2734 个 · 按相关度排序
Find UX pains and opportunities fast through competitor scans, pattern research, and web search. Surfaces how others solve the same flow, common failure modes, and conventions users already expect. Use when the user says "research this UX", "how do others do X", "competitor scan", "find UX patterns", "what's the convention for Y", or before ideating a flow. Part of the Product Design set. Uses web search/fetch tools.
中文简介正在准备中。当前显示原文说明。
Adversarial dialectic tool inspired by GAN. Alternates between Generator (creative advocate) and Discriminator (adversarial critic). Supports forced role selection (g/d), intensity modes (hard/soft), and multi-language output. Use for stress-testing ideas, business plans, code, and spec designs.
中文简介正在准备中。当前显示原文说明。
Rates a project with Jevaluate and keeps the rating private, with the same rubric and checks, a private library that export refuses, and nothing pushed or published. Use when a rating must stay private, such as "/jevaluate-private" followed by a link or folder, "rate this privately", "evaluate my own project", a client's or employer's code, a design doc or a local folder that isn't public, or any rating that must not reach the public ratings or the repo.
中文简介正在准备中。当前显示原文说明。
The sprint completeness oracle — a mechanical, exit-code-driven check that every feature in a sprint manifest is provably complete across three dimensions (a done-record reference, resolvable edge tests, and a resolvable wiring test). Fails loud with a per-feature gap list naming the missing dimension. Read-only. Use to gate a sprint before it is called done (Slice A of the sprint-mode epic), or any time you want a completeness reading.
中文简介正在准备中。当前显示原文说明。
Report the NeatContext context and routing mode active in the current Kimi Code session, including missing-file or stale-routing warnings. Use when the user asks which context is connected or explicitly invokes this skill.
中文简介正在准备中。当前显示原文说明。
Show or set NeatContext routing to auto, ask, or manual for the current Kimi Code session, with an optional global default for new sessions. Use only when the user explicitly invokes this skill or clearly asks to change routing behavior.
中文简介正在准备中。当前显示原文说明。
Report the NeatContext context and routing mode active in Codex, including missing-file or stale-routing warnings. Use when the user asks which context is connected or explicitly invokes this skill.
中文简介正在准备中。当前显示原文说明。
Show or set NeatContext routing to auto, ask, or manual for Codex, with an optional default shared with every other NeatContext host. Use only when the user explicitly invokes this skill or clearly asks to change routing behavior.
中文简介正在准备中。当前显示原文说明。
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.
中文简介正在准备中。当前显示原文说明。
Delegate a prompt to Claude via `claude -p`. Use when the user wants to offload a task to Claude from another agent (Codex, Cursor, another Claude session), get a second opinion, or run a parallel implementation. Default model is opus.
中文简介正在准备中。当前显示原文说明。
TDD pair programming with mode switching. Claude can be driver (writes code) or navigator (watches, questions, provokes). Supports GitHub issues, file watching, or arbitrary prompts. Scientific TDD, baby steps, one test at a time. Trigger on: pair, let's pair, tdd, you drive, I'll drive, dojo.
中文简介正在准备中。当前显示原文说明。
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.
中文简介正在准备中。当前显示原文说明。
Phase exécution. Détecte le mode (epic/task/bug) selon le type d'issue et lance le bon mécanisme : loop driver background pour epic, code-dev synchrone pour task/bug. Usage: /implement <issue#>
中文简介正在准备中。当前显示原文说明。
Conception pipeline for Codex. Equivalent to the repository's Claude skill: detect epic/task/bug mode, then delegate to the existing repo agents and workflows. Usage: /analyse [<issue#>] [<description>]
中文简介正在准备中。当前显示原文说明。
Shared in-workflow quality gates for code/PR skills — the gate model, trust tiers, and the three primitives (evidence-before-done, independent judge, anti-gaming). DO NOT TRIGGER directly — referenced by consumer skills via relative path.
中文简介正在准备中。当前显示原文说明。
[Process] Use when a developer needs to understand and judge scoped work: a change set, subsystem, decision, plan or concept — flow, rationale, trade-offs, testing. Bugs: investigate --mode=debug; one feature's code flow: investigate.
中文简介正在准备中。当前显示原文说明。
[Implementation] Use when the user asks to build a feature from an idea or description with no plan file yet: research and trace the code, create and get the plan approved, build each phase with its tests, review, verify once, sync specs and docs. Existing plan: plan --mode=execute.
中文简介正在准备中。当前显示原文说明。
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
中文简介正在准备中。当前显示原文说明。
Model visible context
中文简介正在准备中。当前显示原文说明。
Practical security review and hardening guidance for application code in Python, JavaScript/TypeScript, and Go. Use this skill whenever the user asks for a security review or audit, wants to harden authentication (password hashing, sessions, JWT, OAuth2/OIDC, MFA), fix OWASP Top 10 issues (injection, XSS, IDOR, CSRF, SSRF, deserialization), threat-model with STRIDE, clean up secrets and .env handling, or set up dependency scanning (pip-audit, npm audit, osv-scanner, gitleaks, SBOM). Also trigger for "make this secure", "is this safe to deploy", bcrypt/argon2id, rate limiting logins, RBAC/ABAC, CSP and security headers, cookie flags, and secure-by-default coding help.
中文简介正在准备中。当前显示原文说明。
Brand mention and authority scanner for AI visibility. Analyzes brand presence across platforms that AI models rely on for entity recognition and citation decisions. Produces a Brand Authority Score (0-100) with platform-specific recommendations.
中文简介正在准备中。当前显示原文说明。
Especialista em event sourcing, CQRS e padrões de arquitetura orientada por eventos. Domina design de event store, construção de projeções, orquestração de sagas e padrões de consistência eventual. Use PROATIVAMENTE para sistemas baseados em event sourcing, requisitos de trilha de auditoria ou modelagem de domínio complexa com consultas temporais.
中文简介正在准备中。当前显示原文说明。
Escrever código C++ idiomático com recursos modernos, RAII, smart pointers e algoritmos STL. Trata templates, move semantics e otimização de desempenho.
中文简介正在准备中。当前显示原文说明。
Escreva código C# moderno com recursos avançados como records, pattern matching e async/await. Otimiza aplicações .NET, implementa padrões empresariais e garante testes abrangentes.
中文简介正在准备中。当前显示原文说明。