Explorar skills
31.375 skills encontradas
ql-verify
Part of the quantum-loop autonomous development pipeline (brainstorm \u2192 spec \u2192 plan \u2192 execute \u2192 review \u2192 verify). Iron Law verification gate. Requires fresh evidence before any completion claim. Use before claiming work is done, before committing, or before marking a story as passed. Triggers on: verify, check, prove it works, ql-verify.
inngest-steps
Use when implementing delays that must survive process restarts (e.g., 24-hour cart abandonment, scheduled follow-ups), waiting for human approval or external events with timeouts (review gates, webhook callbacks, async API completion), polling external services without losing state on crashes, calling other functions and awaiting their results, memoizing expensive operations so they don't re-run
brain-hydrate
Use when users want to bootstrap the brain with existing project knowledge -- reading ADRs, feature specs, UX docs, commit history, and error patterns to seed institutional memory on a project that already has artifacts on disk. Also use for incremental re-hydration after significant work outside the pipeline. Triggers on "hydrate brain", "bootstrap brain", "seed memory", "brain init", "populate b
writers-room-story-engine
Orquestra o desenvolvimento modular de histórias, diagnosticando a fase atual e direcionando para a skill apropriada (fundamentos, construção de mundo, escrita de cenas ou revisão). Utilize ao criar uma história do zero, aprimorar um esboço, fortalecer a estrutura narrativa ou guiar o desenvolvimento em fluxos de trabalho.
pipeline-uninstall
Use when users want to remove the atelier-pipeline multi-agent orchestration system from their project. Cleanly removes all installed files, hook registrations, and CLAUDE.md pipeline section. Preserves user-created custom agents.
inngest-realtime
Use when streaming durable workflow updates to a UI in real time — live order status pages that animate as steps complete, AI agent token streaming from a function to the browser, log tailing for long-running jobs, or human-in-the-loop approval flows that publish a prompt and wait for a user reply. Covers Inngest v4 native realtime: defining typed channels, publishing from inside step.run, minting
flight-check
Realiza uma revisão de qualidade final para apresentações quase prontas antes de serem enviadas ou apresentadas. Utilize quando o usuário compartilha um PowerPoint, PDF, capturas de tela de slides ou texto de slides e solicita uma revisão, verificação final, checagem de sanidade, prontidão, polimento, fontes, citações, ou se a apresentação está pronta. Não use para rascunhos iniciais ou geração de conteúdo.
inngest-durable-functions
Use when building functions that must survive process crashes, retry automatically on failure, run on a schedule, react to events, or maintain state across infrastructure failures — e.g., webhook handlers that drop events, flaky cron jobs, background jobs that fail mid-execution, or workflows that need to resume where they left off. Covers Inngest function configuration, triggers (events, cron, in
webhook-verifier
Reference for cryptographic verification of payment webhooks. Cited by integration-specialist whenever it generates a webhook handler. Documents per-provider signature algorithms, timestamp tolerances, replay-protection strategies, raw-body capture per stack, and the minimum set of events each handler must route. Always use this skill (instead of recalling from training data) — webhook verificatio
claude-plugins
Quick test suite to verify Hive tools are working correctly
cpg-analysis
This skill should be used when the user asks about "Code Property Graph", "CPG analysis", "Joern queries", "CPGQL", "data flow verification", "taint tracking with Joern", "semantic code analysis", or needs to understand how CPG-based verification works for vulnerability detection.
framework-patterns
This skill should be used when the user asks about "framework vulnerabilities", "Next.js security", "Flask security", "Django security", "Rails security", "Spring security", "GraphQL security", "Server Actions", "render_template_string", "SSTI patterns", "redirect SSRF", "mass assignment", "actuator exposure", "SpEL injection", "introspection", or needs to identify framework-specific vulnerability