Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
tripartite-decompositions
GF(3)-balanced structured decompositions for parallel computation. Decomposes problems into MINUS/ERGODIC/PLUS components with sheaf-theoretic gluing. Use for FPT algorithms, skill allocation, or any 3-way parallel workload.
majiayu000/claude-skill-registry 163
-
livekit-omnimodal
LiveKit omni-modal continuous coaching with stick-breaking color selection,
majiayu000/claude-skill-registry 163
-
bio-crispr-screens-library-design
CRISPR library design for genetic screens. Covers sgRNA selection, library composition, control design, and oligo ordering. Use when designing custom sgRNA libraries for knockout, activation, or interference screens.
majiayu000/claude-skill-registry 163
-
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
majiayu000/claude-skill-registry 163
-
remix-icon
Guide for implementing RemixIcon - an open-source neutral-style icon library with 3,100+ icons in outlined and filled styles. Use when adding icons to applications, building UI components, or designing interfaces. Supports webfonts, SVG, React, Vue, and direct integration.
majiayu000/claude-skill-registry 163
-
docs-architect
Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks. Use PROACTIVELY for system documentation, architecture guides, or technical deep-dives.
majiayu000/claude-skill-registry 163
-
mcp-scripts
MCP Script Rules
majiayu000/claude-skill-registry 163
-
security-health-inline
Inline orchestration workflow for security vulnerability detection and remediation. Provides step-by-step phases for security-scanner detection, priority-based fixing with vulnerability-fixer, and verification cycles.
majiayu000/claude-skill-registry 163
-
instantly-install-auth
Install and configure Instantly SDK/CLI authentication.
Use when setting up a new Instantly integration, configuring API keys,
or initializing Instantly in your project.
Trigger with phrases like "install instantly", "setup instantly",
"instantly auth", "configure instantly API key".
majiayu000/claude-skill-registry 163
-
Builtin Developer
Guides development of AILANG builtin functions. Use when user wants to add a builtin function, register new builtins, or understand the builtin system. Reduces development time from 7.5h to 2.5h (-67%).
majiayu000/claude-skill-registry 163
-
android-playstore-pipeline
Complete end-to-end Android Play Store deployment pipeline setup in one command
majiayu000/claude-skill-registry 163
-
bun-init
Initialize a new Bun project with TypeScript and optimal configuration. Use when starting a new Bun project or converting a directory to a Bun project.
majiayu000/claude-skill-registry 163
-
production-dockerfile
Generate production-ready Dockerfiles with multi-stage builds, security best practices, and optimization. Use when containerizing Python applications for production deployment.
majiayu000/claude-skill-registry 163
-
ideation
アイデア・企画フェーズを実行。problem-definition → competitor-analysis → slc-ideation を順次実行し、PRODUCT_SPEC.md を生成。「企画フェーズを開始」「アイデアをまとめたい」「/ideation」などで起動。
majiayu000/claude-skill-registry 163
-
wireframe-generator
YAML定義からChakra UIベースのワイヤーフレーム画像を自動生成する
majiayu000/claude-skill-registry 163
-
malware-triage
Systematic malware triage and initial assessment workflow for professional malware analysis. Use when the user needs to perform initial malware assessment, classify samples, determine analysis priority, identify quick indicators, or decide on next analysis steps. Also use for rapid malware identification and threat classification.
majiayu000/claude-skill-registry 163
-
push-pr
Push commits and create or update pull requests with smart branch management. Use when user says "push this", "push my changes", "create a PR", "open a pull request", "make a PR", "submit for review", or mentions pushing code or creating PRs. Also triggers on "send this up", "open PR", "pr please".
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-thread-delete
Delete a thread. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
umbraco-repository-pattern
Understand and use repositories in Umbraco backoffice (foundational concept)
majiayu000/claude-skill-registry 163
-
when-creating-presentations-use-pptx-generation-dnyoussef-context-cascade
majiayu000/claude-skill-registry 163
-
content-filter
Filter and classify AI research content for relevance, topic, and author category. Use for bulk triage of raw content before detailed claim extraction.
majiayu000/claude-skill-registry 163
-
production-ops
Use when coordinating shoots, vendors, budgets, and compliance for video projects.
majiayu000/claude-skill-registry 163
-
reflection
Self-improving meta-skill that learns from user corrections and updates the TARGET PROJECT's skill files. Only runs when user explicitly says "reflect". Commits all skill updates to Git.
majiayu000/claude-skill-registry 163
-
libeval
libeval - RAG evaluation system. Evaluator orchestrates quality assessment using LLM-as-judge patterns. CriteriaEvaluator scores responses against rubrics. RecallEvaluator measures retrieval performance. TraceEvaluator analyzes execution traces. EvalStore persists results. Use for automated quality testing, RAG pipeline evaluation, and agent performance testing
majiayu000/claude-skill-registry 163