Receber por email

Explorar skills

31.375 skills encontradas

dev:validate

38

Use when the user wants to validate the plugin, check integrity, verify cross-references, or before a release. Also use when the user says 'validate', 'check plugin', or 'verify'.

Automação #ai por raphaelchristi

task

38

Create a living task doc from natural language. Use when you want to track work, capture a new project, or create a thinking log that accumulates context across sessions.

Automação #ai por lsnackerman

dev:release

38

Use when the user wants to release a new version, publish to npm, create a GitHub release, bump version, or tag a release. Also use when the user says 'release', 'publish', 'bump version', 'tag', or 'npm publish'.

Desenvolvimento #ai #git por raphaelchristi

sync

38

Refresh the current session's LOG with a fresh extraction. Use as the last step of /wrap, or any time the session has continued and you want the capture current. Idempotent — safe to invoke multiple times.

Automação #ai por lsnackerman

explore

38

Build topic reserves by searching your entire system, or run discovery mode to find what connects across territories. Use when consolidating scattered knowledge on a topic, before writing/sharing, or when curiosity has no specific target.

Design e Frontend #ai por lsnackerman

harness:setup

38

Use when the user wants to set up the evolver in their project, optimize an LLM agent, improve agent performance, or mentions evolver for the first time in a project without .evolver.json.

Automação #ai #llm por raphaelchristi

harness:deploy

38

Use when the user is done evolving and wants to finalize, clean up, tag the result, or push the optimized agent.

DevOps e Infra #ai #deploy por raphaelchristi

floor

38

Open the floor for your AI's curiosity. Use when wrapping or at natural pauses.

Automação #ai por lsnackerman

heartbeat

38

Scan the system with fresh eyes. Surface what's alive, what's connecting, what's trying to emerge. Route insights where they belong.

Automação #ai por lsnackerman

autostar

38

Esta skill oferece um loop de otimização autônoma generalizada, utilizando RLVR suave para aprimorar iterativamente qualquer artefato mensurável, como código, prompts ou designs. Ela realiza isso executando experimentos estruturados, avaliando resultados com uma rubrica multidimensional e aprendendo a cada tentativa.

Pesquisa e Web #ai por chrisvoncsefalvay

harness:evolve

38

Use when the user wants to run the optimization loop, improve agent performance, evolve the agent, or iterate on quality. Requires .evolver.json to exist (run harness:setup first).

Design e Frontend #ai por raphaelchristi

wrap

38

End work session intentionally. Use at natural stopping points, before context limits, or when switching contexts.

Automação #ai por lsnackerman