Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
vibe-gap-closure-loop
Closes production readiness gaps from a gap analysis document. Autonomously loops dependency analysis, parallel agent dispatch, test gate, re-audit, and repeats until target dimensions reach target score.
majiayu000/claude-skill-registry 163
-
rust-async-patterns
Master Rust async programming with Tokio, async traits, error handling, and concurrent patterns. Use when building async Rust applications, implementing concurrent systems, or debugging async code.
majiayu000/claude-skill-registry 163
-
segment-anything-model
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
majiayu000/claude-skill-registry 163
-
design-justice
Digital equity and trauma-informed design for marginalized populations. Activate on "accessibility", "offline-first", "trauma-informed", "reentry", "recovery population", "shared device", "unstable phone", "digital equity", "design justice", "low-literacy", "intermittent access". NOT for general UX, marketing optimization, or enterprise SaaS design.
majiayu000/claude-skill-registry 163
-
healthcare-audit-logger
This skill should be used when the user asks to "generate audit logs", "create HIPAA audit trail", "log healthcare events", "configure audit logging", "track PHI access", "maintain compliance logs", "audit log format", "healthcare event logging", "access control logging", "authentication logging", "HIPAA logging requirements", or mentions HIPAA audit trails, healthcare event logging, compliance logging, PHI access tracking, authentication auditing, or §164.312(b) logging requirements.
majiayu000/claude-skill-registry 163
-
product-thinker
Use for product decisions, user behavior analysis, and UX evaluation. Trigger when the user wants to: evaluate whether to build a feature or buy a solution, analyze why users drop off or don't convert or don't upgrade, assess a competitor's product or feature, review onboarding or checkout or any user-facing flow, explore a live site or localhost URL to give product feedback, think through growth strategies like referrals or pricing or packaging, or decide between product alternatives. The core signal is the user asking "should we?" or "is it worth?" or "why are users?" or "what do you think about [product/feature/flow]?" or asking you to look at a product and assess it. Also use alongside shaping-work when the user needs product thinking before defining work. NOT for: writing/fixing code, test authoring, PR review, database operations, CI/CD, or decomposing PRDs into tickets.
majiayu000/claude-skill-registry 163
-
mlops-engineer
majiayu000/claude-skill-registry 163
-
ralph-wiggum-codex
Use when a coding task needs an objective-first long-running loop with fresh-context work and review phases, explicit acceptance criteria, resumable state, and real blocked handling.
majiayu000/claude-skill-registry 163
-
strategic-planner
Interview-based strategic planning for complex software tasks. Conducts structured requirements gathering, gap analysis, and generates detailed work plans before implementation begins.
majiayu000/claude-skill-registry 163
-
sprint-254-features
Azure DevOps Sprint 254-262 new features and enhancements (2025)
majiayu000/claude-skill-registry 163
-
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems,
AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues
in source code, committing each fix atomically and re-verifying with before/after
screenshots. For plan-mode design review (before implementation), use /plan-design-review.
Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish".
Proactively suggest when the user mentions visual inconsistencies or
wants to polish the look of a live site.
majiayu000/claude-skill-registry 163
-
Testing
Standards for Component Test Harnesses and TestBed.
majiayu000/claude-skill-registry 163
-
git
Git workflows, branching strategies, and hooks.
majiayu000/claude-skill-registry 163
-
ai-verify
Use when you need to PROVE a claim with evidence, run quality/security scans, or validate that work is actually complete. Evidence before claims -- no 'should work' allowed.
majiayu000/claude-skill-registry 163
-
clean-code
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
majiayu000/claude-skill-registry 163
-
resume-handoff
Resume work from handoff document with context analysis and validation
majiayu000/claude-skill-registry 163
-
video-processing-editing
FFmpeg automation for cutting, trimming, concatenating videos. Audio mixing, timeline editing, transitions, effects. Export optimization for YouTube, social media. Subtitle handling, color grading, batch processing. Use for videogen projects, content creation, automated video production. Activate on "video editing", "FFmpeg", "trim video", "concatenate", "transitions", "export optimization". NOT for real-time video editing UI, 3D compositing, or motion graphics.
majiayu000/claude-skill-registry 163
-
bluebubbles
Use when you need to send or manage iMessages via BlueBubbles (recommended iMessage integration). Calls go through the generic message tool with channel="bluebubbles".
majiayu000/claude-skill-registry 163
-
qa_review_triple-model
Launch four independent AI code reviewers (Opus, Gemini, Codex, Kimi K2.5) to QA/QC code or notebooks.
Each reviewer writes findings to separate markdown files, then orchestrator synthesizes.
Use for critical code review, bug investigation, or quality assurance tasks.
Triggers: triple review, quad review, four model review, independent code review, QAQC,
quality assurance, multi-model analysis, cross-validation, bug investigation, critical review,
kimi review, togetherai review
majiayu000/claude-skill-registry 163
-
post-mortem
Wrap up completed work. Council validates the implementation, then extract and process learnings. Triggers: "post-mortem", "wrap up", "close epic", "what did we learn".
majiayu000/claude-skill-registry 163
-
firecrawl-web-extraction
当需要使用 Firecrawl 完成网页搜索、单页抓取、结构化提取、截图、URL 映射、整站 crawl 或 JavaScript 渲染页面内容提取时使用。适用于“搜索并抓网页内容”“提取某个 URL 的主体内容”“把网页字段按 schema 抽出来”“批量抓文档站”以及需要 Firecrawl CLI 的场景。
majiayu000/claude-skill-registry 163
-
liquid-glass-design
iOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing for SwiftUI, UIKit, and WidgetKit.
majiayu000/claude-skill-registry 163
-
go-functional-options
Use when designing a Go constructor or factory function with optional configuration — especially with 3+ optional parameters or extensible APIs. Also use when building a New* function that takes many settings, even if they don't mention "functional options" by name. Does not cover general function design (see go-functions).
majiayu000/claude-skill-registry 163
-
azure-batch
Expert knowledge for Azure Batch development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring Batch pools/tasks, autoscale, containers, VM/Spot choices, or CI/CD job deployments, and other Azure Batch related development tasks. Not for Azure HDInsight (use azure-hdinsight), Azure Databricks (use azure-databricks), Azure Stream Analytics (use azure-stream-analytics), Azure Functions (use azure-functions).
majiayu000/claude-skill-registry 163