Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
microimpute
ML-based variable imputation for survey data - used in policyengine-us-data to fill missing values
majiayu000/claude-skill-registry 163
-
r2-glacier-migration
Monitor and manage R2 to AWS Glacier Deep Archive migration. Use when checking transfer status, resuming transfers, or managing the archive migration.
majiayu000/claude-skill-registry 163
-
settlement-design
Design cities, towns, and settlements for fictional worlds. Use when creating urban environments, mapping city districts, or when settlements need realistic layered development and spatial logic.
majiayu000/claude-skill-registry 163
-
erlang-message-sync
Erlang-style message passing via /tmp file system. Use when simulating actor model with actual message synchronization between processes. Provides send/receive primitives with blocking and pattern matching.
majiayu000/claude-skill-registry 163
-
creating-subagents
Use when need to create specialized subagent for recurring tasks, domain-specific work, or pipeline automation
majiayu000/claude-skill-registry 163
-
cold-outreach
Master cold email, LinkedIn, and first-touch prospect outreach. Use when crafting outbound sequences, social touches, or follow-ups that must earn fast responses.
majiayu000/claude-skill-registry 163
-
shellcheck
Lint and fix shell script issues using ShellCheck. Use when the user says "check this script", "lint shell", "shellcheck", "fix script warnings", "validate bash", or asks to review a shell script for issues.
majiayu000/claude-skill-registry 163
-
scienceworld-process-pauser
This skill introduces deliberate pauses in task execution. It should be triggered when the agent needs to consider next steps, evaluate intermediate results, or wait for processes to complete. The skill uses the 'wait1' or 'wait' actions to temporarily halt activity, preventing rushed decisions in complex experimental procedures.
majiayu000/claude-skill-registry 163
-
checking-infrastructure-compliance
Execute use when you need to work with compliance checking.
This skill provides compliance monitoring and validation with comprehensive guidance and automation.
Trigger with phrases like "check compliance", "validate policies",
or "audit compliance".
majiayu000/claude-skill-registry 163
-
releasing-plugin-versions
Use when releasing a new plugin version, bumping versions, creating git tags, or publishing GitHub releases for this marketplace
majiayu000/claude-skill-registry 163
-
pr-feedback-classifier
Fetches and classifies PR review feedback with context isolation. Returns structured JSON with thread IDs for deterministic resolution. Use when analyzing PR comments before addressing them.
majiayu000/claude-skill-registry 163
-
20-understand-goal-150
[20] UNDERSTAND. Achieve complete clarity on goals, expectations, and success criteria. Use when starting new tasks, when requirements seem unclear, when scope is ambiguous, or anytime you need full understanding of what success looks like. Triggers on "clarify goal", "understand requirements", "what exactly needed", "define success", or when facing unclear expectations.
majiayu000/claude-skill-registry 163
-
video-frames
Extract frames or short clips from videos using ffmpeg.
majiayu000/claude-skill-registry 163
-
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
majiayu000/claude-skill-registry 163
-
exoplanet-workflows
General workflows and best practices for exoplanet detection and characterization from light curve data. Use when planning an exoplanet analysis pipeline, understanding when to use different methods, or troubleshooting detection issues.
majiayu000/claude-skill-registry 163
-
spec-based-web-dev
Systematic web development workflow from PRD to implementation plan. Generates database schemas, detailed use cases with sequence diagrams, page requirements with state management design (Context + useReducer), and modular implementation plans. Use when building web applications following spec-driven development methodology with PostgreSQL and React.
majiayu000/claude-skill-registry 163
-
agnosticv:validator
Validate AgnosticV catalog configurations against best practices and deployment requirements
majiayu000/claude-skill-registry 163
-
frontend-dev
前端开发规范，包含 Vue 3 编码规范、UI 风格约束、TypeScript 规范等
majiayu000/claude-skill-registry 163
-
mojo-simd-optimize
Apply SIMD optimizations to Mojo code for parallel computation. Use when optimizing performance-critical tensor and array operations.
majiayu000/claude-skill-registry 163
-
docx-template-filling
Fill DOCX template forms preserving 100% original structure - logos, footers, styles, metadata. Zero-artifact insertion. Output indistinguishable from manual entry.
majiayu000/claude-skill-registry 163
-
hecras_parse_compute-messages
Parse HEC-RAS compute output from HDF files to extract execution status,
diagnostic messages, and performance metrics. Converts raw computation
messages into structured diagnostics for workflow orchestration.
Use when checking plan completion status, extracting compute messages,
diagnosing execution failures, analyzing runtime performance, or
interpreting HEC-RAS error codes.
Keywords: compute messages, execution status, plan complete, runtime,
performance, error diagnostics, HEC-RAS output, simulation results,
warnings, convergence, instability, time step, iteration.
majiayu000/claude-skill-registry 163
-
Oracle ADK Expert
Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools, and enterprise patterns
majiayu000/claude-skill-registry 163
-
blog-resume
Resume work on blog posts - both in-progress drafts and published posts needing updates. Restores context when returning to continue work.
Trigger phrases: "resume", "continue", "work on", "update post", "continue working", "resume post", "continue post"
majiayu000/claude-skill-registry 163
-
strategic-investigation
Proactive recovery using plan mode and subagents. After 1-2 failed attempts, STOP trying variations. Enter plan mode and launch parallel Explore/Plan agents to find idiomatic solutions instead of spinning wheels.
majiayu000/claude-skill-registry 163