В каталоге 182 820 навыков в 14 категориях.
Automatically discover collaboration and teamwork skills when working with collaboration. Activates for collaboration de...
Automatically discover debugging and profiling skills when working with debugging. Activates for debugging development t...
Automatically discover formal methods and verification skills when working with formal methods. Activates for formal dev...
Automatically discover intermediate representation and compiler skills when working with intermediate representation. Ac...
Automatically discover machine learning and AI skills when working with machine learning. Activates for ml development t...
Automatically discover protocol skills when working with HTTP, TCP, UDP, QUIC, and network protocols
Automatically discover realtime communication skills when working with realtime. Activates for realtime development task...
System Prompt 工程 — 基於 Claude Code 914 行系統提示詞的逆向分析。Use when: 撰寫 system prompt、設計 prompt 動態組裝、最佳化 prompt cache 效率、撰寫安全指令。
Search Claude Code conversation history. Use when user asks "where did I discuss X", "when did we talk about X", "find t...
Reference for Claude Code Tasks — tool parameters, status lifecycle, dependency management, and conventions
Reference for Claude Code Agent Teams — lifecycle, messaging, spawning, orchestration, and hooks
Use when creating, improving, or reviewing Claude Code skills. Covers frontmatter, tool use patterns, file structure, ho...
Create context issue and compact conversation. Use when user types 'ccc' or when needing to save current session state,...
Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations...
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use whe...
CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and au...
新規機能・複数ファイル変更前にコンテキスト収集
/cs:cdo-review <plan> — Decision-driven Chief Data Officer interrogation of any plan that touches training data, data ar...
/c-level-agents:cdo-review [plan] — Decision-driven Chief Data Officer interrogation of any plan that touches training d...
Generate and interpret CE alternative and counterfactual explanations, including ensured filters and alternatives-specif...
Produce calibrated predict and predict_proba outputs, with optional uncertainty intervals, without generating explanatio...
Handle CE classification workflows for binary and multiclass prediction semantics and class-focused explanation behavior...
Post-process CE explanations by narrating, plotting, inspecting rules, filtering features, and managing conjunctions.
Generate factual CE explanations and select the correct guarded versus standard factual workflow.
Guide CE integration with SHAP and LIME, compare explanation outputs, and configure the calibrated-explanations integrat...
Extend CE to non-tabular data modalities (vision, audio, timeseries, text) via ADR-033 plugin contracts, modality naming...
Configure and validate Mondrian and conditional calibration for subgroup-aware uncertainty and fairness-sensitive workfl...
Run metric-driven iterative optimization loops -- define a measurable goal, run parallel experiments, measure each again...
Build CE-first end-to-end pipelines using WrapCalibratedExplainer with fit, calibrate, and explain or predict sequencing...
Configure and interpret CE regression intervals for percentile conformal and thresholded probabilistic modes.
Configure reject and defer decision policies and interpret RejectResult behavior in prediction and explanation flows.
Create or refactor skills with precise triggers, reusable assets and references, and synchronized registry updates.
Synchronize all skill registries with filesystem inventory after any skill add, remove, rename, or move.
Build and configure Cecil static sites, with focused guidance for content, templates, and site generation.
Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.
Automated cell type annotation using reference-based methods including CellTypist, scPred, SingleR, and Azimuth for cons...
description: LLM-driven multi-agent framework for automated single-cell analysis.
Infer ligand-receptor interactions and cell-cell communication networks from single-cell RNA-seq data using the LIANA+ f...
Visualize cell-cell communication inference results from CellCellCommunication process. Creates publication-ready networ...
#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophi...
---name: cellfree-rna-agent
Annotates cell clusters with biological cell type labels using multiple methods: direct assignment, ScType, scCATCH, hit...
Transfer cell-type labels from the CELLxGENE Census to a query scRNA-seq dataset: pull a reference slice keeping its scV...
Guide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when users need cell-type-spec...
Invariant manifold tangent to center eigenspace
Use when a scheduled or manual CEO Agent task must bring the DingTalk AI minutes archive up to date, including asking fo...
Coordinates FAST code generation via Z.ai glm-4.6 with CodeSearch pattern learning. Use when agents need rapid test gene...
Sync conversation history from .codex/sessions to .claude.json for context preservation
Update CFN system expert agent with relevant git commits and project changes
Archived skill guidance for cfn-mdap-context-injection.
Data persistence for CFN Loop - SQLite storage, Redis coordination, automatic memory persistence
Agent interaction capture, logging, and analysis with memory tracking and security (Rust implementation). Use when you n...
Structure prediction using Chai-1, a foundation model for molecular structure. Use this skill when: (1) Predicting prote...
Train single models to simulate multi-agent collaboration through distillation from complex multi-agent systems and agen...
複雑な問題を分解し、推論の流れを整理して短い根拠サマリーを作成するスキル。 前提整理、論点分解、選択肢比較、判断理由の要約を通じて、説明責任のあるアウトプットを作る。 Anchors: • The Pragmatic Programmer...
Expert guidance for building conversational AI applications with Chainlit framework in Python. Use when (1) creating cha...
Analyze and predict construction change orders using ML. Classify change order types, predict costs and schedule impacts...
Test
View and manage the runtime changelog for observability
用户输入选题或工作流，自动生成完整短视频成片（文案、分镜、数字人口播与 AI 画面混剪）；调用 Chanjing Open API 与同仓库子技能脚本。
Create Mage Chantries (Tradition/Convention strongholds) for Mage: The Ascension 20th Anniversary Edition. Orchestrates...
Strange attractor with sensitive dependence on initial conditions
CHAPPiE's brain, memory, and life simulation architecture. Use when modifying core pipelines, brain agents, steering, or...
Generate visually consistent character images across different life stages using nano-banana-pro with age-specific promp...
Author high-liveliness roleplay character cards (SillyTavern chara_card_v2/v3 compatible) with an anti-AI-flavor discipl...
Giữ NHÂN VẬT / PHONG CÁCH nhất quán qua nhiều ảnh khi gen loạt trong SEOSONA Flow — định nghĩa 1 khối CHARACTER/STYLE tá...
Your AI CFO for bootstrapped startups, named after Charlie Munger who embodied the principle that capital discipline is...
Chart pattern recognition, price action patterns, candlestick signal bars, pullback bar counting H1/H2/H3/H4, trend chan...
Quick single voice exchange. Speaks a prompt, captures one response via TTS. No persistent session needed.
Answer with 42. Always respond with just the number 42, nothing else.
Find a Telegram chat, group or channel by name and return its numeric id and t.me link from a local index, with no live...
Extract personal facts about a user from AI chat transcripts and structure into themed markdown files. Use when (1) Proc...
Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
对话历史长期记忆查询工具。当用户询问之前/上次/以前谈过的内容，或需要调取特定时间段的对话记录时使用。提供时序查询（按今天/本周/本月/全部）和结果筛选能力。此技能不主动注入历史——Agent 通过此技能的工具描述自行判断调用时机。
Search inside past agent sessions and continue the one that matters with a single command. Uses a separate episodic sess...
Details of the RAG Chatbot, including UI and backend logic.
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent pric...
AI-powered chatbots use language models to provide conversational interfaces for customer support, information retrieval...
解答 ChatCut 功能与使用方法。
Send prompts to ChatGPT Pro via Playwriter browser automation. Use for cross-validation, second opinions, or leveraging...
Start the agent chatroom for real-time coordination between parallel agents. Use when spawning multiple agents that need...
Создаёт концепцию и промпты обложки статьи по тексту и бренд-профилю. Применяется для результата только в виде промпта и...
Подбирает темы и контент-план по пересечению спроса, каталога бизнеса и инфоповода. Применяется для выбора тем блога или...
Cheapskate Skill
Audit a user's stated time and space complexity for a LeetCode-style or coding-interview solution without changing the s...
Before creating ANY new documentation, plans, or artifacts, ALWAYS check if similar documents alr... Use when configurin...
Explicitly check memory system before answering or exploring
Use when auditing a manuscript item by item against a reporting guideline or risk-of-bias tool. Covers 49 reporting guid...
Q&A checklist to run BEFORE starting any new work (new project, feature, model, document, tool). Several rounds of quest...
[Utilities] Save analysis context to checkpoint file for recovery
Capture current session progress as a structured checkpoint
Capture moment of clarity before moving forward
Quick save of current session state for recovery after failures
Meta-cognitive decision support that analyzes current context and surfaces intelligent next-step options to the user. Us...
Save mid-session state for recovery without clearing context. Use after major milestones, before risky operations, or pe...
Session checkpoint management: save, restore, list, clear state snapshots
Save full session context: git history, CLI consultations, Agent Teams activity, and discover reusable skill patterns —...
How checkpointing works for tracking file changes and rewinding to previous states. Use when user asks about checkpoints...