Receber por email
← Voltar para o catálogo

cm-skill-evolution

Repair or extend CodyMaster skills with a three-mode loop: FIX, DERIVED, and CAPTURED, grounded in current repo tooling.

46estrelas
Atualizado há 4 meses

Ver no GitHub ↗

Como adicionar

/plugin marketplace add tody-agent/codymaster

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/cm-skill-evolution-mpsupnyb/svg)](https://www.skillteca.com.br/skills/cm-skill-evolution-mpsupnyb)
#ai

Skills relacionadas

Ver todas de Desenvolvimento →

Alerta por categoria

Receba novas skills de Desenvolvimento toda segunda

1 email curto, só com as skills novas de Desenvolvimento. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

cm-skill-evolution

Use this skill after cm-skill-health identifies a degraded or broken skill, or when cm advisory handoff --for cm-skill-evolution produces a structured recovery note.

Modes

FIX

Use when the skill should exist already but is inaccurate, broken, or partially missing.

Checklist:

  • repair broken references
  • restore missing support files
  • align docs and profiles
  • re-run skill validation and test gate

DERIVED

Use when the original promise was too ambitious, but the repo has enough primitives to ship a truthful MVP.

Checklist:

  • keep the same user problem
  • reduce claims to what the code can support today
  • reuse existing repo building blocks instead of inventing a new subsystem

CAPTURED

Use when the main value is operational learning rather than a new code path.

Checklist:

  • append the lesson with cm retro --project . --tool skill --note "..."
  • record durable context in .cm/CONTINUITY.md
  • update the relevant skill so future sessions do not repeat the same failure

Evolution Loop

  1. Start from the health note.
  2. Preferred source: cm advisory handoff --for cm-skill-evolution
  3. Pick one mode only.
  4. Define the smallest truthful recovery.
  5. Patch the skill and its discovery surfaces.
  6. Verify:
  7. npm run validate:skills
  8. npm run check:skills
  9. repo test gate if code or docs wiring changed materially
  10. Capture the lesson in retro and continuity.

Decision guide

  • The feature existed and drifted: FIX
  • The changelog promised more than the repo ever shipped: DERIVED
  • The issue is mainly process and should inform future work: CAPTURED

Output

## Skill Evolution
- Skill: cm-...
- Mode: FIX | DERIVED | CAPTURED
- Change: ...
- Verification: ...
- Learning captured: yes | no

Preferred advisory input:

## Advisory Handoff
- Consumer: cm-skill-evolution
- Skill: cm-...
- Recovery path: FIX | DERIVED | CAPTURED | NONE
- Confidence: 0.xx
- Source analysis: EA-...
- Task: ...
- Status: completed | partial | failed
- Evidence: ...
- Selected skills: ...
- Target skills: ...
- Quality weight: 0.xx
- Next step: ...
Compartilhar X LinkedIn