agentleFS
ad1codead1code/sdd-harness/skills/sdd-implement/SKILL.md

sdd-implement

Skill4 starsChanged 22 days agoMITView on GitHub

Implementa SOLO la tarea Tn indicada de specs/NNN/tasks.md con el test primero (rojo comprobado antes de verde), pasa scripts/verify.sh, pide revisión al agente code-reviewer, marca la tarea y se para. Usar con plan y tareas aprobados.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No cambies un test ni verify.sh para que pase.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Basado en hello-sdd de MoureDev (Apache-2.0) y en ECC (MIT), adaptado. Ver NOTICE. -->

Implementar una tarea

La única fase en la que se escribe código.

Proceso

  1. Lee la tarea en tasks.md y el plan.md. Comprueba que las tareas de las que depende están marcadas.
  2. Rojo. Escribe primero los tests de los RF de la tarea y ejecútalos. Tienen que fallar porque falta el comportamiento, no por un import roto. Un test escrito pero no ejecutado no cuenta.
  3. Verde. Lo mínimo para que pasen. Vuelve a ejecutarlos.
  4. Ejecuta scripts/verify.sh y enseña la salida real con su código. Solo 0 permite cerrar.
  5. Lanza el agente code-reviewer sobre el diff. Un BLOCK se arregla antes de seguir.
  6. Marca la tarea, di qué RF cubre, y para. No empieces la siguiente sin el OK del usuario.

Sin tareas pendientes, la siguiente fase es sdd-validate.

Reglas

  • Lo que no está en la spec ni en el plan no se implementa: para y pregunta.
  • No cambies un test ni verify.sh para que pase. Si un test está mal, dilo antes.
  • Si el código se aparta del plan, propón el cambio en plan.md. Si cambia un comportamiento de la spec, es sdd-change.
  • Tras dos intentos fallidos sobre el mismo error, para y explica qué has probado.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.