2,118 skills
Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in …
Use pup CLI for immediate Datadog operations or generate code for integration into applications
将课程课件、作业文件（PDF、DOCX、Markdown、HTML、图片等）、课堂代码和历史答案格式转成简洁的大学生风格 Markdown 作业答案，并可由主 agent 按模块调度子代理解题与 review。Use when asked to complete course homework, read homework files in varied formats, match homework to lectures/slides/code, use methods taught in class, imitate previous hw*_solution Markdown sty…
Designs cross-platform state management solutions compatible with React Native, Flutter, and native platforms
Store with XState. state store.
Score and validate phone numbers via Trestle's phone_intel API, then generate DataSift/REISift-ready CSVs with phone tags for upload. Use whenever someone wants to: validate phones, score activity, check if connected, generate phone tags for DataSift, prepare dial lists, prioritize a call list, ide…
Tyou 多语言文案/本地化/i18n 工作流 skill。涉及新增或修改多语言文本、`TableLocalizationText`、`#TableLocalizationText.xlsx`、`tyou.i18n.get`、`LocalizeLabel`、切语言显示、文案 key、中文/英文字段、导表后使用多语言时必须使用。会路由到 `luban-dev` 完成源 Excel 修改和导表，不用于手写字典或直接改生成代码。
Local opencode documentation reference (latest). OpenCode AI coding agent documentation. Use for agents, skills, tools, configuration, CLI, TUI, and MCP servers.
Systematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with parallel agents, self-validation, and optional adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow.
Generates type-safe API client code for mobile apps from OpenAPI/Swagger specifications
MS-DIAL-based metabolomics preprocessing as alternative to XCMS. Covers peak detection, alignment, annotation, and export for downstream analysis. Use when processing MS-DIAL output files for R/Python analysis or when preferring GUI-based preprocessing.
Use when structuring a FastAPI application, designing dependency injection chains, defining Pydantic v2 schemas, adding JWT authentication, or writing async route tests with httpx.
2. Isolate the quantization step responsible. The quantization pipeline is: fp32 input → quantize → int8 input int8 GEMM (or other op) with int32 accumulation int32 accumulation → dequantize → fp32/fp16 output Test each boundary: - Quant-dequant roundtrip: quantize the fp32 input to INT8, then imme…
Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.
Deploy and manage system services with serviceman. Use when adding, checking, or managing daemons on Linux (systemd/OpenRC) or macOS (launchctl).
Code-review workflow for Developer Studio repositories.
Theming with Bootstrap. custom themes.
Open a browser-based diff viewer showing all current changes in a VS Code-style file tree with syntax-highlighted diffs. Live-reloads as files change. Use when the user wants to "see the diff", "show changes", "what did I change", or "open diff viewer".
Structured task templates for agent coding work. Use when creating, assigning, or executing coding tasks that need clear structure, deliverables, and verification steps. Covers implementation, error analysis, fixes, and refactoring workflows with timeouts, checkpoints, and rollback plans.
Run all five review agents on changes, synthesize findings, triage based on developer thinking, and fix approved items. Trigger when the user says "review", "run the agents", "run all four", "run all five", "full review", "code review", or similar.
Modify Allbert in an isolated rebuild worktree, run Tier A validation, and produce an operator-reviewed patch.
Bundle a single marketplace delivery wrapper into a distributable archive, validating metadata and optionally publishing
Guide for creating new OAuth-based integrations in the Orient codebase. Use when adding external service integrations (APIs like Linear, GitHub, Slack, Notion, etc.), implementing OAuth flows, or creating catalog-based integration manifests. Covers the full integration lifecycle from manifest defin…
Professional code review with auto CHANGELOG generation, integrated with Codex AI
Expertise on the CI/CD pipeline, remote builds using Argo Workflows, Kaniko, and GitHub Actions in the ARM64 K3s cluster.
CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety system. Bun/TypeScript CLI.
Ensure quality across component-driven, headless digital platforms using Contentful, Next.js, Vercel, and Storybook. Design comprehensive QE/QA strategies spanning CMS content, APIs, frontend rendering, and CI/CD pipelines—catching bugs before users, not after launch.
VST3 format adapter for Pulp — SingleComponentEffect wiring, bus arrangement negotiation, parameter / MIDI event routing, state round-trip, and the pitfalls discovered while wiring the adapter against Steinberg's SDK.
Overall Equipment Effectiveness calculation skill with loss categorization and improvement analysis.