В каталоге 182 820 навыков в 14 категориях.
List and filter tickets/issues from configured backend
open な子が全部ブロッカー待ちで止まった親 Issue を、子を他の親へ移して close する。「issue-regroup」「親issueを閉じられるようにして」「子を付け替えて」と指示されたとき。
Internal runtime support for universal skills that validate canonical scoped issue titles. Do not invoke directly.
Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress m...
Enable self-referential iteration to complete complex tasks that require multiple attempts, trial-and-error exploration,...
Iteration 6 of Multiplicity Cascade - Documentation that modifies itself when read
Iteration 7 of Multiplicity Cascade - Self-creating chaos engines
Iteration 8 of Multiplicity Cascade - Collides unrelated domains for emergence
Iteration 5 of Multiplicity Cascade - Spawns meta-patterns from patterns
> Compiler: skill-compiler/1.0.0
Pattern for progressively refining context retrieval to solve the subagent context problem
Execute 4-phase loop for progressive context refinement. Use when complex searches require multiple refinement cycles or...
4-phase context retrieval protocol for subagents — Dispatch, Evaluate, Refine, Loop
Use when preparing for ITIL Foundation (Version 5) from PeopleCert — the value system, the four dimensions, value co-cre...
Inspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes avail...
Inspect and launch distributed ML training
World J Skill
Show all your installed skills. Deprecated alias — use /janitor-report --brief.
Check skills for errors and missing info
Find and remove broken skills
Compare your skill with similar ones on GitHub
Find new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, eva...
Find duplicate skills that do the same thing
Automatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty d...
Check if a new skill overlaps with existing ones before installing. Deprecated alias — use /janitor-discover with a URL...
Full health check of all your skills in one report. Use when the user wants to check for errors, find duplicates, detect...
Search GitHub for new skills to install. Deprecated alias — use /janitor-discover (combines search + pre-install check).
Show how many context window tokens each skill consumes. Deprecated alias — use /janitor-value (which combines tokens wi...
Show which skills you use. Deprecated alias — use /janitor-value (which now combines usage + token cost).
Show whether each skill is earning its context-window cost — combined tokens-used view sorted by waste. Use when the use...
日本語の技術文書・書籍原稿の文章規範。段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、翻訳調の比喩と擬人化の禁止（「運ぶ」「効く」「開か...
Use this skill when accessing JARVIS for computed materials properties, 2D materials data, or NIST materials datasets.
Complete current JAT task with full verification. Verifies work (tests/lint), commits changes, writes memory entry, clos...
Begin working on a JAT task. Registers agent identity, checks Agent Mail, selects a task from Beads, detects conflicts,...
JAX ML - use when working on related tasks
JAX high-performance numerical computing. Use for ML research.
Essential tools for using JAX in machine learning and mathematical analysis, covering core concepts, transformations, ML...
JAX, Flax, Optax, and Equinox patterns for ML training. Covers JIT, vmap, pmap, TPU usage, and functional model design....
High-performance numerical computing and machine learning workflows using JAX. Supports array operations, automatic diff...
Jeff Bezos 视角. Amazon 创始人 / 前 CEO, 1997-2020 致股东信 24 封 + Working Backwards 内部机制的结构化镜片. 核心装备: Day 1 心态, Type 1/Type 2 决策分...
Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in...
Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on...
TypeSafe AI's Jev System One model for typed software decisions: Choice/Score/Noul question primitives, state design, co...
Use Jev to select among available tools, skills or agents, or evaluate outputs against explicit rubrics. Use when the us...
Design how a closed LLM judgment (relevance, novelty, evidence strength) moves to TypeSafe Jev. Use when replacing an LL...
Analisa o projeto atual em busca de decisões semânticas implementadas de forma frágil — cadeia de if/else com string mat...
Web content extraction via Jina AI Reader API. Three modes: read (URL to markdown), search (web search + full content),...
This skill should be used when the user asks to "orchestrate jira", "work on issue", "complete jira ticket", "developmen...
Smart multi-agent task execution with automatic routing. Use when user types 'jjj' or for routine coding tasks (tests, c...
Use when the user explicitly asks to launch and supervise a job. Require an authorized launch, monitoring, recovery, and...
Search and filter AI Agent / LLM internship positions in Shanghai for a 2024-cohort AI undergraduate. Covers company lis...
求职 / 面试辅导(求职教练视角 — 求职定位与职业叙事 / 简历与 ATS 优化 / 求职渠道与内推策略 / 职场社交 / 行为面试与专业面试 / 面试心理与表达 / 谈薪与 offer 决策 / 校招与应届生 / 转行求职 / 特殊群体...
Use when creating journal cover images, generating scientific artwork prompts, or designing graphical abstracts. Creates...
Create session learning logs that persist institutional memory across Claude Code sessions.
Use as the AI build stage of the Butterbase journey. Implements the AI section of 02-plan.md by delegating to the ai ski...
Use as the auth build stage of the Butterbase journey, after journey-schema (and rls if separate). Implements the Auth s...
Use when preparing for the Japan Statistical Society Certificate Grade Pre-1 (統計検定準1級) — probability theory and distribu...
React renderer for json-render that turns JSON specs into React components. Use when working with @json-render/react, bu...
Knowledge pack synthesized from JSP 912 Human Factors Integration in Defence Systems, Part 1 Directive and Part 2 Guidan...
MOVED — jtbd now ships in the humane plugin (glebis/humane-agentic-design), not here. This directory is a redirect; inst...
Check a finished drive's result against what the drive promised, and give a pass or reject verdict with a reason for eve...
Delegate coding tasks to Google Jules AI agent for asynchronous execution. Use when user says: 'have Jules fix', 'delega...
Interact with the Jules CLI to manage asynchronous coding sessions. Use this skill to assign tasks, monitor progress, an...
Gay.jl integration for deterministic color generation. SplitMix64 RNG, GF(3) trits, and SPI-compliant fingerprints in Ju...
Master Julia 1.10+ with modern features, performance optimization, multiple dispatch, and production-ready practices.
- Working on julia pro tasks or workflows
Julia package equivalents for 137 K-Dense-AI scientific skills. Maps Python bioinformatics, chemistry, ML, quantum, and...
Reference system prompt and tool schemas for Junie. Use when imitating, comparing, or analyzing Junie's prompting style;...
孙宇晨(Justin Sun)的思维框架与表达方式。基于21,829条推文（14,418 EN + 7,411 ZH）、 1本自传《这世界既残酷也温柔》、155集音频课《财富自由革命之路》(~18小时)、 40+篇深度采访与调查报道、2篇核...
World K Skill
Protocol names ARE K-lines.
2026-01-06 12:00 [agent=codex-cli] Create/init backlog scaffold, default config, and optionally write agent guide files...
Setting up a new repo still requires manual folder creation and tool wrapper
Kubernetes-native AI agent framework for building, deploying, and managing AI agents on Kubernetes. This skill should be...
Deploy and manage Kagenti platform, operator, agents, and tools on Kubernetes.
End-to-end workflow for fine-tuning LLMs using Kaggle datasets. Use when downloading datasets from Kaggle for model trai...
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competiti...
Search the web using Kagi. Use for web searches with Quick Answer AI summaries.
[Project Management] AI agent orchestration board (Coming Soon)
Use when rewriting, sharpening, or producing a prompt for Claude or another current frontier model. Sets standing rules...
Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it...
Subsumtion einer Vereinbarung, eines Beschlusses oder einer abgestimmten Verhaltensweise unter das Kartellverbot § 1 GWB...
Show available Kata skills, displaying the usage guide, explaining skill reference, or when the user asks for help with...
Create a context handoff file, pausing work mid-phase, stopping work temporarily, or creating a checkpoint for session r...
Resume work from a previous session, restoring context after a break, continuing work after /clear, or picking up where...
Switch model profile for kata agents (quality/balanced/budget). Triggers include "set profile", "set profile".
Mietsicherheit im Wohnraummietrecht – Höchstbetrag von drei Nettokaltmieten und Ratenzahlungsrecht § 551 Abs. 1, Abs. 2...
Use when querying and maintaining the knowledge base for project context, decisions, and architecture documentation on s...
Use when knowledge base and memory system for AI agents. Covers company KB, persistent memory, session recall, and brain...
精选 K-Dense Scientific Agent Skills 的机器学习与人工智能工具包。用于 scikit-learn、PyTorch Lightning、Transformers、SHAP、time series ML、Time...
Search the web and fetch page contents with Keenable AI — web search, page extraction, point-in-time queries, prompt-dri...
Reflective Memory
Use when after metabolite KEGG identifiers and hierarchy metadata have been assigned (via assign_hierarchy with 'KEGG' i...
Use this skill whenever the user wants to discuss, explore, or ask questions about a topic using the local knowledge bas...
Digital-human implementation and demo skill for choosing, prototyping, and QA-ing low-cost 2D photoreal digital humans a...
Kelly Education Intel: App-in-Skill daily industry intelligence cockpit for education, training, tutoring, and admission...
Keras high-level neural network API. Use for deep learning.
This prompt instructs an image generation/editing system to produce a high-resolution vertical portrait that preserves t...
Use when evaluating LLM-generated structured output against expected results using keyword matching and F1 metrics.
Extracts up to 50 highly relevant SEO keywords from text. Use when user wants to generate or extract keywords for given...