Use when the task involves reading, creating, or editing `.docx` documents, especially when
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions,…
Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime,…
Help address review/issue comments on the open GitHub PR for the current branch using gh — from luokai0/ai-agent-skills-by-luo-kai
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; — from org/repo
Batch-generate images through the OpenAI Images API with a prompt sampler and gallery output.
Compatibility alias for OpenAI platform documentation guidance. Delegate to the canonical local `openai-docs` payload while preserving route compatibility.
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout — from luokai0/ai-agent-skills-by-luo-kai
Use when the task requires automating a real browser from the terminal (navigation, form
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific — from luokai0/ai-agent-skills-by-luo-kai
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, — from luokai0/ai-agent-skills-by-luo-kai
Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, — from luokai0/ai-agent-skills-by-luo-kai
Receive and verify OpenAI webhooks. Use when setting up OpenAI webhook handlers for fine-tuning jobs, batch completions, or async events like fine_tuning.job.completed,…
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request — from luokai0/ai-agent-skills-by-luo-kai
Bridge AI coding agents across machines over SSH. Run commands and agent prompts on paired remote machines, and send/receive messages between running agent sessions.
Persistent Action Bus + Orchestrator for OpenClaw + EVEZOS. Supports device commands, chain operations, quarantine and confirmation, durable event storage, idempotent execution,…
Queen-led multi-agent orchestrator for GetFresh Ventures Growth by Design CEO AI Kit. Manages hierarchical agent dispatch, strategic/tactical/adaptive modes, royal directives, and…
OpenClaw + npm vibes-coded-agent-connector: register agents, manifest listings, hosted skill uploads, Solana checkout, receipts, affiliates, proof-of-use.
Todoist task management for OpenClaw. Unified todo API with multi-agent identity, scheduled checks and reminders.
An open-source terminal-native AI coding agent written in Go that supports 75+ LLMs including Claude, GPT, Gemini, and local models.
Full OpenCode delegation workflow — routing rules, agent-to-role mapping, model routing, invocation patterns, and examples for delegating tasks to OpenCode (GitHub Copilot).
Migrate from OpenAI to OpenRouter with minimal code changes. Use when switching to OpenRouter or maintaining dual compatibility.
Guides creation and maintenance of best-practice files for the Opensquad best-practices library. Handles format validation, cross-references, versioning, and catalog consistency.
Give agents structured Airflow, lineage, dbt, and warehouse workflows through installable skills and an Airflow MCP surface instead of loose shell access.
\"Apply current optimization techniques to improve prompt. 應用最新優化技術改善提示。 Use when: improving accuracy, consistency, creativity, speed, or safety of existing prompt.\
Use DSPy to define modular LLM programs, metrics, and evaluation sets so an agent can optimize prompts and pipeline behavior with measurable feedback instead of ad hoc prompt…
Analyse et améliore un prompt existant pour obtenir de meilleurs résultats avec un LLM. À utiliser quand l'utilisateur a un prompt qui ne donne pas les résultats voulus o — from…
Orama is a full-text, vector, and hybrid search engine that runs in the browser, on a server, or at the edge in under 2KB.
Use local Codex/Claude JSONL logs as evidence, then produce a human-written daily diary summary and write it into Obsidian.
Full-stack skill for the ORCA Hand — 17-DOF tendon-driven robotic hand (ETH Zurich). Implements agentic-control-kernel Plant interface with typed schemas, safety shields,…
Execute orchestrate multi-agent systems with handoffs, routing, and workflows across AI providers. Use when building complex AI systems requiring agent collaboration, task…
Master coordinator for Unite-Hub workflows. Routes tasks to specialists, manages multi-agent pipelines, maintains context across runs, handles errors, and generates system…
Operational manual for AI agents using the Ornn skill-lifecycle API via the NyxID CLI (`nyxid proxy request ornn-api …`).
Operational manual for AI agents using the Ornn skill-lifecycle API via direct HTTPS with a NyxID bearer token (`curl -H "Authorization: Bearer $TOKEN" …`).
Pattern 5: Concurrent Event-Driven Multi-Agent Loop. Coordinates multiple Claude sessions as OS threads sharing a common event bus and memory address space.
Erzeugt Tenor-Bausteine, Rubrum und formale Mindestanforderungen fuer Antrag, Beschwerde und Klageschrift nach ZPO, VwGO, SGG, FGO und BVerfGG.
Workflow zur strukturierten Aufnahme, Priorisierung und Ausgabe im Thema Output Beschwerde Antrag Stellungnahme. — from Klotzkette/claude-fuer-deutsches-recht
Use the Agent class for multi-step tool loops, conversation history, and reusable LLM agents. Use when building agents with skills, structured output, or stateful conversations.
Erzeugt Ausgaben im juristischen Schriftsatzstil auf Deutsch: Antrag-Begruendung-Beweismittel-Struktur, Subsumtionsdarstellung im Vier-Schritt, Zitierweise nach BGH-Standard,…
Turn documentation sites, GitHub repos, and PDFs into installable agent skill packages when hand-authoring a reusable skill would be slow or inconsistent.
Skill untuk menghasilkan Instructions lengkap bagi AI Agent yang akan di-deploy di Paperclip.ing, dalam struktur tiga level: Director, Manager, dan Specialist.
Use INSTEAD of superpowers:executing-plans and superpowers:dispatching-parallel-agents. Executes plan tasks via multi-agent parallel dispatch with built-in verification.
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspecti — from…
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspecti — from…
Multi-agent parallel development cycle with requirement analysis, exploration planning, code development, and validation.
Run LiteParse locally to extract PDF text, spatial JSON, OCR-backed output, and page screenshots before sending documents into an agent workflow.
Erstellt eine Tabelle mit zwei Spalten (Klaegerseite und Beklagtenseite) fuer streitige Sachverhaltsangaben Punkt fuer Punkt.
Setzt Patentlizenz-Term-Sheets in deutsch-englische Vertragsklauseln um; erklärt Legal-English-Begriffe im deutschen Rechtskontext und vermeidet unklare Transaktionssprache.
Prüft Patentlizenzverträge: Schutzrechte, Territory, Field of Use, Exklusivität, Unterlizenzen, Royalties, Milestones, Improvements, Inhaberschaft, Gewährleistung, Durchsetzung,…
Patientenrechte Behandlungsvertrag Aufklärung: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen.
Keep skill-listing deltas scoped per agent or thread so each agent gets its own first-turn announcement surface.
Use when creating or editing a persona in .agent-src.uncompressed/personas/ — voice / focus / unique questions / output expectations — even when the user just says 'add a reviewer…
Reusable approval-loop pattern for fanning out lead personalization across parallel Claude Code Task sub-agents.
~/.claude/pev/{task_id}/ 配下にsubagent (主にexecutor) の memory directoryを標準化。並列実行時の情報共有と次セッションへの引き継ぎを実現
pgvector performance optimization: HNSW vs IVFFlat index selection and tuning, ef_search / m / ef_construction parameters, iterative scanning for filtered queries, scalar and…
Screenshot a running Phoenix feature and attach images to a GitHub PR. Builds the frontend, starts Phoenix with env vars, uses agent-browser to capture screenshots, uploads to…
Composition de pipelines de sous-agents où la sortie d'un agent alimente l'entrée du suivant. Se déclenche avec "pipeline agent", "chaîne d'agents", "agent chain", "agent — from…
类案检索报告与办案备忘工作流，用于把案例检索压缩成可讨论、可转发、可复核的备忘文本，包含案例样本、案号核验与链接增强。Use when：律师、争议解决团队或合规调查团队需要快速形成“类案要点 + 可核验线索 + 交付版备忘”的标准产物。NOT for：仅要单条案例原文、仅做案例列表罗列、或不需要对比分析的场景。要求关键信息必须可追溯到当次 MCP…
检索司法案例与裁判文书资料。当前本机只订阅 `case-keyword`（检索司法案例-关键词），不得假定 `case-semantic`、`case-number` 等旧 MCP 可用。Use when：用户明确要找类案、裁判样本、裁判文书线索，或希望围绕一个争议问题先看法院如何处理。NOT…
法条引用核验与纠偏，用于检查草稿、问答、备忘或合同审查记录里已经写出来的法条引用是否准确、一致、可追溯。Use when：用户已经有一段文本，想确认其中法规名称、条号或引用表达是否可靠。NOT for：主题检索法规、案例检索、案号识别、以及未形成引用文本前的纯资料探索。要求只依据当次核验返回给出“命中 / 不命中 /…