126 个 · 按相关度排序
Analyze the last seven days of agent and model token usage to identify unnecessary spending. Recommend changes to model selection, prompt caching, and overlapping work, with estimated dollar savings, percentage reductions, and implementation priorities.
中文简介正在准备中。当前显示英语简介。
Design an AI agent around its requirements, or audit an existing agent for architectural problems. Deliver justified decisions, verification plans, and a PDF report with a diagram, covering budgets, permissions, stopping rules, and failure handling.
中文简介正在准备中。当前显示英语简介。
Turn voice calls into GBrain records containing transcripts, summaries, audio links, and references to people or companies. The workflow also sends summaries to a configured messaging service; automatic processing when calls end requires additional implementation.
中文简介正在准备中。当前显示英语简介。
Build MCP servers, which let AI agents use external APIs and services through tools. The skill guides tool design, authentication, input validation, implementation, testing, and evaluation using TypeScript or Python.
中文简介正在准备中。当前显示英语简介。
Review development plans with external AI tools, then revise and review them again while actionable concerns remain. Choose reviewers and a cycle limit to work toward a plan with resolved review findings.
中文简介正在准备中。当前显示英语简介。
Build and update Convex backend code, including schemas, queries, authentication, storage, and scheduled jobs. Apply input and output validation, indexed data access, and deployment checks to verify the implementation.
中文简介正在准备中。当前显示英语简介。
Build MCP servers, which let AI agents use external APIs and services through tools. The skill guides tool design, authentication, input validation, implementation, testing, and evaluation using TypeScript or Python.
中文简介正在准备中。当前显示英语简介。
Guide a bug bounty investigation from scope checks and asset discovery to vulnerability testing, impact validation, and report writing. Covers web applications, source code, and AI features, with an emphasis on reproducible evidence of real harm.
中文简介正在准备中。当前显示英语简介。
Delegate a coding task to Aider (`aider`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Aider - phrasings like "have Aider do X", "delegate this to aider", "run it through Aider", or "use Aider to implement/fix/refactor" - or wants to run a queue of coding tasks through Aider while staying the reviewer. This includes asking Aider to drive a local or self-hosted OpenAI-compatible endpoint ("have Aider use my local model", "run Aider against llama.cpp / Ollama / vLLM / LM Studio"), which Aider reaches via `--api-base`. DO NOT USE for local-model or coding requests that do not name Aider, for tasks small enough to do inline, or when the user wants the code written directly without delegating.
中文简介正在准备中。当前显示原文说明。
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
中文简介正在准备中。当前显示原文说明。
Review generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. Invoke it on your own initiative the moment you finish writing, editing, or refactoring non-trivial production code, before presenting or committing — don't wait to be asked. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).
中文简介正在准备中。当前显示原文说明。
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
中文简介正在准备中。当前显示原文说明。
Use when auditing a codebase for semantic duplication - functions that do the same thing but have different names or implementations. Especially useful for LLM-generated codebases where new functions are often created rather than reusing existing ones.
中文简介正在准备中。当前显示原文说明。
Provides patterns to build declarative AI Services with LangChain4j for LLM integration, chatbot development, AI agent implementation, and conversational AI in Java. Generates type-safe AI services using interface-based patterns, annotations, memory management, and tools integration. Use when creating AI-powered Java applications with minimal boilerplate, implementing conversational AI with memory, or building AI agents with function calling.
中文简介正在准备中。当前显示原文说明。
Use this self-contained Browser Use repo skill for Python agents that automate websites, browser sessions, custom tools, LLM/provider setup, persistent CLI sessions, cloud/sandbox production deployment, MCP, skills, and troubleshooting. Prefer ChatBrowserUse by default and route to focused sub-skills for implementation details.
中文简介正在准备中。当前显示原文说明。
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
中文简介正在准备中。当前显示原文说明。
Suede AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates. Use when a change ships LLM, RAG, agent, classifier, prompt, or generated-media behavior, or when asked to write evals for an AI feature, design test cases for a model surface, audit existing eval coverage, or judge whether AI behavior is safe to ship. No AI-SPEC means no eval plan, and no eval plan holds the recommended ship verdict. NOT FOR: reviewing or grading the implementation code behind the AI surface (use suede-code); wiring a passing suite into CI as a required check (use suede-ci-gate); UAT of the built feature beyond the eval suite (a private Suede Labs companion, not in this pack).
中文简介正在准备中。当前显示原文说明。
Maintain the pure-Go SQLite password identity store, reusable parser, immutable account evidence, idempotent enrollment, portal injection, and login E2E tests. Excludes local JSON database internals and MFA/profile feature implementation.
中文简介正在准备中。当前显示原文说明。
Submit a pull request following the repo's contribution guidelines. Reviews the diff, checks for common rejection reasons, and helps the user write their own PR description. The LLM reviews. the user writes. Use when implementation is complete and tests pass. Not for responding to review comments after the PR is open. Use oss-post-pr for that.
中文简介正在准备中。当前显示原文说明。
Architect a feature with the Carmack Council before writing code. Use when explicitly asked to plan a feature, do a "council plan", "carmack plan", or invoke /council-plan. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js), Brandur Leach (Postgres), Vercel Performance, Simon Willison (LLM pipeline), Karri Saarinen (UI quality), Vitaly Friedman (UX quality). Interactive feature discovery followed by parallel subagent dispatch. Produces a sequenced, attributed implementation plan with no code. Stack: Next.js App Router / React / TypeScript / tRPC / Prisma / Neon / Clerk.
中文简介正在准备中。当前显示原文说明。
Package codebases into LLM-optimized markdown, and run the Deep Think Authority pipeline (context-builder → Deep Think review → structured AUTHORITY → Flash/Antigravity implementation agent). Use when generating project context, preparing Deep Think reviews, or binding a weaker coding agent to a senior reasoning pass.
中文简介正在准备中。当前显示原文说明。
Auto-activates when generating Product Requirements Prompt (PRP) documents from synthesized design outputs, providing structured templates and comprehensive implementation guidance.
中文简介正在准备中。当前显示原文说明。
Add technical context, implementation hints, and effort estimates to user stories
中文简介正在准备中。当前显示原文说明。
Create distinctive, production-grade frontends by composing design dimensions and tech-specific implementations
中文简介正在准备中。当前显示原文说明。