flow
Skill2 starsChanged 4 months agoApache-2.0View on GitHub
Flujo de trabajo estándar del framework para cualquier proyecto. Usar SIEMPRE que el usuario inicie trabajo en un módulo, feature, bug o mejora: "vamos con X", "empecemos Y", "siguiente feature", "hay un bug en", "revisemos Z", "implementa", "desarrolla". También cuando pregunte cómo funciona algo del sistema o pida una mejora. Guía el ciclo completo: explorar → decidir → especificar → ejecutar → commit/push → verificar → documentar.
33 other projects use a version of this.
Adopted by
Most recently taken up by
- phuthuycoding/kanban-flowtheir own version, first seen Nov 8, 2026
- baodhg/FLOWtheir own version, first seen Nov 8, 2026
- jocarrd/crux-agentstheir own version, first seen Nov 8, 2026
- cofin/flowtheir own version, first seen Nov 7, 2026
- retospect/precis-mcptheir own version, first seen Nov 6, 2026
- luckys/agent-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use grill, implement and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
renatorozasSkillgrill
Adversarial code review. Don't let me ship until the changes pass your scrutiny.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 5 projects that use this
SentrySkillreview
Fixture review skill.
Also in 6 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 3 projects that use this
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
Other versions33 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 33
- react/react★ 252ksame name
- facebook/react★ 252ksame name
- software-mansion/react-native-audio-api★ 856same name
- simota/agent-skills★ 96same name
- panayiotism/claude-harness★ 79same name
- rainday/smart-blog-skills★ 35same name
- cofin/flow★ 19same name
- basezh/agent-skills-on-base★ 15same name
- retospect/precis-mcp★ 11same name
- foryouself83/harness-tier★ 10same name
23 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- module-auditSkill
- spec-devSkill
The file
Files
Flow — flujo de 7 etapas
Generalización de engram-workflow / nexocontable-workflow / spec-dev, probado en Engram, NexoContable y Aiva.
1. EXPLORAR
Leer el código relevante antes de proponer nada: controller/service/componente,
estado actual, gaps. Consultar memoria en este orden: fw lessons-search
"<descripción + archivos>" (lecciones estructuradas del framework — constraints
primero, obligatorio, sin esperar a que el usuario lo pida), luego mem_search de
Engram y claude-mem si el MCP está disponible (memoria de sesión/observaciones).
El DECISIONS_LOG del proyecto se lee siempre, con o sin MCP. No proponer
soluciones sin haber leído el código.
Los documentos describen intención; el repo describe realidad — si difieren, la
realidad manda y se reporta.
2. DECIDIR
Cambios con tradeoffs o impacto arquitectónico: presentar opciones con pros/contras concretos y riesgos reales; esperar confirmación. Fixes obvios: pasar directo a 3. Si la decisión contradice una entrada CERRADA del DECISIONS_LOG: reportar y detenerse.
3. ESPECIFICAR
Tarea no trivial → spec (templates/SPEC_TEMPLATE.md) o codex-prompt
(templates/codex-prompt-template.md): autocontenido, exacto,
con RESTRICCIONES (scope negativo) y VERIFICACIÓN mecánica. Archivar en
docs/codex-prompts/YYYY-MM-DD-*.md. Clasificar por la escalera de delegación:
mecánica→Haiku, estándar→Sonnet, crítica (dinero/auth/seguridad)→agente principal.
4. EJECUTAR
Según el tier. Protocolo de error del ejecutor: 3 intentos → detenerse y reportar. Si la sesión acumula fallos (2 rechazos o errores seguidos): backpressure — consolidar lo verificado antes de aceptar más trabajo.
5. COMMIT / PUSH
Un commit por unidad verificable, mensaje prescrito en el spec. Nunca mezclar dominios.
6. VERIFICAR
Gate no negociable: typecheck en verde (anotando pre-existentes) + greps de confirmación (existe lo nuevo, no existe lo viejo) + prueba de comportamiento (input concreto → output esperado) + tests del área.
7. DOCUMENTAR
fw task-close --task ID --tipo ... --clase ... --modelo ... --resultado ... --dur N --est N— siempre, sin que el usuario lo pida.- Rechazo de review →
fw review-add --task ID --categoria ... "detalle". - Lección transferible →
fw lesson-add --kind incident|pattern|constraint "...". - Decisión nueva → entrada en DECISIONS_LOG.
- Incidente/bug grave → INCIDENT_LOG; si la lección es arquitectónica, promover regla DO NOT REVERT al CLAUDE.md.
- Guardar en memoria de sesión (
mem_savede Engram) lo no derivable del código.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

