Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
self / nn / torch
General SOP for common requests related to self, nn, torch.
majiayu000/claude-skill-registry 163
-
slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
majiayu000/claude-skill-registry 163
-
vscode
VS Code integration for viewing diffs and comparing files. Use when showing file differences to the user.
majiayu000/claude-skill-registry 163
-
gathering-architecture
The drum sounds. Eagle, Swan, and Elephant gather for system architecture. Use when designing major systems from vision to implementation.
majiayu000/claude-skill-registry 163
-
edit-canvas-app
Edit an existing Power Apps canvas app. USE WHEN the user wants to modify, update, change, or edit an existing Canvas App or pa.yaml files.
majiayu000/claude-skill-registry 163
-
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
majiayu000/claude-skill-registry 163
-
Data Analysis
Turn raw data into decisions with statistical rigor, proper methodology, and awareness of analytical pitfalls.
majiayu000/claude-skill-registry 163
-
supabase-security
Audit de sécurité complet pour les projets Supabase. Lance un pentest automatisé qui vérifie RLS, buckets, auth, keys exposées, et génère un rapport avec remediation. Utiliser quand l'utilisateur dit "audit supabase", "sécurité supabase", "vérifier mon supabase", ou veut s'assurer que son backend Supabase est sécurisé.
majiayu000/claude-skill-registry 163
-
smart-rules
[Utility] Analyzes user prompts and efficiently loads only relevant rule documents. Auto-generates category-document mapping config file on first invocation by scanning project documents. Supports both automatic and manual invocation. (project)
majiayu000/claude-skill-registry 163
-
kubectl
Manage Kubernetes clusters, deployments, pods, and services using kubectl.
majiayu000/claude-skill-registry 163
-
pdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
majiayu000/claude-skill-registry 163
-
create-doc
Create or improve documentation based on the current conversation. Use this when a plan has been created and changes were requested because it didn’t follow the repository’s conventions.
majiayu000/claude-skill-registry 163
-
dependency-scanner
Software Composition Analysis (SCA) and dependency vulnerability scanning. Scan npm, pip, maven, gradle dependencies. Check CVE databases, generate SBOM (CycloneDX, SPDX), identify license compliance issues, and track EPSS scores for prioritization.
majiayu000/claude-skill-registry 163
-
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
majiayu000/claude-skill-registry 163
-
ducklake
Decide when DuckLake is the right MotherDuck storage pattern. Use when evaluating fully managed DuckLake, BYOB, own-compute DuckLake access, data inlining, object-storage layout, or file-aware maintenance instead of native MotherDuck storage.
majiayu000/claude-skill-registry 163
-
landing-page-intel
Extract competitor and customer intelligence from any company's landing page HTML. Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements, and more. No API keys required.
majiayu000/claude-skill-registry 163
-
ralph-resume
Resume a PAUSED Ralph session — retry failed task, skip, or abort
majiayu000/claude-skill-registry 163
-
moai-lang-rust
Rust 1.92+ development specialist covering Axum, Tokio, SQLx, and memory-safe systems programming. Use when building high-performance, memory-safe applications or WebAssembly.
majiayu000/claude-skill-registry 163
-
duet
Two-party working posture — user as director, agent as executor. Every fork, tradeoff, and taste choice is surfaced via batched AskUserQuestion with structural framing, a recommended default, and concrete previews when comparison is visual, so the human steers direction while the agent handles implementation. Eliminates the review-bottleneck (no giant diff to approve at the end — review is distributed across picks) and prevents codebase-understanding debt (the user remembers the architecture because they picked it). Use whenever the user invokes /duet, or says "work with me", "ask before", "check with me", "I want to decide", "don't assume", "human-in-the-loop", "co-author", "pair with me", "duet", or whenever a task clearly involves aesthetic, architectural, or irreversible strategic decisions — even without those exact words. Pair with the Duet output style to minimize cognitive load between picks.
majiayu000/claude-skill-registry 163
-
subagent-driven-development
（中文）Use when executing implementation plans with independent tasks in the current session
majiayu000/claude-skill-registry 163
-
meeting-insights-analyzer
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
majiayu000/claude-skill-registry 163
-
source-verifier
Ensure every factual claim in a response is backed by verifiable evidence from the codebase, documentation, or external sources. Use when preparing technical documentation, code reviews, or any output where accuracy is non-negotiable.
majiayu000/claude-skill-registry 163
-
cross-repo-coordination
Coordinate changes across project-beta repositories when updating runner configurations. Ensures workflow labels match runner scale set names. Use when changing runnerScaleSetName or deploying new runner pools.
majiayu000/claude-skill-registry 163
-
diff-review-4meta5-skills
majiayu000/claude-skill-registry 163