Explorar skills

Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use ao treinar, depurar, exportar ou aplicar adaptadores de Apple Foundation Models localmente em Macs com memória limitada, ou quando surgirem problemas de memória com o toolkit AFM, .fmadapter, QLoRA, esquema de dataset, launchd ou MLX.

Use AFTER first-round planning is complete, to do META-PLANNING — what wasn't planned that should have been? What pitfalls don't surface in the first round due to existing context bias, context rot, plan mode system prompt biases, or other distortions? Triage importance, surface escape routes (subagent assessment, backups, operator ready for ctrl+C, anything). NOT a duplicate of plan mode or commo

Trigger on "acceptance criteria", "consult acceptance", "success criteria", "signoff matrix", "deliverables per phase", "primary path fallback", "definition of done". Per-phase deliverables, measurable criteria (tech + business/ops), owner, primary path + fallback. NOT commercial terms (use consult-commercial), NOT gate questions (use consult-gates).

Monthly devlog — longer, more reflective recap. ~1200-2000 words. Stitches together the month's work, names the pattern, draws a non-obvious lesson. Goes deeper than a weekly recap.

The workflow used in this project for planning and organising work using `jj` VCS

Orquestrador meta-autônomo que continuamente descobre trabalho, despacha agentes, revisa resultados e gerencia o ciclo de vida completo no espaço de trabalho do usuário. Use quando o usuário deseja uma operação autônoma e sem intervenção.

Comprehensive security audit: detects insecure defaults, hardcoded secrets, sharp edges, supply chain risks, and OWASP vulnerabilities. Based on Trail of Bits methodology. Use when auditing security, reviewing config, or pre-deployment checks. For PR diffs, use /security-review instead.

Auxiliar de prompts de permissão do Codex para simulação padrão de /fewer-permission-prompts, propostas seguras de prefix_rule, verificação de execpolicy, aplicação e reversão.

Esta skill configura um pipeline de pesquisa multiagente automatizado para descobrir achados não-consensuais em diversos domínios, como hardware de IA, biotecnologia ou geopolítica. Ela cria um sistema auto-executável que re-executa periodicamente, realizando pesquisa profunda setor por setor e análise intersetorial para identificar achados subvalorizados.

Monthly delta tracking and progress reporting for GEO clients. Compares two GEO audits (baseline vs. current), calculates score improvements across all categories, tracks action item completion, and generates a "here's your progress" client report. Use when user says "compare", "delta", "monthly report", "progress", "confronta", "progressi", "report mensile", or when running a monthly client check

Lightweight entry point for small, well-understood changes