Use this skill when you need a four-agent execution team that humans can see and type into directly.

Use when reviewing a PIDA branch, diff, or PR. Focus on bugs, regressions, missing tests, API contract drift, persistence risks, and operational issues before style comments.

Create clean, conventional git commits

Verify that a change really works before you claim completion

Use this skill when editing src/parsers, src/instruments, src/domain, or parser-backed normalization code and tests. Trigger on tasks involving trace export parsing, normalization, ranking inputs, adapter contracts, or schema stability. Do not use for unrelated CLI or documentation-only changes.

Use when working on nex-editor architecture or implementation, especially the Rust editor core, runtime facade, WASM bridge, browser playground, or cross-platform rendering protocol.

Walks the merchant through Stripe onboarding, captures their API keys, and writes them to Vercel env vars. Handles the common case where KYC takes days by supporting a preview-mode deploy path.

Test-driven development workflow with test generation, coverage analysis, and multi-framework support

A skill for driving GitHub pull request creation. Handles change review, required checks, commit, push, and PR creation in one flow, and expects fresh verification evidence from `code-change-verification` when repository code changed.

Use when a task needs an implementation plan that is iteratively created and stress-tested through review-and-revise cycles before implementation begins — catches blind spots, incorrect codebase assumptions, unnecessary complexity, and performance pitfalls while changes are still cheap

>

Use the open-source free `Roslynator` analyzer packages and optional CLI for .NET. Use when a repo wants broad C# static analysis, auto-fix flows, dead-code detection, optional CLI checks, or extra rules beyond the SDK analyzers.

Build, debug, modernize, or review ASP.NET Core applications with correct hosting, middleware, security, configuration, logging, and deployment patterns on current .NET.

Use when creating a new pinu-bot character or doing a major character redesign. Covers neutral-first design, shared API mapping, emotion-family construction, visual harness review, and finish criteria for cross-state cohesion. Do not use for small one-off expression tweaks.

React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.

Review a GitHub pull request for this repository when the user starts the prompt with `$pr-review` followed by a PR number, such as `$pr-review 105`. Conduct a real PR review focused primarily on backend correctness, API/schema consistency, persistence/runtime safety, and frontend interoperability with the backend. Submit the final review on GitHub as either approval or changes requested.

Three.js performance optimization and best practices guidelines. Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving 3D scenes, WebGL/WebGPU rendering, geometries, materials, textures, lighting, shaders, or TSL.

Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Use when the user asks to create, build, modify, analyze, read, validate, or format any Excel spreadsheet, financial model, pivot table, or tabular data file. Covers: creating new xlsx from scratch, reading and analyzing existing files, editing existing xlsx with zero format loss, formula recalculation and validation, and applying professional financial formatting standards. Triggers on 'spreadsheet', 'Excel', '.xlsx', '.csv', 'pivot table', 'financial model', 'formula', or any request to produce tabular data in Excel format.

>-

Perform high-rigor structural and aesthetic audits with findings-first output, actionable remediation, and governance-aware preconditions.

python-expert

>

>

Debugs Next.js App Router issues systematically. Use when hitting a build error, hydration mismatch, server action failure, or runtime crash.

Extend, edit, validate, and review shipped Grafana dashboards for BioETL. Use when tasks touch `grafana/dashboards/*.json`, dashboard navigation, panel queries, variables, units, thresholds, Loki/Tempo drilldowns, or operator-facing dashboard UX. Treat repo dashboard JSON as source of truth and update docs when shipped dashboard behavior changes.

Meta-skill for the Turri bundle that routes natural language health conversations to the right capability — nutrition logging, health profile, pattern discovery, experiments, news, or daily coaching.

Add a Civilization-style ceremonial quote when a substantial task is truly complete. Use this whenever the user or agent is wrapping up a real deliverable such as a feature, refactor, analysis, design doc, process change, report, or writing task, even if they do not explicitly ask for a quote; skip short replies, tiny fixes, and unfinished work.

academic-search

A learning skill that teaches Java and Spring Boot to an experienced Go developer through iterative project building and Go-to-Java concept mapping.

OpenClaw 하네스 — Plan→Work→Review 에이전트 오케스트레이션 + 모델 라우팅 + 채널 브릿지. Claude Code 하네스 생태계 분석 기반. GLM/GPT/Claude 모델 지원. GLM-5.1 포함. 한국어 감지→GLM 자동 라우팅. sessions_spawn으로 에이전트별 모델 별도 지정. 브릿지로 실시간 채널 알림.

>

Run, debug, maintain, or extend ExaAiAgent for AI-assisted penetration testing, attack-surface mapping, repo/code security review, and multi-agent offensive-security workflows. Use when an AI agent needs onboarding instructions for operating ExaAiAgent, when a user wants to launch scans from CLI/TUI, when ExaAiAgent itself needs maintenance, or when another agent should use ExaAiAgent with any LiteLLM-supported provider (OpenAI, Anthropic, OpenRouter, Ollama, Gemini-compatible endpoints, and other LiteLLM-backed providers).

ShanghaiTech graduate thesis formatting, structure checking, and LaTeX implementation with shtthesis. Use when creating, linting, fixing, or migrating a ShanghaiTech thesis or dissertation, especially for LaTeX projects that need compliant covers, abstracts, table of contents, chapter structure, references, appendices, blind-review builds, or print-ready output.

Creates typed mock data files in src/data/ following project conventions. Use when needing test data for new features or components.

A full pipeline that systematizes an organization's strategy framework through OKR design, BSC mapping, SWOT analysis, vision & mission statement, and strategy execution roadmap. Use this skill for 'build a strategy framework,' 'design OKRs,' 'BSC analysis,' 'SWOT analysis,' 'write vision and mission,' 'strategy roadmap,' 'strategy formulation,' 'mid-to-long-term strategy,' 'business strategy framework,' and 'strategy system design' — across the full spectrum of organizational strategy development. It also supports supplementing and validating existing OKRs or SWOT analyses. Note: Financial statement preparation, ERP system implementation, performance review execution, and real-time KPI dashboard development are outside the scope of this skill.

Execute repo work one task at a time using a strict plan → execute → iterate loop tracked in .copilot-todo.yaml.

Fuzzing for finding edge cases and crashes

Ship the current branch into `develop` with the full GitHub flow: verify repo state, run the right tests, commit if needed, push, create or reuse a PR, request Codex review, address findings until clean, and merge when safe. Use when the user asks to merge the current branch into `develop`, create a PR and let Codex review it, or finish a reviewed PR merge automatically.

UI-first implementation and staging workflow for Zeus. Use when building routes, components, or forms before backend integration, or when creating UI scaffolds with mock data and later wiring to real APIs.

Generate polished HTML slide presentations from video scripts, outlines, or topic briefs. Produces single-file HTML with scroll-snap navigation, animations, and distinctive design. Use when user asks to create a presentation, slide deck, or wants to turn a script/outline into visual slides.

Use kpf, a fast, idempotent drop-in replacement for kubectl port-forward that manages and reuses port-forward sessions. Use when a user needs repeatable Kubernetes port forwarding with quick startup.

Performance analysis, profiling techniques, bottleneck identification, and optimization strategies for code and systems. Use when the user needs to improve performance, reduce resource usage, or identify and fix performance bottlenecks.

Coding factory — transforms a spec into a reviewed PR via BUILD → INSPECT pipeline with adversarial review. Use when you need to implement a spec end-to-end with independent code review, or when the user invokes /factory run <spec-path>.

juicebox-performance-tuning

>

MiniMax MCP server integration with token-efficient AI delegation. Use for web search, image analysis, MCP server integration in terminal/desktop Claude, and Claude-MiniMax collaboration patterns. Provides working scripts and slash commands.

Validates directory naming conventions for titles, assemblies, and modules. Use when restructuring content or adding new directories.

oh-dear