Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
train-model
Execute model training with optimization algorithms. Use when running training loops on datasets.
majiayu000/claude-skill-registry 163
-
document-lessons-as-snippets
When you make a mistake or discover a better approach, immediately suggest creating an Agent Beha... Use when configuring AI agent workflows and patterns. Agent Behavior category skill.
majiayu000/claude-skill-registry 163
-
cost-estimate
コスト見積書を作成する。予算策定、見積もり、コスト計画時に使う。
majiayu000/claude-skill-registry 163
-
python-dev
Python 开发规范，包含 PEP 8 风格、类型注解、异常处理、测试规范等
majiayu000/claude-skill-registry 163
-
task-authoring
Task Authoring skill for the ikigai project
majiayu000/claude-skill-registry 163
-
dna-extraction
Extract the functional DNA from existing works (TV, film, books, plays). Use when adapting a source work, when analyzing what makes something work, when creating trope maps for reuse, or when you need to separate structural necessity from stylistic choice.
majiayu000/claude-skill-registry 163
-
frontend-testing
Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.
majiayu000/claude-skill-registry 163
-
pivot-or-perish-audit
A framework to break out of "zombie company" cycles by forcing a scientific assessment of product-market fit. Use this when growth has stalled on a "flat hockey stick," when you are questioning your current strategy, or when you suspect you are avoiding a necessary pivot due to ego or investor pressure.
majiayu000/claude-skill-registry 163
-
multi-ai
Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.
majiayu000/claude-skill-registry 163
-
axiom-codable
Use when working with Codable protocol, JSON encoding/decoding, CodingKeys customization, enum serialization, date strategies, custom containers, or encountering "Type does not conform to Decodable/Encodable" errors - comprehensive Codable patterns and anti-patterns for Swift 6.x
majiayu000/claude-skill-registry 163
-
diffdock
Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.
majiayu000/claude-skill-registry 163
-
add-ravendb-index
Create RavenDB indexes for efficient document queries (project)
majiayu000/claude-skill-registry 163
-
dspy-rag-pipeline
This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions "RAG with DSPy", "context retrieval", "multi-hop RAG", or needs to build a DSPy system that retrieves external knowledge to answer questions with grounded, factual responses.
majiayu000/claude-skill-registry 163
-
testing-skills-with-subagents
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
majiayu000/claude-skill-registry 163
-
monthly-review
Aggregate weekly summaries into a monthly overview. Use when asked to "monthly review", "review the month", "summarize this month", or "month summary".
majiayu000/claude-skill-registry 163
-
harness-eks-deployments
AWS EKS deployment patterns via Harness CD - Native Helm, Kubernetes manifests, and GitOps strategies with rolling, canary, and blue-green deployments
majiayu000/claude-skill-registry 163
-
character-arc
Design and troubleshoot character transformation arcs. Use when characters feel static, when transformation feels unearned or abrupt, when you can't articulate what false belief needs to die, or when characters serve plot without having internal journeys. Covers positive, negative, and flat arcs.
majiayu000/claude-skill-registry 163
-
leverage-point-audit
Audit a codebase for the 12 leverage points of agentic coding. Identifies gaps and provides prioritized recommendations. Use when improving agentic coding capability, analyzing why agents fail, or optimizing a codebase for autonomous work.
majiayu000/claude-skill-registry 163
-
epic-ui-guidelines
Guide on UI/UX guidelines, accessibility, and component usage for Epic Stack
majiayu000/claude-skill-registry 163
-
commands-en-shinpr-ai-coding-project-bo-72c261b1
Implement user skill change requests with maximum precision optimization
majiayu000/claude-skill-registry 163
-
worklog
Add timestamped work log entries to track progress and decisions. Use for documenting work, decisions, gotchas, and handoffs between agents.
majiayu000/claude-skill-registry 163
-
fun-mode
Use when starting a session and wanting creative engagement, or when user says '/fun' or asks for a persona
majiayu000/claude-skill-registry 163
-
makefile
Makefile patterns for project automation and build tasks. Use when user asks to "create Makefile", "add make target", "automate with make", "build commands", or set up project automation with GNU Make.
majiayu000/claude-skill-registry 163
-
heart-gate
majiayu000/claude-skill-registry 163