Loading...
Loading...
Found 765 Skills
Use when starting feature work that needs isolation - creates a temporary branch for implementation work with safety verification
Use when writing server-side code with Supabase — Edge Functions, Hono apps, webhook handlers, or any backend that needs Supabase auth and client creation. Trigger whenever the user imports from `@supabase/server`, mentions `supabase/server`, Supabase Edge Functions, or needs server-side auth (JWT verification, API key validation, CORS handling) with Supabase. Also trigger when you see legacy patterns in existing code — `Deno.serve`, `createClient(Deno.env.get('SUPABASE_URL'))`, imports from `esm.sh/@supabase`, `deno.land/std` serve, or usage of `SUPABASE_ANON_KEY` / `SUPABASE_SERVICE_ROLE_KEY` — these indicate code that should be migrated to this package.
Produces async communication to stakeholders, primarily non-attendees and secondarily some attendees who want a reference. Translates meeting outcomes into what-it-means language for readers, with channel variants (slack, teams, email, notion, exec-memo) and audience variants (engineering, design, leadership, customer-facing, mixed). Surfaces a primary CTA up front, flags technical-to-business translations for user verification, and detects thread continuation from prior updates.
Performs a comprehensive health check of a CockroachDB cluster. Gathers deployment context first, then provides tier-appropriate diagnostics. Self-Hosted uses SQL against node-level system tables and CLI. Advanced/BYOC use Cloud Console and SQL with node visibility. Standard monitors provisioned compute and workload via Cloud Console. Basic monitors Request Unit consumption and connectivity. Use for daily checks, pre-maintenance validation, post-incident verification, or production readiness assessment.
Step-by-step analysis for complex problems — multi-step reasoning, hypothesis verification, adaptive planning with revision.
Post-implementation cleanup that removes AI-generated bloat while preserving functionality. Runs pass-by-pass with test verification after each pass. Activate after kraken/spark complete a feature, or when a codebase needs hygiene work.
Visual + DOM diff between two recorded sessions at matching trajectory step ids; used for visual regression and replay verification
Use GitHub MCP, Context7 MCP, and Exa WebSearch MCP to search and answer based on problem scenarios. This skill must be used when users require web retrieval, GitHub project lookup, source code verification, framework or SDK document lookup, API usage lookup, global information lookup, official websites, blogs, product information, news, or comparison materials. This skill strictly prohibits Bash, subagent, and ordinary file retrieval tools from participating in external searches.
Runs the full validator workflow after coding tasks for requests such as "run the validator", "run final verification", "validate before commit", or "run validation". Executes checks and reviews before commit, push, or PR creation.
Novel Research Skill. Used for searching and organizing writing materials, genre references, real-world research, professional details, historical and geographical information, technical data, case inspirations, visual references, and market observations; stored in research.yaml, records, or notes. Activated when users request information searching, material collection, latest updates, research verification, background authenticity, modifying research notes, or saving sources.
Configure webhooks to receive inbound messages and delivery updates with signature verification.
Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or dependency upgrades. Smoke / canary / post-deploy verification.