Explorar skills

Use PROACTIVELY when the user invokes /implement <slug> or asks "now build it / run the tasks / execute the plan". Runs the `implementer` subagent in a forked context which walks specs/<slug>/tasks.md and writes src/** + tests/** one task at a time, one commit per task.

Read-only report on the active feature — phase, active slice, next action, evidence, open questions, drift, risks, handoff readiness. Use when the user says "where am I", "what's next", "status", "is this ready to ship", "show the active feature". Not for invoking phases or for the menu (use `/rite`).

Compatibility wrapper for the legacy PM leadership workflow covering org design, coaching, product judgment, AI strategy, and career growth.

Esta skill oferece sessões noturnas autônomas universais que escaneiam projetos, identificam problemas como segurança, código morto e performance, e geram um loop bash para corrigi-los usando novas sessões Claude enquanto você dorme. Ela cria um pull request para revisão matinal.

Safety check before executing destructive or irreversible commands. Catches dangerous shell commands, risky git operations, secret exposure, and high-blast-radius actions before they run. Activates automatically when Claude is about to execute shell commands that match known risk patterns. Trigger phrases: "check before running", "is this command safe", "safety check", "pre-execution review".

Audit ytstack internal consistency. Compares README (source of truth) against docs/concept.md, .ytstack/DECISIONS.md, and actual plugin content (skills/, hooks/, agents/, artifacts). Reports drift: missing or extra skills, workflow mentions that do not resolve to real skills, trigger-map gaps, hook-list mismatches, skill-count drift, banned-words hits. Run before approving doc changes or after a v

One-command health check. Exercises every hook path and reports pass/fail per hook — without writing to vault/. Trigger when the user says "status", "health check", "is everything wired up", "did the install work", "dashboard", or invokes /llm-wiki-stack:llm-wiki-status directly. Strictly read-only against vault content; any accidental write is the skill's own bug.

O encurtador de URL PicSee via MCP permite encurtar URLs, gerar códigos QR, visualizar análises detalhadas de cliques e gerenciar links. Ele suporta encurtamento anônimo de URL, com recursos autenticados completos disponíveis via OAuth 2.1.

14 opinionated skills for running a healthcare AI startup as a solo founder — daily briefings, PMF intelligence, sales coaching, conference pipelines, and content creation as slash commands

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series a

Analisa qualquer processo de negócio manual ou repetitivo e gera um plano de automação completo, incluindo diagrama de arquitetura, pontuação de automação, cálculo de ROI, plano de implementação e recomendação de tecnologia.

Use when the user asks to design database schemas, plan data migrations, optimize queries, choose between SQL and NoSQL, or model data relationships.