Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
dosdp-design-patterns
Skills for understanding and applying DOSDP (Dead Simple Ontology Design Patterns) to ensure consistent ontology term creation and maintenance. This skill is about recognizing patterns and ensuring consistency, not using dosdp-tools directly.
majiayu000/claude-skill-registry 163
-
reactree-patterns
majiayu000/claude-skill-registry 163
-
bd-issue-tracking
Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.
majiayu000/claude-skill-registry 163
-
physicist-analyst
Analyzes events through physics lens using fundamental laws (thermodynamics, conservation, relativity),
quantitative modeling, systems dynamics, and energy principles to understand causation, constraints, and feasibility.
Provides insights on energy systems, physical limits, technological feasibility, and complex systems behavior.
Use when: Energy decisions, technology assessment, systems analysis, physical constraints, feasibility evaluation.
Evaluates: Energy flows, conservation laws, efficiency limits, physical feasibility, scaling behavior, emergent properties.
majiayu000/claude-skill-registry 163
-
gh-fix-ci
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.
majiayu000/claude-skill-registry 163
-
open-eth-terminal-action-generator
An agent that can help users with creating new actions to check into the codebase. It should generate action code and link it to the application after querying the user for information about the goal of the action.
majiayu000/claude-skill-registry 163
-
unsloth-orpo
majiayu000/claude-skill-registry 163
-
commit-messenger
コミットメッセージの命名規則を設定する。「コミットメッセージ設定」「コミット規則」「コミット形式を設定」「コミットメッセージルール」「commit message 設定」「コミットの書き方を設定」「コミットフォーマット」などで起動。プロジェクト固有のコミットメッセージルールを管理。
majiayu000/claude-skill-registry 163
-
azure-monitor-ingestion-java
Azure Monitor Ingestion SDK for Java. Send custom logs to Azure Monitor via Data Collection Rules (DCR) and Data Collection Endpoints (DCE).
Triggers: "LogsIngestionClient java", "azure monitor ingestion java", "custom logs java", "DCR java", "data collection rule java".
majiayu000/claude-skill-registry 163
-
azure-ai-formrecognizer-java
Build document analysis applications with Azure Document Intelligence (Form Recognizer) SDK for Java. Use when extracting text, tables, key-value pairs from documents, receipts, invoices, or building custom document models.
majiayu000/claude-skill-registry 163
-
scienceworld-target-locator
This skill determines the most likely location for a target object based on domain knowledge and environmental clues. Trigger this when the agent needs to find a specific item (like an animal) but it is not in the current room. It analyzes the environment description and suggests a room to teleport to for further investigation.
majiayu000/claude-skill-registry 163
-
parallel-workflows
Optimizes parallel execution of multiple tasks. Use when user mentions running tasks in parallel or together. Do NOT load for: single tasks, sequential-only work, or tasks with dependencies.
majiayu000/claude-skill-registry 163
-
beads-issue-tracking
Track complex, multi-session work with dependency graphs using beads (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.
majiayu000/claude-skill-registry 163
-
start-discussion
Start a technical discussion. Discovers research and existing discussions, offers multiple entry paths, and invokes the technical-discussion skill.
majiayu000/claude-skill-registry 163
-
idb-state-persistence
IndexedDB patterns for local-first state persistence using the idb library. Use when implementing features that require persistent state across navigation and sessions. Covers data modeling, defaults, CRUD operations, state managers, and reset patterns. Integrates with web-components for reactive UI updates.
majiayu000/claude-skill-registry 163
-
literature-review
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
majiayu000/claude-skill-registry 163
-
sam-gov-ops
Query SAM.gov for federal contracts, entity registrations, exclusions, and opportunities. Uses official GSA APIs for government contractor intelligence and OSINT research.
majiayu000/claude-skill-registry 163
-
causal-inference-root-cause
Use when investigating why something happened and need to distinguish correlation from causation, identify root causes vs symptoms, test competing hypotheses, control for confounding variables, or design experiments to validate causal claims. Invoke when debugging systems, analyzing failures, researching health outcomes, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?"
majiayu000/claude-skill-registry 163
-
blog-manager
Use for all blog writing tasks including creating articles (Zenn Japanese, dev.to/Medium English), managing ideas, and setting up blog projects. This is the unified entry point for technical blog writing workflow. Supports idea tracking with status management (backlog/in-progress/done).
majiayu000/claude-skill-registry 163
-
hitl-approval
Implement human-in-the-loop approval flows. Use when adding Slack approvals, dashboard review queues, action gating, or trust-based auto-approval.
majiayu000/claude-skill-registry 163
-
pop-assessment-anthropic
Validates PopKit compliance with Claude Code patterns using concrete standards and automated checks
majiayu000/claude-skill-registry 163
-
update-doc
Use when user says 'update docs', 'sync documentation', 'refresh docs', or after code changes need documenting. Updates llmdoc system based on recent code changes.
majiayu000/claude-skill-registry 163
-
phase-validation
Phase 0-6 검증 자동화. 각 Phase별 필수 조건 확인.
majiayu000/claude-skill-registry 163
-
hosted-agents
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments.
majiayu000/claude-skill-registry 163