Explorar skills

Full-spectrum web application VAPT skill for Claude Code, OpenCode, Codex CLI & Gemini CLI — from reconnaissance to exploitation to remediation reporting

Meça a amplitude do mercado de ações dos EUA usando linhas de avanço/declínio, porcentagem de ações acima das médias móveis e novas máximas/mínimas via API Finskills.

Prepare commits for the current feature branch, push, and create or update a PR to main.

Depura erros e rastreia falhas em agentes de IA e suas ferramentas. Identifica erros de contexto, loops infinitos, chamadas de ferramenta malformadas, problemas de análise de resposta e conflitos entre subagentes.

Este guia detalha a integração do protocolo DEPEG para agentes de IA, um programa Solana que converte memecoins da pump.fun em stablecoins lastreadas em USDC na proporção de 1:1, com staking, boosters e distribuição de rendimentos. Abrange o acesso à leitura do estado on-chain e instruções do usuário como troca, staking, resgate de recompensas, unstaking e compra de boosters.

Review a document against its SDLC lifecycle context — assess completeness and check consistency with parent documents in the document hierarchy.

Gera um artigo HTML aprofundado de arquivo único no estilo visual "principle-deepdive", com tema duplo claro/escuro, acentos índigo/âmbar, diagramas SVG inline e cartões recolhíveis. É legível offline, tem menos de 300KB e é ideal para artigos analíticos longos que exploram tópicos princípio por princípio.

実装・commit 後、`acceptance-check` 通過後・PR 作成前に別の AI (Codex CLI または Claude CLI headless) に diff を渡してセカンドオピニオンのコードレビューを得る。backend は環境変数 `CROSS_REVIEW_BACKEND` で `codex` / `claude-self` から選択でき、未指定時は利用可能な CLI を自動検出する。

Use this skill whenever working on a bug fix — from triage through implementation through verification. Triggers on: "fix this bug", "there's an error", "something is broken", "debug this", "this isn't working", "root cause", "why is this failing", "production issue", "investigate this", "hotfix needed", "patch this". This skill applies systematic root cause analysis before touching code, ensures

Use when the user wants to prevent broken code from being pushed, block git push when tests fail, run tests before push, set up push protection, or add a safety net against pushing untested code. Covers any request to gate pushes on test results — whether they mention "hook", "pre-push", or just describe wanting to stop bad code from reaching the remote. Also handles auto-fix/auto-repair of test f

Use when, just after abandoning or failing at something, you catch yourself concluding "that wasn't worth reaching anyway" — the post-mortem self-deception / motivated-reasoning anti-pattern. Fires when writing a post-mortem after a failure or rollback, recording a lesson after a retreat, or when an operator/agent's stated reason for quitting smells like comfort rather than analysis. The tell: a g

Use when user asks for a rough draft, first pass, brainstorm, MVP, stub, sketch, or proposes to "draft a PR for review and refinement before sending upstream" — anywhere the user is throwing a brick (deliberately rough work) to elicit jade (refinement, feedback, selection)