Explorar skills

Systematically assess and mitigate risks using risk registers, probability-impact matrices, mitigation strategies, and contingency plans. Use when the user asks to assess risks, build a risk register, plan for failure modes, evaluate downside scenarios, prepare contingency plans, or quantify uncertainty before a decision or launch. NOT for finding conceptual flaws or blind spots in ideas (use crit

Verifica opcionalmente e, em seguida, faz commit do código para a branch atual ou para uma nova branch de funcionalidade.

a2a (Agent-to-Agent) é uma revisão de código adversarial entre modelos. O código escrito por Claude é revisado por Codex, e o código de Codex é revisado por Claude, garantindo uma detecção abrangente de falhas.

Use when starting new feature work that should happen in an isolated git worktree on its own branch.

Assess web applications against OWASP WSTG and OWASP Top 10 with reproducible evidence capture.

Use when the user asks to commit, create a git commit, checkpoint changes, save work to git, or write a commit message.

Research before craft for long-form technical content. Profile the audience (knowledge level, jobs-to-be-done, prior beliefs), tier sources (primary > peer-reviewed > authoritative > popular > vendor), triangulate every load- bearing claim across three sources, manage evidence types (data, expert quotes, demonstrations, case studies, source code), and apply citation discipline (when, how, link-rot

Use when the user asks about token usage, session cost, or wants to check optimization effectiveness.

Use when starting a new session, the project has changed significantly, or you need a fresh context summary.

Identify and document boundary conditions, corner cases, error scenarios, and validation requirements that implementations must handle. Use when the user asks to find edge cases, identify corner cases, specify validation rules, enumerate error scenarios, harden a function against bad inputs, or think through what can go wrong at the boundaries of a system. NOT for writing the actual tests (use tes

Use when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (use skill-creator) or when rewriting an existing skill (use transformer). Example triggers - "write a prompt for my summarizer", "tighten this system prompt", "evaluate this agent prompt".

Rewrites landing page copy to be more compelling, benefit-focused, and conversion-optimized.