crit-cli
Acerca de
La habilidad crit-cli permite la creación y gestión programática de comentarios de revisión de código a través de comandos CLI, compatible con flujos de trabajo multiagente en artefactos compartidos. Permite publicar/despublicar revisiones, sincronizar con PRs de GitHub, y leer/escribir archivos JSON de crit. Úsala para operaciones de revisión automatizadas, no para sesiones de revisión interactivas que requieren la habilidad separada `crit`.
Instalación rápida
Claude Code
Recomendadonpx skills add tomasz-tomczyk/crit -a claude-code/plugin add https://github.com/tomasz-tomczyk/critgit clone https://github.com/tomasz-tomczyk/crit.git ~/.claude/skills/crit-cliCopia y pega este comando en Claude Code para instalar esta habilidad
Documentación
Crit CLI Reference
If a plan was just written and the user said
/critorcrit, invoke the/critcommand — do not use this reference skill. This skill covers CLI operations likecrit comment,crit pull/push, andcrit share.
Comments have three scopes:
- Line comments (
scope: "line") — tied to specific lines, stored infiles.<path>.comments - File comments (
scope: "file") — about a file overall, stored infiles.<path>.commentswithstart_line: 0 - Review comments (
scope: "review") — general feedback, stored in the top-levelreview_commentsarray
The review file path is shown by crit status.
Reading comments
When crit completes a review round, read stdout and follow its instructions. Unresolved comments are often embedded in that prompt as JSON. Check stderr for approved: true or approved: false.
When you need to read comments separately:
crit comments # human-readable, unresolved only (default)
crit comments --json # flat JSON for agents
crit comments --all # include resolved comments
crit comments --plan <slug> # plan reviews
crit comments [path] # explicit review.json or .crit directory
Review-level comments are listed first — easy to miss in raw review.json. Uses the same review resolution as crit comment (--output, --plan, daemon session).
Multiple active sessions
When more than one review session matches the current directory and branch, crit comment refuses to guess. Run crit status (or crit status --json) to list every active session, then target the intended review explicitly:
crit comment --session <id> --author <name> <path>:<line> <body>
crit comment --session <id> --json --file comments.json --author <name>
The JSON status output exposes the candidates in sessions.
Review file format
{
"review_comments": [
{
"id": "r_f1e2d3",
"body": "Overall the architecture looks good",
"scope": "review",
"author": "User Name",
"resolved": false,
"replies": [
{ "id": "rp_b4a5c6", "body": "Thanks, addressed the minor issues", "author": "Copilot" }
]
}
],
"files": {
"path/to/file.go": {
"comments": [
{
"id": "c_a1b2c3",
"start_line": 5,
"end_line": 10,
"body": "Comment text",
"quote": "the specific words selected",
"anchor": "The sessions table needs a complete rewrite...",
"author": "User Name",
"resolved": false,
"replies": [
{ "id": "rp_c7d8e9", "body": "Fixed by extracting to helper", "author": "Copilot" }
]
}
]
}
}
}
Field rules:
resolved:falseor missing — both mean unresolved. Onlytruemeans resolved.quote(optional): the specific text the reviewer selected — narrows scope within the line range. Focus changes on the quoted text rather than the entire range.anchor(line comments): full text of the commented lines when placed. When edits shift line numbers, locate content by anchor rather than trustingstart_line/end_line.drifted: true: original content was removed or heavily rewritten — line numbers are approximate at best.- Unresolved comments may have
replies— read them before acting.
Authoring and replying with crit comment
# Review-level (general feedback)
crit comment --author 'Copilot' '<body>'
# File-level (whole file, no line numbers)
crit comment --author 'Copilot' <path> '<body>'
# Line (single line or range)
crit comment --author 'Copilot' <path>:<line> '<body>'
crit comment --author 'Copilot' <path>:<start>-<end> '<body>'
# Reply to an existing comment
crit comment --reply-to <id> --author 'Copilot' '<body>'
Hard rules:
- Always pass
--author 'Copilot'(or your agent name) so comments are attributed correctly. - Always single-quote the body — double quotes break on backticks and shell metachars.
- Line numbers reference the file on disk (1-indexed), not diff line numbers.
- Reply bodies support markdown — use code fences and inline code where helpful.
- Only pass
--resolvewhen the user explicitly asks. Never resolve proactively.
Bulk commenting with --json
When leaving 3+ comments, use --json for atomicity (single write, no partial state) and speed (one process). The JSON payload can come from stdin or from --file <path>:
# Stdin is fine when bodies are short single lines:
echo '[
{"body": "overall feedback", "scope": "review"},
{"path": "session.go", "body": "restructure", "scope": "file"},
{"file": "src/auth.go", "line": 42, "body": "Missing null check"},
{"file": "src/auth.go", "line": "50-55", "body": "Extract to helper"},
{"reply_to": "c_a1b2c3", "body": "Fixed — added null check"},
{"reply_to": "r_f1e2d3", "body": "Done"}
]' | crit comment --json --author 'GitHub Copilot'
For multi-paragraph bodies, prefer --file. A raw newline inside a "body" string is invalid JSON, and it's easy to introduce one when shell-quoting a heredoc. Write the JSON to a temp file via your edit tool, then:
crit comment --json --file /tmp/crit-bulk.json --author 'GitHub Copilot'
--file - is shorthand for stdin if you need to be explicit.
Per-entry schema:
| Field | Type | Required | Notes |
|---|---|---|---|
file / path | string | line/file comments | Relative path. path alone (no line) → file-level. |
line | int/string | line comments | 42 or "45-47" |
end_line | int | optional | Defaults to line |
body | string | always | |
author | string | optional | Per-entry override; falls back to --author |
scope | string | optional | "review" / "file" — usually inferred |
reply_to | string | replies | Comment ID (c_… or r_…) |
resolve | bool | optional | Only when user explicitly asks |
Scope inference (when scope omitted): has reply_to → reply; no file/path and no line → review-level; path but no line → file-level; file/path + line → line.
Multi-file disambiguation
If crit comment errors with "comment found in multiple files", IDs collided across files. Disambiguate with --path:
crit comment --reply-to c_a1b2c3 --path src/auth.go --author 'Copilot' 'Fixed the null check'
In --json mode, set the file field on the entry. Review-level IDs (r_…) are globally unique and never need this.
Plan-mode comments
Plan reviews (via crit plan or the ExitPlanMode hook) store the review file in ~/.crit/plans/<slug>/. Always pass --plan <slug> — without it, crit comment looks in the project root and won't find the comments. The slug is shown in the review feedback prompt.
crit comment --plan my-plan-2026-03-23 --reply-to c_a1b2c3 --author 'Copilot' 'Updated the plan'
GitHub PR sync
crit pull [pr-number] # Fetch PR review comments into the review file
crit push [--dry-run] [--event <type>] [-m <msg>] [pr] # Post review comments as a GitHub PR review
Requires gh CLI installed and authenticated. PR number is auto-detected from the current branch.
--event values: comment (default), approve, request-changes. -m adds a review-level body message.
Sharing
crit share <file> [file...] # Upload and print URL
crit share --qr <file> # Also print QR code (terminal only)
crit share --org <slug> <file> # Share under an organization
crit share --org <slug> --visibility unlisted <file> # Org share with explicit visibility
crit unpublish [file...] # Remove shared review
- Always relay the output — copy the URL (and QR if used) into your response. Don't make the user dig through tool output.
--qris terminal-only — skip in mobile apps, web chat UIs, or anywhere Unicode block characters won't render correctly.--org <slug>shares under an organization. Visibility defaults toorganization(members only). Override with--visibility(organization,unlisted,public).- Unpublish uses the persisted delete token in the review file — no extra args needed.
Repositorio GitHub
Preguntas frecuentes
¿Qué es el Skill crit-cli?
crit-cli es un Skill de Claude creado por tomasz-tomczyk. Los Skills agrupan instrucciones y recursos que Claude carga cuando los necesita para realizar tareas relacionadas con crit-cli sin indicaciones adicionales.
¿Cómo instalo crit-cli?
Usa los comandos de instalación de esta página: añade crit-cli a Claude Code como plugin o clona su repositorio en tu directorio de skills y reinicia Claude para cargarlo.
¿A qué categoría pertenece crit-cli?
crit-cli pertenece a la categoría Meta.
¿Se puede usar crit-cli gratis?
Sí. crit-cli aparece en AIMCP y se puede instalar gratis.
Habilidades relacionadas
Esta 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.
Esta 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.
Esta 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 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.