2,118 skills
Specialized skill for building production-ready serverless applications on GCP. Covers Cloud Run services (containerized), Cloud Run Functions (event-driven), cold start optimization, and event-driven architecture with Pub/Sub.
Use when a fast end-to-end smoke run is needed for the Eve loop development, will run on circle packing task.
Generate reflections for past Codex session histories using the Reflection CLI. Use when asked to summarize or reflect on previous Codex conversations, list projects/sessions, filter by date or session id, or refresh cached reflections from ~/.codex/sessions.
Diagnosticá problemas de performance frontend con evidencia antes de proponer cambios. Usá esta skill solo cuando el usuario pida analizar lentitud de navegación, renders excesivos, fetches duplicados, useEffects redundantes, componentes pesados o cuellos de botella visibles.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them …
Add, remove, list, or swap GitHub Actions self-hosted runners on a CI host that uses the env-var-driven `gh-runner` docker image (raw `docker run`, no compose). Triggers, "add gh runner", "remove gh runner", "list ci runners", or similar. Run `setup-ci-host` first if /data/miles_ci is not yet provi…
HackenProof bug bounty triage workflow for Claude Code plugin marketplace operations. Use when analyzing security reports, validating scope and exploitability, assigning severity, detecting duplicates, setting report state, adding labels/comments, and preparing consistent triage decisions for Hacke…
Use Mirra to voice call history, transcripts, and call metadata. Covers all Voice SDK operations via REST API.
Apply Test-Driven Development workflow for new features and bugfixes.
使用 wrangler CLI 操作 Cloudflare。当用户提到 Cloudflare、CF、Workers、Pages、R2、D1、KV、CDN、DNS、WAF 等时触发此技能。
Performs structured code reviews on pull requests or code changes. Use when asked to review a PR, check code quality, analyze diffs, or provide feedback on code changes. Follows a systematic methodology covering correctness, readability, performance, and security.
维护 .ai_state/architecture/ 长效档案 (项目现状档). Refactor/System 路径完成后强制更新 ARCHITECTURE.md 总入口 + {type}-{slug}.md 子系统档. 注: 不同于 cx 端的 architect.toml subagent (后者是 design stage 工作者).
Bun 作为运行时、包管理器、打包器和测试运行器。何时选择 Bun 而非 Node、迁移注意事项以及 Vercel 支持。
Use this skill when writing new features, fixing bugs, or refactoring code in Verendar. Enforces test-driven development with 80%+ coverage using xUnit, FluentAssertions, NSubstitute, and Testcontainers. Activate proactively whenever the user is about to write new application code, fix a bug, or ad…
Development skill from everything-claude-code
ALWAYS use when writing code importing "satori". Consult for debugging, best practices, or modifying satori.
JWT implementation, token management, refresh patterns, and security.
Use when choosing which Prefactor SDK skill to load for agent instrumentation or for building a custom provider integration on top of @prefactor/core.
AFSIM 2.9.0 仿真技能：创建、编译、调试、可视化和分析仿真场景。 工作流：写 .txt → mission.exe 编译 → 修复错误 → mystic.exe 可视化 → Python 分析。
Implements full-stack features spanning database, API routes, and React UI for the Katalis platform.
Homey (Athom) app development with SDK v3 — manifest/compose structure, drivers, capabilities, flow cards, Node.js runtime constraints, CLI commands, validation and publishing. Use when working on this Homey app (drivers, capabilities, flows, app.json, .homeycompose) or any Homey apps SDK question.
Red-Green-Refactor test-driven development cycle
Allocate canonical project-scoped output directories, audit workflow artifacts, and drive reviewed cleanup plans through the nils-cli `agent-out` command.
Design predictive maintenance strategies using sensor data, ML models for remaining useful life (RUL), and the P-F curve framework. Use this skill when the user needs to reduce unplanned downtime, transition from reactive to predictive maintenance, evaluate sensor/IoT investments, or estimate equip…
Query, search, and manage repositories indexed by Greptile (AI codebase intelligence). Use when asking questions about a codebase, searching for code patterns, indexing repos for Greptile review, or checking Greptile index status. Requires GREPTILE_TOKEN and a GitHub/GitLab token.
Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelligently routes to sub-agents for codebase research, clarifying questions, or web search as needed.
Use when the user asks about Django at specialist level - models/ORM, QuerySets, URLs, views (FBV/CBV), templates, forms, auth, migrations, transactions, security, middleware. Triggers PT/EN - "Django", "model Django", "QuerySet", "ORM Django", "view Django", "form Django", "migration Django", "aut…
Align a technical document with the actual code implementation and correct drift. Use when a user asks to update docs to match current behavior, audit a technical document against the repository, or fix stale architecture, API, workflow, or operator documentation.
Start the frontend dev server. Use when user wants to start the frontend or mentions /run-frontend command.
Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.