Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
majiayu000/claude-skill-registry 163
-
team-chemistry-evaluator
Analyze roster fit and personality dynamics. Leadership assessment, role clarity, locker room culture, trade/signing impact.
majiayu000/claude-skill-registry 163
-
creating-knowledge-entries
Create GitHub Issue knowledge entries. TRIGGERS - share knowledge, document solution, create how-to, add to knowledge base.
majiayu000/claude-skill-registry 163
-
reading-notion
Notion URLが会話に登場した時、またはNotionのコンテンツを検索・取得する必要がある時に使用してください。
majiayu000/claude-skill-registry 163
-
tsconfig-builder
Generate properly configured tsconfig.json files for TypeScript projects with appropriate compiler options for various project types. Triggers on "create tsconfig", "generate tsconfig.json", "typescript config for", "configure TypeScript".
majiayu000/claude-skill-registry 163
-
nqs-sqd-research
Deep technical assistant for projects that combine Neural Quantum States (FFNN and Transformer-based) with Sample-based Quantum Diagonalization (SQD). Trigger this skill whenever the task involves: (1) designing or analyzing NQS architectures for quantum chemistry, (2) connecting classical samplers to qiskit-addon-sqd, (3) studying sample-efficiency, bias, and variance in few-sample regimes (e.g. 12–14-bit H2).
majiayu000/claude-skill-registry 163
-
solarwinds-logs
Search and analyze DealerVision production logs via SolarWinds Observability API. Use when investigating errors, debugging issues, checking system health, or when the user mentions logs, SolarWinds, production errors, or system monitoring. Requires the `logs` CLI tool to be installed.
majiayu000/claude-skill-registry 163
-
queue-observability
Monitor message queues, job processing, and detect backpressure
majiayu000/claude-skill-registry 163
-
gob-background-jobs
Use when user requests "parallel" commands, running multiple builds/tests simultaneously, or long-running tasks. Use `gob add` instead of parallel Bash tool calls - gob provides job management, output capture, and proper process control.
majiayu000/claude-skill-registry 163
-
license-checker
Assess license compatibility for Python package redistribution using SPDX.org license database. Evaluates whether a given license allows building and distributing wheels, with real-time license information lookup.
majiayu000/claude-skill-registry 163
-
load-conversation
Load the full content of a previous Claude Code conversation into current context. Use when user asks to "load conversation <uuid>" or "show me conversation <uuid>" or references loading/viewing a past conversation by its ID.
majiayu000/claude-skill-registry 163
-
typer-patterns
Modern type-safe Typer CLI patterns with type hints, Enums, and sub-apps. Use when building CLI applications, creating Typer commands, implementing type-safe CLIs, or when user mentions Typer, CLI patterns, type hints, Enums, sub-apps, or command-line interfaces.
majiayu000/claude-skill-registry 163
-
Agent Prompting & Delegation
Best practices for writing effective Task tool prompts that produce clear, structured outputs from sub-agents. Covers context engineering, instruction clarity, output format specification, and parallel delegation patterns. MUST BE USED PROACTIVELY when spawning sub-agents to ensure high-quality results.
majiayu000/claude-skill-registry 163
-
vibe-validate
Expert guidance for vibe-validate, an LLM-optimized validation orchestration tool. Use when working with vibe-validate commands, configuration, pre-commit workflows, or validation orchestration in TypeScript projects.
majiayu000/claude-skill-registry 163
-
castella-a2a
Connect to A2A protocol agents from Castella. Communicate with agents, display agent cards, send messages, handle responses, and stream results.
majiayu000/claude-skill-registry 163
-
debug-coffee-ahk
查询 coffee-ahk 编译架构、bug 定位方法、调试技巧，use when debugging/fixing bugs or need to understand compilation flow
majiayu000/claude-skill-registry 163
-
clink-codex-delegate
Activate when user mentions "clink codex" to provide guidance on delegating implementation tasks to clink codex as a junior developer. Use when assigning coding tasks, discussing task delegation, or working with clink codex for code implementation.
majiayu000/claude-skill-registry 163
-
review-pr
Review pull requests using GitHub CLI. Invoke with /review-pr <pr-number-or-url>
majiayu000/claude-skill-registry 163
-
prometheus-config-generator
Prometheus Config Generator - Auto-activating skill for DevOps Advanced.
Triggers on: prometheus config generator, prometheus config generator
Part of the DevOps Advanced skill category.
majiayu000/claude-skill-registry 163
-
markdowntown-workbench
Use this when working on the Workbench UI, Workbench state/store, export/compile pipeline, or adapter/target behavior (agents-md, claude-code, github-copilot, etc.).
majiayu000/claude-skill-registry 163
-
sag
ElevenLabs text-to-speech with mac-style say UX.
majiayu000/claude-skill-registry 163
-
agent-workflow
Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates building-agents-* and testing-agent skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.
majiayu000/claude-skill-registry 163
-
skills-dcramer-ash
majiayu000/claude-skill-registry 163
-
aico-pm-clarification
Resolve requirement ambiguities through STRUCTURED questioning: one question at a time, with recommended options and reasoning.
UNIQUE VALUE: Prevents overwhelming users with multiple questions. Provides expert recommendations for each decision.
Use this skill when:
- Running /pm.clarify command
- User says "unclear", "not sure what this means", "confused about"
- User asks "what does X mean?", "how should X work?", "can you clarify?"
- Requirements have conflicting or inconsistent details
- Stories are missing acceptance criteria or have gaps
- Need to fill information gaps BEFORE development can proceed
Process: Ask ONE question at a time (max 5 per session), provide recommended option with reasoning.
DO NOT ask multiple questions at once - this overwhelms users.
majiayu000/claude-skill-registry 163