В каталоге 182 820 навыков в 14 категориях.
Search and navigate The Fold's skill lattice using meta-tooling. Use for finding functions, exploring dependencies, type...
Multi-agent distributed context preservation protocol using cryptographic sharding, gossip propagation, and Byzantine fa...
Start a Space-Agents session. Displays welcome screen with project status.
Spawn 5 parallel agents applying quality principles across planning, building, and validating code. Use when designing f...
Progressive memory recall with 4 scope layers AND 3 depth layers. Scope: identity > project > room > deep. Depth: IDs on...
Sales prospecting and lead generation
Find hand-raisers in a comment-keyword campaign. Use to qualify leads, deduplicate, and prepare CRM handoff. Read README...
Autonomous technical lead. Takes commander's intent and drives a project to completion through an OODA loop over impleme...
Use to keep context lean. Read only what you need. Compress aggressively.
Retrieval-augmented Lean4 proof generation. Queries 94k+ exemplars from DeepSeek-Prover V1+V2, uses hybrid search (BM25...
Reference system prompt and tool schemas for Leap.new. Use when imitating, comparing, or analyzing Leap.new's prompting...
Extract and persist insights from the current conversation to the knowledge base
Extract durable memory from conversations or wisdom from learning content with strict durability test
Analyze conversation for learnings and save to docs folder
Save a learning to project memory. Invoke automatically (without user asking) whenever a task required more than one fix...
Extract reusable knowledge from the current session into a persistent skill. Use when you discover something non-obvious...
Guided, hands-on course teaching architects how to use Claude Code — six short modules, each built around an exercise on...
Distill learnings from completed features and propose amendments to constitution.md or prompt.md. Use after feature comp...
Teach Claude a new pattern, preference, or convention explicitly. Use when you want to save a correction, preference, or...
Extract reusable patterns from the current session and save them as skills. Use after solving a non-trivial problem to c...
Persistent memory system for storing and recalling learnings across sessions. AUTO-INVOKE THIS SKILL when you: - Fix a...
[Utilities] Teach Claude lessons that persist across sessions. Triggers on 'remember this', 'always do', 'never do', 'le...
When the user asks to learn, remember, or save a preference — or after a conversation where the user gave corrections or...
[learn] topic|url|repo→discover→fetch→synthesize→SKILL.md+soul
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task...
This skill should be used when the user asks to "save learnings", "remember this for next time", "add this to CLAUDE.md"...
Runs the learning cycle on all LearningAgent sessions with pending transcripts. Identifies issues, investigates root cau...
Extract lessons from conversation and persist to project configuration
Extract learnings from current conversation and add to project's CLAUDE.md.
Use when the user wants to actually internalize an installed best practice — not just understand or apply it once, but b...
Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when th...
Capture lessons after fixing a bug or receiving a correction — ecto, liveview, oban, iron law mistakes. Use when the use...
用于深度理解研究型代码仓库的方法论 skill。当用户想要学习一个新的 ML/AI repo、理解其实现与论文的对应关系、或为后续修改做准备时使用。结合对话式学习风格，逐组件拆解模型实现。
When a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a...
Use when the user wants to get oriented on grimoire itself — what it is, why it exists, its core concepts, and how to ac...
Record mistakes. Check before similar builds. Avoid repeating silently.
Disable continuous learning mode
Enable continuous learning mode for automatic insight extraction
Detect recurring patterns in user's project. Apply automatically next time.
Learn user's preferences over time. Code style, naming, structure. Save to global prefs.
Scan project code to detect patterns, dependencies, and conventions. Propose domain rules based on what the code actuall...
Clear the knowledge base and start fresh
Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises...
General-purpose timeout estimation skill. Trains dual models (duration regression + risk classification) from corpus dat...
Train RVC voice models from artist names. Full pipeline: YouTube search, download, stem separation, preprocessing, train...
Log a learning, discovery, or decision to the vault with full context from the current conversation.
Index directory for automatically learned skills from execution feedback
Manage learned patterns - list, view, archive, boost or penalize confidence. Use when you want to see what patterns Clau...
Extract a learned skill from the current conversation
세션에서 반복되는 작업 패턴을 감지하고 재사용 가능한 스킬이나 룰로 추출합니다. evolve 스킬과 연동하여 .claude 설정을 자동 진화시킵니다. Use when you notice repeated pattern...
Create a compact teaching brief with learning goal, approximate level, relevant prior knowledge, constraints, and prefer...
Provides on-demand access to accumulated learnings stored in ~/.claude-mind/memory/learnings.md.
Extracts reusable patterns from sessions. Use at session end to capture debugging insights and project-specific knowledg...
Dispatch entry point for the LearningAgents plugin. Routes to sub-commands for creating agents, running learning cycles,...
ai-integration for learning technology evaluation and implementation.
Recognize and capture reusable patterns, workflows, and domain knowledge from work sessions into new skills. Use when co...
Capture new learnings discovered during code exploration or user interaction that were not present in context, memories,...
学习笔记自动化：视频/播客转录 → 知识点提取 → 闪卡生成 → 知识图谱更新。触发词：学习笔记、闪卡、Anki、知识提取、视频学习
Help the user learn from real work through adaptive dialogue and evidence. Use when they ask to practice or check their...
Manufacturing Intelligence — Leela AI develops MOOLLM for practical use and industrial exploration
Route disclosure-controlled coaching for LeetCode-style and coding-interview attempts. Use for natural-language coaching...
Governed durable conversation capture and retrieval for LeeWay agents. When a runtime exposes an authorized LeeWay Tool...
ΦAIN v2.0: Φ-Aetheric Information Nexus. Master cognitive architecture. Auto-boots trinity + phase-boundary-detector + f...
Auto-activates structured briefing sessions for complex legal queries -- detects when multi-agent coordination benefits...
Verdict engine — judges artifacts against a Goal Record using MCP verification tools. Returns structured pass/fail verdi...
将法律文本（法律条文或法律案例）转换为规范的 Markdown 格式，删除推广冗余信息。本技能应在用户需要处理法律条文（如民法典、刑法等）、整理法律案例（如最高法典型案例、裁判文书等）、或从粘贴文本中格式化法律文档时使用。注意：本技能只负责...
Analyze failed or stuck proofs and propose auxiliary lemmas to help complete the proof in Isabelle/HOL or Coq. Use when...
Add a learned pattern (lesson) that Ralph will remember for future stories.
Contract surface for Lev's 4-slot memory model (working, episodic, semantic, procedural) with pluggable providers.
Leonid Levin''s algorithmic complexity meets playful mutual ingression. Use for: BB(n) prediction markets, Kolmogorov co...
Playful mutual ingression meets Leonid Levin's algorithmic bounds. Use for: playful exploration with theoretical guarant...
Coordinates 9 specialized audit workers (security, build, architecture, code quality, dependencies, dead code, observabi...
Cohesive Linear HoTT patterns for interaction entropy with diagram generation. Implements Schreiber's cohesive modalitie...
Human interface agent that translates ecosystem activity into clear, actionable communication. Creates status briefings,...
Use Lians when a user wants Cursor to remember durable preferences, decisions, or prior work across chats, or wants to i...
libagent - Agent orchestration library for conversational AI. AgentMind class coordinates LLM completions, memory manage...
李碧华小说创作思维——奇情叙事、冷艳诡谲、历史重构、香港都市传奇。 触发词：「李碧华视角」「像李碧华那样写」「奇情」「冷艳」「霸王别姬」。 擅长：爱情与恐怖交织、历史重构、女性执念、宿命轮回、影视化叙事。
libchat - Chat web components library. ChatClient provides composed client for authentication, API communication, and st...
libeval - RAG evaluation system. Evaluator orchestrates quality assessment using LLM-as-judge patterns. CriteriaEvaluato...
libllm - LLM API client for OpenAI-compatible endpoints. LlmApi class handles chat completions and embeddings via HTTP....
libmemory - Memory management for LLM context windows. WindowBuilder constructs token-limited context from conversation...
libprompt - Prompt template management with Mustache. PromptLoader loads .prompt.md files from directories and renders t...
Use the Libra ergonomic machine-learning client for query-driven tabular, NLP, vision, recommendation, dashboard, and an...
Web research agent for documentation, web search, and code search. Use when: querying docs, searching latest tech info,...
Research and documentation expert - finds answers and examples
Specialized agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and find...
HUAOMP Library — acquire, catalog, query, and curate knowledge across 20 departments. Receipt-backed acquisitions, SHA-2...
Autonomous curator for Source Library - discover, evaluate, and import historical texts in alchemy, Hermetica, Kabbalah,...
CRISPR library design for genetic screens. Covers sgRNA selection, library composition, control design, and oligo orderi...
libutil - General utilities. countTokens and estimateTokens for GPT-style token counting. generateHash creates SHA256 ha...
libvector - Vector similarity search. VectorIndex stores embeddings with metadata and performs cosine similarity search....
Behavioral rules and lifecycle event handlers for the core-tools package. Defines automated behaviors that trigger at sp...
Ligand-aware protein sequence design using LigandMPNN. Use this skill when: (1) Designing sequences around small molecul...
Light 科研主线第 3 步·提 idea:从模糊方向/数据/文献**结构化发散**(激发算子系统生成,不是泛泛头脑风暴) → 产**值得做且做得成的分层候选 idea**(moonshot 冲刺/solid 稳妥/safe 保底),每个...
将科研方法图、机制图、流程图及模型架构参考重建为可编辑 Adobe Illustrator 矢量图，处理贝塞尔轮廓、复合路径、渐变、分组和文字，并在真实 Illustrator 保存重开及导出检查；适用于 light-diagram-pro...
科研伦理、学术规范与风险审查。在所有科研任务中默认检查学术不端、数据造假、图片重复使用、引用不规范、隐私泄露、版权、结论夸大、过度包装、论文代写、专利权属、软著材料不真实等风险（常驻，所有任务后台生效）。对论文、项目、软著、专利与比赛材料做...
李继刚（Prompt布道师/Prompt之神）的AI提示词创作思维——Lisp压缩美学+哲学底色+结构化写作+极简主义。 触发词：「李继刚视角」「像李继刚那样写」「Prompt之神」「汉语新解」「压缩美学」「ljg-skills」「Lisp...
LIME-based local explanation skill for individual predictions across tabular, text, and image data.
Use when recalling conversations from Limitless Pendant, finding what was discussed in meetings, searching lifelogs, or...
Core Lindy workflow for creating and configuring AI agents. Use when building new agents, defining agent behaviors, or s...