tools:' && echo "allowed-tools: OK" || echo "allowed-tools: MISSING"
Got: All four required fields present. All six metadata fields present. name matches directory name. description under 1024 characters.
If fail: Report each missing field as BLOCKING. name does not match directory name? Report as BLOCKING with expected value. description exceeds 1024 characters? Report as SUGGEST with current length.
Step 3: Locale-Specific Validation (Translations Only)
Frontmatter contains locale field? File is translated SKILL.md. Perform these additional checks. No locale field? Skip this step.
-
Translation frontmatter fields — Verify these five fields present:
locale— target locale code (e.g.,de,ja,zh-CN,es)source_locale— origin locale (typicallyen)source_commit— commit hash of English source used for translationtranslator— who or what produced translationtranslation_date— ISO 8601 date of translation
-
Prose language scan — Sample 3-5 body paragraphs (outside code blocks, frontmatter, headings). Verify prose written in target locale, not English. Ignore: code blocks, inline code, tool names, field names, file paths, English terms that have no standard translation in target language.
-
Code block identity check — Compare code blocks in translated file against English source at
skills/<skill-name>/SKILL.md. Code blocks must be identical (code is never translated). Flag any code block whose content differs from English source.
# Check translation frontmatter fields
for field in "locale:" "source_locale:" "source_commit:" "translator:" "translation_date:"; do
grep -q "^${field}\|^ ${field}" i18n/<locale>/skills/<skill-name>/SKILL.md \
&& echo "$field OK" || echo "$field MISSING"
done
Got: All five translation fields present. Body paragraphs in target locale. Code blocks match English source exactly.
If fail: Report missing translation fields as BLOCKING. Body paragraphs in English despite non-English locale? Report as BLOCKING — file has untranslated prose. Code blocks differ from English source? Report as BLOCKING — code must not be translated or modified.
Step 4: Check Required Sections
Verify all six required sections present in skill body (after frontmatter).
Required sections:
## When to Use## Inputs## Procedure(with### Step N:sub-sections)## Validation(may also appear as## Validation Checklist)## Common Pitfalls## Related Skills
# Check each required section
for section in "## When to Use" "## Inputs" "## Procedure" "## Common Pitfalls" "## Related Skills"; do
grep -q "$section" skills/<skill-name>/SKILL.md && echo "$section: OK" || echo "$section: MISSING"
done
# Validation section may use either heading
grep -qE "## Validation( Checklist)?" skills/<skill-name>/SKILL.md && echo "Validation: OK" || echo "Validation: MISSING"
Got: All six sections present. Procedure section contains at least one ### Step sub-heading.
If fail: Report each missing section as BLOCKING. Skill without all six sections is non-compliant with agentskills.io standard. Provide section template from create-skill meta-skill.
Step 5: Check Procedure Step Format
Verify each procedure step follows required pattern: numbered step title, context, code block(s), Expected:/On failure: blocks.
For each ### Step N: sub-section, check:
- Step has descriptive title (not just "Step N")
- At least one code block or concrete instruction exists
**Expected:**block present**On failure:**block present
Got: Every procedure step has both Expected: and On failure: blocks. Steps contain concrete code or instructions, not vague descriptions.
If fail: Report each step missing Expected/On failure as BLOCKING. Steps contain only vague instructions ("configure the system appropriately")? Report as SUGGEST with note to add concrete commands.
Step 6: Verify Line Count
Check that SKILL.md is within 500-line limit.
lines=$(wc -l < skills/<skill-name>/SKILL.md)
[ "$lines" -le 500 ] && echo "OK ($lines lines)" || echo "OVER LIMIT ($lines lines > 500)"
Got: Line count is 500 or fewer.
If fail: Over 500 lines? Report as BLOCKING. Recommend using refactor-skill-structure skill to extract code blocks >15 lines to references/EXAMPLES.md. Typical reduction: 20-40% by extracting extended examples.
Step 7: Check Registry Synchronization
Verify skill is listed in skills/_registry.yml under correct domain with matching metadata.
Check:
- Skill
idexists under correct domain section pathmatches<skill-name>/SKILL.mdcomplexitymatches frontmatterdescriptionpresent (may be abbreviated)total_skillscount at top of registry matches actual skill count
# Check if skill is in registry
grep -q "id: <skill-name>" skills/_registry.yml && echo "Registry: FOUND" || echo "Registry: NOT FOUND"
# Check path
grep -A1 "id: <skill-name>" skills/_registry.yml | grep -q "path: <skill-name>/SKILL.md" && echo "Path: OK" || echo "Path: MISMATCH"
Got: Skill listed in registry under correct domain with matching path and metadata. Total count accurate.
If fail: Not found in registry? Report as BLOCKING. Provide registry entry template:
- id: skill-name
path: skill-name/SKILL.md
complexity: intermediate
language: multi
description: One-line description
Checks
- SKILL.md file exists at expected path
- YAML frontmatter parses without errors
- All four required frontmatter fields present (
name,description,license,allowed-tools) - All six metadata fields present (
author,version,domain,complexity,language,tags) -
namefield matches directory name -
descriptionis under 1024 characters - All six required sections present (When to Use, Inputs, Procedure, Validation, Common Pitfalls, Related Skills)
- Every procedure step has Expected: and On failure: blocks
- Line count is 500 or fewer
- Skill listed in
_registry.ymlwith correct domain, path, metadata -
total_skillscount in registry is accurate - (Translations only) All five translation frontmatter fields present (
locale,source_locale,source_commit,translator,translation_date) - (Translations only) Body paragraphs in target locale, not English
- (Translations only) Code blocks identical to English source
Pitfalls
- Check frontmatter with regex only: YAML parsing can be subtle.
description: >multiline block looks different fromdescription: "inline". Check both patterns when searching for fields. - Miss the Validation section variant: Some skills use
## Validation Checklistinstead of## Validation. Both acceptable; check for either heading. - Forget registry total count: After add a skill to registry,
total_skillsnumber at top must also be incremented. Common miss in PRs. - Name vs title confusion:
namefield must be kebab-case matching directory name.# Titleheading is human-readable and can differ (e.g., name:review-skill-format, title:# Review Skill Format). - Lenient mode skip blockers: Even in lenient mode, missing required sections and frontmatter fields should still be flagged. Lenient mode only relaxes style and metadata recommendations.
- Translated skills with English prose: File with non-English frontmatter, non-English headings, English body paragraphs passes all structural checks. Always verify body text language for translated skills —
localefield in frontmatter signals that prose must be in target language, not English.
See Also
create-skill— Canonical format specification; use as authoritative reference for what valid SKILL.md looks likeupdate-skill-content— After format validation passes, use this to improve content qualityrefactor-skill-structure— When skill fails line count check, use this to extract and reorganizereview-pull-request— When reviewing PR that adds or modifies skills, combine PR review with format validation
Repositorio GitHub
Habilidades relacionadas
content-collections
MetaEsta habilidad proporciona una configuración probada en producción para Content Collections, una herramienta centrada en TypeScript que transforma archivos Markdown/MDX en colecciones de datos con tipado seguro mediante validación Zod. Úsala al construir blogs, sitios de documentación o aplicaciones Vite + React con mucho contenido para garantizar seguridad de tipos y validación automática de contenido. Abarca todo, desde la configuración del plugin de Vite y compilación MDX hasta la optimización de despliegue y validación de esquemas.
polymarket
MetaEsta habilidad permite a los desarrolladores crear aplicaciones con la plataforma de mercados de predicción Polymarket, incluyendo la integración de API para operaciones y datos de mercado. También proporciona transmisión de datos en tiempo real a través de WebSocket para monitorear operaciones en vivo y actividad del mercado. Úsela para implementar estrategias de trading o crear herramientas que procesen actualizaciones de mercado en tiempo real.
creating-opencode-plugins
MetaEsta habilidad ayuda a los desarrolladores a crear complementos de OpenCode que se conectan a más de 25 tipos de eventos, como comandos, archivos y operaciones LSP. Proporciona la estructura del complemento, las especificaciones de la API de eventos y los patrones de implementación para módulos en JavaScript/TypeScript. Úsala cuando necesites interceptar, monitorear o extender el ciclo de vida del asistente de IA de OpenCode con lógica personalizada basada en eventos.
sglang
MetaSGLang es un framework de alto rendimiento para el servicio de LLM que se especializa en generación rápida y estructurada para JSON, expresiones regulares y flujos de trabajo de agentes utilizando su caché de prefijos RadixAttention. Ofrece una inferencia significativamente más rápida, especialmente para tareas con prefijos repetidos, lo que lo hace ideal para salidas complejas y estructuradas, y conversaciones multiturno. Elige SGLang sobre alternativas como vLLM cuando necesites decodificación restringida o estés construyendo aplicaciones con uso extensivo de prefijos compartidos.
