S Skillteca
Receber por email
Explorar Categorias Coleções Newsletter
← Voltar para o catálogo

known-good

Desenvolvimento Autor: boshu2

Test fixture skill that satisfies all 15 auditor checks (Pass 1 + Pass 2). **Use when:** - The auditor integration tests assert PASS verdict on a canonical input **Triggers:** "known-good fixture", "auditor PASS smoke", "skill-auditor regression" **Not ideal for:** - Real-world use (this is a test fixture)

393estrelas
Atualizado há 4 meses
Ver no GitHub ↗ Licença: NOASSERTION

Como adicionar

/plugin marketplace add boshu2/agentops

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/known-good/svg)](https://www.skillteca.com.br/skills/known-good)
#test

Skills relacionadas

Ver todas de Desenvolvimento →

claude-api

153.1k

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a C

Desenvolvimento #ai #api por anthropics

skill-creator

153.1k

Crie novas skills, modifique e aprimore as existentes, e meça seu desempenho. Utilize para desenvolver, editar, otimizar, testar e comparar skills, além de refinar suas descrições para maior precisão de acionamento.

Desenvolvimento #test por anthropics

claude-code-plugin-release

83.4k

Fluxo de trabalho automatizado de versionamento semântico e lançamento para plugins do Claude Code. Gerencia incrementos de versão em manifestos package.json, marketplace.json, plugin.json, publicação npm (para que npx claude-mem@X.Y.Z seja resolvido), verificação de build, marcação git, lançamentos no GitHub e geração de changelog.

Desenvolvimento #ai #git por thedotmack

claude-mem

83.4k

Contexto Persistente Entre Sessões para Cada Agente – Captura tudo o que seu agente faz durante as sessões, comprime com IA e injeta contexto relevante de volta em sessões futuras. Compatível com Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode e mais.

Desenvolvimento #ai por thedotmack

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

/known-good — Auditor PASS test fixture

A minimal but complete SKILL.md that satisfies all 15 auditor checks. Used by tests/integration/test_skill_auditor.bats to confirm the auditor returns PASS or WARN on conforming input.

⚠️ Critical Constraints

  • This is a test fixture, not a runtime skill. Do not invoke. Why: auditor tests pin the exact content; runtime use would surprise contributors.
  • Frontmatter shape is canonical. YAML description: | block scalar with explicit Triggers and Use-when markers. Why: exercises description-has-triggers form (a) AND form (b) simultaneously.
  • Constraints are front-loaded. This ## ⚠️ Critical Constraints section appears before any other H2. Why: tests constraints-frontloaded heuristic.
  • Every constraint has a Why. Each bullet ends with Why: <reason>. Why: tests rationale-present heuristic.

Workflow

Phase 1: Setup

Read the fixture, parse frontmatter.

Checkpoint: frontmatter has name, description, metadata.tier.

Phase 2: Validate

Run all 8 Pass-2 checks.

Checkpoint: all 8 checks return pass or n/a.

Phase 3: Emit verdict

Aggregate via max-severity rule.

Checkpoint: verdict is PASS (no warns, no fails).

Output Specification

Format: stdout marker known-good confirming the fixture loaded cleanly. Filename: none — runtime fixture only. Exit code: 0.

Quality Rubric

  • [ ] Frontmatter passes Pass 1 (heal-skill structural)
  • [ ] Constraints section is front-loaded (first H2 after title)
  • [ ] Every constraint has a Why: rationale
  • [ ] Each Phase has a Checkpoint
  • [ ] Output Specification is explicit
  • [ ] Quality Rubric exists with checkboxes
  • [ ] SKILL.md is under 250 lines

Examples

# Run auditor against this fixture; expect exit 0 and verdict PASS or WARN
bash skills/skill-auditor/scripts/audit.sh tests/fixtures/skills/known-good

Troubleshooting

| Problem | Cause | Solution | |---------|-------|----------| | Auditor returns FAIL | Fixture drifted from canonical shape | Restore from git; do not edit without updating tests |

Compartilhar X LinkedIn