Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
cts-triage
Run CTS test suites and investigate failures
majiayu000/claude-skill-registry 163
-
tutorial-engineer
Creates step-by-step tutorials and educational content from code. Transforms complex concepts into progressive learning experiences with hands-on examples. Use PROACTIVELY for onboarding guides, feature tutorials, or concept explanations.
majiayu000/claude-skill-registry 163
-
data-validator
Validate data against schemas, business rules, and data quality standards.
majiayu000/claude-skill-registry 163
-
github-cli
Use this skill when the user asks to work with GitHub from the command line using gh CLI. This includes managing repositories, issues, pull requests, releases, authentication, codespaces, actions, and any other GitHub operations. Use this skill for phrases like "create a PR", "manage issues", "clone a repo", "check gh status", or any GitHub CLI workflow.
majiayu000/claude-skill-registry 163
-
dag-hallucination-detector
Detects fabricated content, false citations, and unverifiable claims in agent outputs. Uses source verification and consistency checking. Activate on 'detect hallucination', 'fact check', 'verify claims', 'check accuracy', 'find fabrications'. NOT for validation (use dag-output-validator) or confidence scoring (use dag-confidence-scorer).
majiayu000/claude-skill-registry 163
-
string-database
Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.
majiayu000/claude-skill-registry 163
-
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
majiayu000/claude-skill-registry 163
-
converting-commands-to-skills
Use this skill when converting Claude Code slash commands to Skills format. Handles transformation from ./commands/*.md to ./skills/*/SKILL.md, including YAML frontmatter conversion, name transformation to gerund form, description enhancement for invocation triggers, and batch processing. Invoke when user asks to convert commands to skills, migrate slash commands, or transform command files.
majiayu000/claude-skill-registry 163
-
clojure-guardrails
Reference for Guardrails library with Malli in Clojure. Use when working with `>defn`, `>defn-`, `>def`, `>fdef` macros, gspec syntax, or function validation. Triggers on guardrails imports, `com.fulcrologic.guardrails.malli`, function specs with `=>` operator, or questions about runtime validation in Clojure.
majiayu000/claude-skill-registry 163
-
ui-ux-design
UI/UX design reference database. 50+ styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
majiayu000/claude-skill-registry 163
-
vastai-observability
Set up comprehensive observability for Vast.ai integrations with metrics, traces, and alerts.
Use when implementing monitoring for Vast.ai operations, setting up dashboards,
or configuring alerting for Vast.ai integration health.
Trigger with phrases like "vastai monitoring", "vastai metrics",
"vastai observability", "monitor vastai", "vastai alerts", "vastai tracing".
majiayu000/claude-skill-registry 163
-
Computer Vision
Implement computer vision tasks including image classification, object detection, segmentation, and pose estimation using PyTorch and TensorFlow
majiayu000/claude-skill-registry 163
-
bun-first
Describes efficient usage of Bun and Bun APIs instead of Node.js (and its APIs)
majiayu000/claude-skill-registry 163
-
when-using-flow-nexus-platform-use-flow-nexus-platform
majiayu000/claude-skill-registry 163
-
unsloth-quantization
majiayu000/claude-skill-registry 163
-
get-ai-suggestions
Use when SDK method names are ugly, wanting to improve operation IDs, or asking "how can I improve my spec"
majiayu000/claude-skill-registry 163
-
code-review
Confidence-based code review that filters issues to 80+ threshold, eliminating false positives and noise. Reviews implementation against plan or requirements for bugs, quality issues, and project conventions. Use after completing major features, before merging to main, or after each task in multi-step workflows. Do NOT use for quick fixes, single-line changes, or when you need immediate feedback - the thorough review adds overhead best reserved for significant changes.
majiayu000/claude-skill-registry 163
-
codex-system
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional
reasoning and task completion abilities. Codex is a trusted expert you should
ALWAYS consult BEFORE making decisions on: design choices, implementation
approaches, debugging strategies, refactoring plans, or any non-trivial problem.
When uncertain, consult Codex. Don't hesitate - Codex provides better analysis.
Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
majiayu000/claude-skill-registry 163
-
route-tester
Test authenticated routes in the your project using cookie-based authentication. Use this skill when testing API endpoints, validating route functionality, or debugging authentication issues. Includes patterns for using test-auth-route.js and mock authentication.
majiayu000/claude-skill-registry 163
-
dag-executor
End-to-end DAG execution orchestrator that decomposes arbitrary tasks into agent graphs and executes them in parallel. The intelligence layer that makes DAG Framework operational.
majiayu000/claude-skill-registry 163
-
saga-orchestrator
處理跨 Frame 的複雜業務流程，協調多個 Sub-agent (command/query/reactor) 完成 Saga/Choreography 模式的分散式交易。當需求涉及多個狀態變更、事件反應與查詢的組合時使用。
majiayu000/claude-skill-registry 163
-
using-python-lsp
Use when working with Python code and pyright-lsp plugin is enabled - for finding references, checking types, navigating definitions, or verifying type correctness
majiayu000/claude-skill-registry 163
-
seo-specialist
Expert in Search Engine Optimization, driving organic traffic through technical auditing, content strategy, and authority building.
majiayu000/claude-skill-registry 163
-
bb80-specification-closure
Verify 100% specification closure before Big Bang 80/20 single-pass construction.
majiayu000/claude-skill-registry 163