一个技能，一个新的可能。找到适合你的 AI 工作流。
andrej-karpathy
【开发与工程】Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
sharp-coder
【开发与工程】Two-layer performance skill combining disciplined THINK layer (surgical edits, simplicity) and terse SPEAK layer (caveman compression). Triggers on requests for brevity, token efficiency, or disciplined coding.
building-workflows
【设计与创意】Build, edit, test, enable, and monitor PostHog workflows over MCP. Author the action/edge graph so it runs and opens cleanly in the visual editor, then change drafts surgically with patch operations. Use when asked to build, set up, automate, change, fix, or debug a workflow, campaign, broadcast, drip sequence, or event-triggered automation in the wo…
refactor
【设计与创意】Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
karpathy-coder
【开发与工程】Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM mi…
redesign
【设计与创意】Upgrade an existing website or app to premium quality without breaking functionality — audit the current design, identify generic/AI tells, then apply taste and system rules surgically. Use when the user wants to improve, modernize, polish, or "make better" an existing UI/codebase.
render-hook-replacement
【开发与工程】Replace an existing video's opening with a supplied clip or free kinetic text hook while retaining and verifying every original body frame, audio, captions and ending. Use for surgical hook tests rather than regenerating the complete ad.
ugc-fixloop
【开发与工程】the UGC fix-loop toolkit — surgically re-render a bad window/beat of a single-take UGC master (stitch_replacement.py, pure FFmpeg) and GPT cross-model review a Seedance prompt before render (vet_seedance_prompt.py, routed through the openai-proxy). Fetch it into a one-shot UGC recipe so both scripts resolve on any machine and the vet call bills the A…
behavioral-guidelines
【开发与工程】Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
karpathy-guidelines
【开发与工程】Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
code-sync
【文档与办公】Reconcile the project's documents with what the code now shows, after a merge or at the end of a build: spec statuses (building → done only with a named gate, or → stale with the reason), assumed specs owed ratification, the project README map and its Last verified date. Surgical edits only. Use when the user says "/memory-kit:code-sync", "sync the d…
zipai-optimizer
【效率与协作】ALWAYS use this when the request matches Zipai Optimizer: Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware.
workflow-coding-discipline
【开发与工程】Guardrails for writing, editing, refactoring, or debugging code: surface assumptions, simplicity first, surgical changes. Use when vibe-coding keeps producing wrong results, or for "think before coding" or "surgical changes".
agentprivacy-archer
【效率与协作】Precision Strike Operative (Ranger variant) for 0xagentprivacy. Activates for single-property disclosure operations, maximum-precision minimum-residue proofs, targeted credential verification, or any task requiring surgical privacy operations — reveal exactly one truth and leave no trace.
amazon-competitor-analyzer
【设计与创意】Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
generic-react-code-reviewer
【开发与工程】Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or reviewing pull requests.
github-code-reviewer
【开发与工程】Review GitHub PRs with surgical precision. Flag only high-severity issues (bugs, security, performance, breaking changes) via succinct inline comments on specific lines. Skip style, nits, and minor improvements. High signal, low noise.
gradle
【文档与办公】Provides authoritative guidance for ALL Gradle operations: executing builds, running tests with surgical filtering, introspecting project structure, creating modules, and diagnosing failures; ALWAYS use instead of raw shell `./gradlew` for build execution, test runs, task introspection, module creation, performance audits, and documentation research.…