Receber por email

Explorar skills

2.905 skills encontradas

research

20

Minimal codex-native research loop. Use for docs/papers/state-of-the-art scan with source-backed recommendations.

Pesquisa e Web #ai #python por Borda

plan

20

Analysis-only planning — classify and scope a task without writing code; outputs a structured plan to .plans/active/.

Desenvolvimento #ai #python por Borda

analyse

20

Minimal codex-native analysis loop. Use for issue/PR/problem analysis before implementation with measurable gates.

Desenvolvimento #ai #python por Borda

resolve

20

Minimal codex-native resolve loop. Use to apply review findings, rerun checks, and publish unresolved gaps with measurable gates.

Desenvolvimento #ai #python por Borda

fix

20

Reproduce-first bug resolution — capture bug in failing regression test, apply minimal fix, run quality stack and review loop.

Desenvolvimento #ai #python por Borda

review

20

Minimal codex-native review loop. Use for local diff review with measurable quality gates and a JSON artifact.

Desenvolvimento #ai #python por Borda

refactor

20

Test-first refactoring — audit coverage, add characterization tests, apply changes with safety net, run quality stack and review loop.

Desenvolvimento #ai #python por Borda

setup

20

Post-install setup for foundry plugin. Merges statusLine, permissions.allow, and enabledPlugins into ~/.claude/settings.json; symlinks rules, TEAM_PROTOCOL.md, and skills into ~/.claude/.

DevOps e Infra #ai #python por Borda

retro

20

Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.

Marketing #ai #python por Borda

release

20

Minimal codex-native release loop. Use for SemVer-aware release readiness with measurable gates and artifact output.

Desenvolvimento #ai #python por Borda

investigate

20

Systematic diagnosis for unknown failures — local environment, tool setup, CI vs local divergence, hook misbehavior, and runtime anomalies. Gathers signals broadly, ranks hypotheses, uses adversarial review (Codex or foundry:challenger) for ambiguous cases, probes each, and reports root cause with a recommended next action. NOT for known code bugs (/develop:debug) or config quality (/foundry:audit

Desenvolvimento #ai #python por Borda

review

20

Realiza revisão de código multiagente para arquivos Python locais, diretórios ou diferenças do git, cobrindo arquitetura, testes, desempenho, documentação, lint, segurança e design de API. O escopo são arquivos-fonte Python na árvore de trabalho local, excluindo projetos sem arquivos Python.

Desenvolvimento #ai #api por Borda