Loading...
Loading...
Found 2,153 Skills
Comprehensive LLM audit. Model currency, prompt quality, evals, observability, CI/CD. Ensures all LLM-powered features follow best practices and are properly instrumented. Auto-invoke when: model names/versions mentioned, AI provider config, prompt changes, .env with AI keys, aiProviders.ts or prompts.ts modified, AI-related PRs. CRITICAL: Training data lags months. ALWAYS web search before LLM decisions.
Scaffold and implement GitHub Apps from existing automation ideas using Probot + @octokit/app. Use when turning scripts, bots, or manual GitHub workflows into a proper GitHub App.
Create powerful pitch closings with market insights, proprietary advantages, founder mission, and subtle FOMO triggers in under 45 seconds.
Design new APIs or review existing ones using debate-driven multi-agent workshop. Agents propose designs and challenge each other on consumer UX, domain modeling, security, performance, and standards compliance. Use when the user wants to design a new API, review an existing API, decide between REST/GraphQL, or improve API architecture. Keywords: api design, api review, rest api, graphql, openapi, api architecture, api specification, endpoint design, api standards.
Use when converting a design document, PRD, or task list into beads issues - ensures lossless conversion with proper epic hierarchy, validated dependencies for maximum parallelization, and three independent subagent review passes before execution
Create and maintain a control-system metalayer for autonomous code-agent development in any repository. Use when you need explicit control primitives (setpoints, sensors, controller policy, actuators, feedback loop, stability and entropy controls), repo command/rule governance, and a scalable folder topology that lets agents operate safely and keep improving over time.
Diagnoses sales needs and sequences appropriate skills for comprehensive deal execution. Use this skill when unsure which sales skill to use, planning multi-step deal strategies, coaching reps on process, or coordinating complex sales motions.
Drive an evidence-driven, iterative product+engineering spec process that produces a full PRD + technical spec (often as SPEC.md). Use when scoping a feature or product surface area end-to-end; defining requirements; researching external/internal prior art; mapping current system behavior; comparing design options; making 1-way-door decisions; planning phases; and maintaining a live Decision Log + Open Questions backlog. Triggers: spec, PRD, proposal, technical spec, RFC, scope this, design doc, end-to-end requirements, phase plan, tradeoffs, open questions.
Researches how the industry solves a defined issue, collects references from engineering blogs, open-source projects, and technical articles, then produces a design document with industry baseline, research summary, design goals, non-goals, and proposed design. Use when an issue definition exists in docs/issues/ and a concrete design is needed before implementation begins.
Query PostgreSQL with Prisma 7 efficiently, using Prisma Client for mutations and selectively using raw SQL for complex/performant reads (SELECT/COUNT) when appropriate.
Run application agents through SpendGuard with strict hard budget caps. Use when setting up `spendguard-sidecar`, creating agent IDs, setting or topping budgets, sending OpenAI/Grok/Gemini/Anthropic calls through SpendGuard endpoints, and troubleshooting budget enforcement errors like insufficient budget, in-flight lock conflicts, missing `x-cynsta-agent-id`, or remote pricing signature failures.
This skill should be used when the user needs to query COSMIC Cancer Gene Census to check if genes are known cancer genes. Triggers include requests to annotate genes with cancer information, check if variants are in cancer genes, or retrieve cancer gene properties from COSMIC database.