В каталоге 182 820 навыков в 14 категориях.
Turn one recurring pain point into one measurable, bounded workflow improvement.
Generate and update AGENTS.md (CLAUDE.md) for projects using a single template with dynamic per-type tooling injection....
หา AI/LLM improvements ใน scope — prompts, token cost, guardrails, evals — แก้หลัง user confirm
Analyze conversations to identify improvements for prompts, instructions, skills, or workflows. Use when something went...
Analyzes conversation history to improve CLAUDE.md files. Use when you notice patterns in how Claude misunderstands requ...
Prompt engineering architect that transforms raw prompts into optimized, production-ready prompts. PROACTIVELY activate...
Single-pass rewrite of an LLM prompt — paste a prompt or point at a file (system prompt, prompt template, agent definiti...
Use when the user asks to improve, compare, audit, or identify gaps in an existing skill.
Virtual gene knockout simulation using foundation models to predict transcriptional changes
Agent Mail inbox monitoring. Check pending messages, HELP_REQUESTs, and recent completions. Triggers: "inbox", "check ma...
Internal ACE turn step — The email half of a turn: triage ace@ unread mail one thread at a time.
Full character autonomy across all layers of existence
Incident response playbook design for mid-2026 — NIST 800-61r3, ISO 27035, ATT&CK-driven detection, PICERL phases, AI-cl...
Run a structured blameless post-mortem after an incident
Incognito mode patterns for ephemeral conversations with blank slate option. Controls tool access (write tools always di...
options income, covered call strategy, cash secured puts, credit spreads, iron condor, wheel strategy, premium selling,...
Commit code after each logical unit of work is complete Use when configuring AI agent workflows and patterns. Agent Beha...
Create searchable knowledge base from existing documentation and code for fast context lookup in brownfield projects. In...
Index a folder's contents into the context system for fast retrieval
Save conversation Q&A pairs to persistent memory for later retrieval
Index- und Staffelmiete im Wohnraummietrecht – Gestaltung und Prüfung der Staffelmietvereinbarung § 557a BGB (Schriftfor...
Review an AI system for prompt injection delivered through retrieved documents, web pages, emails, tickets, code reposit...
AI model inference and serving. Activate when: (1) Setting up LocalAI or vLLM, (2) Configuring model serving, (3) Workin...
本地全链路「小说/剧本 → 漫剧/短视频」创作 Agent 解决方案。三种用法：①启动本项目一键跑；②不启动本项目，Agent 按本规范 + skills/ 技能库复刻全流程（剧本→人物圣经/风格→资产生图→分镜→逐镜视频→合并成片）；③接...
专为InfiniteTalk项目设计的小省导购员数字人带货提示词生成技能，基于四大智能体协同（提示词生成师、质量管控师、知识库运维师、跨环节适配师），生成适配Image-to-Video模式的结构化提示词（角色固定特征+动作时序+场景环境+...
Manage AICP's caching surfaces — LocalAI prompt cache (`prompt_cache_path`/`prompt_cache_all` per model YAML), KV cache...
Adds files, folders, zips or web pages to the vault as untouched raw copies, writes a source note for each, and updates...
Recognize and occupy with dignity the relational spaces built by previous instances and maintained by specific users acr...
Analyze project structure and update AGENTS.md with detected tech stack, commands, and configurations.
Register an agent on kradleverse
Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-di...
Analyze a codebase and create or improve an AGENTS.md file for future agent instances. Use when onboarding to a reposito...
初始化和增量更新 AI 记忆文件（CLAUDE.md、AGENTS.md、GEMINI.md）。通过交互式选择和差异对比，智能补全记忆项内容。触发条件：当用户提及初始化记忆文件、更新 CLAUDE.md、同步 AI 记忆、init-ai-m...
Generate $HOME/.claude/CLAUDE.md with AI-driven environment detection and advanced configuration options
Generates hierarchical context files (CLAUDE.md) throughout a project directory tree, providing AI agents with directory...
Walk the operator through creating the first NanoClaw agent for a DM channel — resolve the operator's channel identity,...
Initialize or update CLAUDE.md coding standards for any project by auto-detecting tech stack and assembling rules from t...
Initialize Contextium session state and verify environment
Initialize Claude skills in the current project and verify setup. Use when user says '/init-skills', 'setup skills', 'in...
Load relevant .agents context.
Ink terminal renderer for json-render that turns JSON specs into interactive terminal UIs. Use when working with @json-r...
Use when context window is filling up too fast or input token cost is too high. Audits overhead sources.
Request clarification when input is ambiguous. Use when user request has missing parameters, conflicting interpretations...
Create Instagram content for AI/tech educational posts. Use when the user wants to create Instagram content including ca...
当需要把本仓库 pipelines/skills 下的所有 skills 安装到系统级（默认同时安装到 Codex: ~/.codex/skills 和 Claude Code: ~/.claude/skills），以便在任意项目/对话中可...
Install skills using local repos (../skills + ../hooks) first. Do not require npm publish.
This skill should be used when the user asks to "install a skill", "add a skill to the project", "unpack a skill", or "i...
Talk to Instantly Ai Founders about their expertise. Instantly Ai Founders provides authentic advice using their mental...
Instar's identity system gives agents a continuous self that survives context compaction, session restarts, and autonomo...
Instar's job scheduler lets you define tasks that run automatically on a cron schedule. Each job spawns a real Claude Co...
Instar lets you spawn, monitor, and communicate with Claude Code sessions running as background processes in tmux. Each...
Export instincts for team sharing
Export learned instincts for cross-project sharing
Import instincts from teammate
Import instincts from other projects or exports
View learned instinct patterns with confidence scores
Search memex for user feedback patterns (frustration, corrections, praise, successful outcomes) to identify recurring mi...
Use when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability...
Structured outputs with Instructor. Extract typed data from LLMs using Pydantic models and validation. Use for data extr...
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse compl...
Use this when adding tracing/observability to an LLM or AI-agent application - capturing prompts, tool calls, token usag...
保险经纪人 / 保险代理人 (中国保险经纪人/代理人 (从业者视角)) Master OS — automated mastery of 中国保险经纪人/代理人 (从业者视角): top builders' mental models, t...
Generate a phased delivery orchestration plan for creative-direction-driven work, mapping which skills run when, what lo...
This prompt instructs an AI to read the full user–assistant conversation and produce a structured “Cold Start Summary” t...
Automatic agent selection and intelligent task routing.
Turn rough ideas into clear work orders before planning or building. Use when request is vague like "add a button", "mak...
太子意图分拣规则，定义闲聊/旨意/不确定分类与 fast_track 快车道判定标准
Route ambiguous Phoenix/LiveView/Ecto work requests to the correct /phx: workflow. Use when intent is unclear, mixed (bu...
Clarify user intent before executing tasks. Use when requests are vague, ambiguous, or could be interpreted multiple way...
Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a new project, adding context in...
Intent classification and mapping for natural language commands. Uses unsloth/transformers for ML-based intent detection...
ユーザーとの効果的な対話パターン、質問生成、曖昧さ解消、合意形成、ユーザー負担軽減のガイドラインを定義する。ユーザーに質問する際、要件を確認する際、フィードバックを収集する際、またはユーザーが対話改善、質問方法、確認プロセス、Progres...
Turns docs, posts, and codebases into interactive walkthroughs — narrated animation, quizzes, and widgets. Use when the...
| Skill | Path | Description |
Automatically routes tasks to external AI CLIs (Codex or Gemini) when more efficient. No manual commands needed - routin...
Problem-solving strategies for interpolation in numerical methods
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scr...
针对 Modular RAG MCP Server 项目的模拟技术面试 Agent。读取用户简历（可选），围绕三个方向进行最多 3 轮深度追问，结束后生成并持久化面试报告（含参考答案、包装识别点评、评分）。Use when user say...
Synthesize a batch of customer interviews into evidence-for + evidence-against the hypothesis, with pattern surfacing an...
Question the user relentlessly about a plan, decision, or an idea to uncover hidden assumptions, risks, and edge cases....
Analyze and explain Claude's reasoning, decision patterns, and problem-solving approaches. Use when user requests "expla...
Codified expertise for demand forecasting, safety stock optimisation, replenishment planning, and promotional lift estim...
Mandatory protocol that prevents AI agents from fabricating information. Forces best practice search before every action...
Capital Flow Recovery & Liquidity Optimization Guard. Orchestrates multi-stage collections choreography and liquidity en...
Delegate complex tasks to OpenCode subagent, use when >=2 file modifications or batch operations
Invokes Google Gemini models for structured outputs, multi-modal tasks, and Google-specific features. Use when users req...
iOS 应用上架大师 (审核 + ASO + 合规 + 国内/海外多区 + 付费策略) (iOS App Store launch — submission, review, ASO, compliance, post-launch mon...
个人 IP 图解创作器。用你的 IP 形象，生成专属内容图解。用于把用户授权提供的照片、主页截图、简介、账号资料或角色档案转成稳定的极简手绘图解角色，并继续生成长文配图、图文号知识卡、手机海报、方法拆解图、分镜故事图、IP 演讲 PPT、直...
Global Intellectual Property & Trademark Protection Scout. Patrols international application marketplaces and digital st...
Binder design ranking using ipSAE (interprotein Score from Aligned Errors). Use this skill when: (1) Ranking binder desi...
Use when inferring maximum-likelihood phylogenetic trees, selecting substitution models, running bootstrap support analy...
Use when preparing for ISACA Advanced in AI Security Management (AAISM) — eligibility through an existing security manag...
Core Plain Language standard (ISO 24495-1:2023). Governs all user-facing responses to ensure clear, structured, findable...
<!-- What should this skill be called? -->
Audit and triage general issue backlogs with read-only defaults, interactive cleanup decisions, and guidance steering; u...
boy-scout ラベルの open Issue を「やる価値があるか」「対応方針がポリシーに合っているか」で判定し、タイトル・本文・ラベルを直す。1つの PR に収まらず割れる Issue は sub-issue に割る。初回の検査では...
broken-window ラベルの open Issue を「やる価値があるか」「対応方針がポリシーに合っているか」で判定し、タイトル・本文・ラベルを直す。1つの PR に収まらず割れる Issue は sub-issue に割り、AI...
issue:needs-human-decision が付いた boy-scout Issue の論点を1件ずつ人間に示し、決まった方針を本文へ書き戻して ai-fixable に変換する。/sweep の前処理として人間が打つ。「issu...
needs-human-decision が付いた Issue の論点を1件ずつ人間に示し、決まった方針を本文へ書き戻して ai-fixable か ready-for-human に変換する。broken-window の有無を問わない。...
Plan-and-Execute pipeline with Wave Pipeline pattern. Orchestrator coordinates planner (Deep Interaction) and executors...