Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
Design Undo/Redo Systems
CREATE comprehensive undo/redo systems with Command Pattern. Design state management for complex applications with canvas interactions, multiple stores, and user actions. Use when building new undo/redo functionality from scratch.
majiayu000/claude-skill-registry 163
-
manual_tests.run_fire_tests
Runs all 6 'should fire' tests serially with resets between each. Use after NOT-fire tests to verify rules fire correctly.
majiayu000/claude-skill-registry 163
-
implement_plan
Implement technical plans from thoughts/shared/plans with verification
majiayu000/claude-skill-registry 163
-
epic-management
Use for LARGE work requiring feature-level grouping. Creates epic tracking issues, manages related issues under a common label, tracks epic progress, and coordinates with milestones.
majiayu000/claude-skill-registry 163
-
bun-development
Modern JavaScript/TypeScript development with Bun runtime. Covers package management, bundling, testing, and migration from Node.js. Use when working with Bun, optimizing JS/TS development speed, or migrating from Node.js to Bun.
majiayu000/claude-skill-registry 163
-
ln-770-crosscutting-setup
Coordinates logging, error handling, CORS, health checks, and API docs
majiayu000/claude-skill-registry 163
-
decision-graph
Use when building a deciduous decision graph to capture design evolution, architecture history, or how a codebase's design changed over time. Provides the deciduous CLI commands and graph structure guidelines.
majiayu000/claude-skill-registry 163
-
update-system-map
Update the System Knowledge Map documentation
majiayu000/claude-skill-registry 163
-
jj:describe
Generate and set a commit description for a commit in jj
majiayu000/claude-skill-registry 163
-
brand-guidelines-enforcer
[Design System] Lightweight brand guidelines enforcement for UI copy and visual motifs. Use when (1) checking UI labels/buttons/error messages against brand tone, (2) validating color usage in specific contexts, (3) ensuring reserved components are used correctly, (4) user asks to 'check brand guidelines', 'validate brand compliance', 'review copy tone', or 'enforce design rules'.
majiayu000/claude-skill-registry 163
-
verdict-flags
a skill that contains all the best practices for using Verdict Flags in shopify codebases. It should be uses whenever the agent is creating, updating or removing flags
majiayu000/claude-skill-registry 163
-
swift-unit-tests
How to run swift unit tests
majiayu000/claude-skill-registry 163
-
elixir-verification-gate
MANDATORY verification before claiming anything works. Run actual commands, read actual output, provide evidence. Use when claiming tests pass, build succeeds, or code works.
majiayu000/claude-skill-registry 163
-
ln-621-security-auditor
Security audit worker (L3). Scans codebase for hardcoded secrets, SQL injection, XSS, insecure dependencies, missing input validation. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
majiayu000/claude-skill-registry 163
-
rust-systems-programming
Complete guide for Rust systems programming including ownership, borrowing, concurrency, async programming, unsafe code, and performance optimization
majiayu000/claude-skill-registry 163
-
dh-frame
This skill should be used when creating a new Daggerheart campaign, establishing world tone and themes, selecting or building a campaign frame, or reframing an existing adventure. Campaign frames provide pitch, tone, themes, community/ancestry/class guidance, principles, distinctions, inciting incidents, and special mechanics for a particular type of story.
majiayu000/claude-skill-registry 163
-
excel-data-analyzer
Analyze messy and unstructured Excel files to identify data quality issues, detect format inconsistencies, find missing values, and generate comprehensive analysis reports. Use when Claude needs to work with Excel files (.xlsx, .xls) for data quality assessment, structure analysis, or when users request data auditing, cleaning recommendations, or statistical summaries of spreadsheet data.
majiayu000/claude-skill-registry 163
-
backtesting-trading-strategies
Test backtest crypto trading strategies against historical data with performance metrics.
Use when validating trading strategies with historical data.
Trigger with phrases like "backtest strategy", "test trading signals", or "validate approach".
majiayu000/claude-skill-registry 163
-
evaluation-rubrics
Use when need explicit quality criteria and scoring scales to evaluate work consistently, compare alternatives objectively, set acceptance thresholds, reduce subjective bias, or when user mentions rubric, scoring criteria, quality standards, evaluation framework, inter-rater reliability, or grade/assess work.
majiayu000/claude-skill-registry 163
-
swift-networking
Handle networking in Swift - URLSession, async/await, Codable, API clients, error handling
majiayu000/claude-skill-registry 163
-
discover-containers
Automatically discover container and Docker skills when working with Docker. Activates for containers development tasks.
majiayu000/claude-skill-registry 163
-
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
majiayu000/claude-skill-registry 163
-
word
Create, read, edit, and manipulate Microsoft Word documents (.docx files). Use when users ask to work with Word files, create documents, read .docx files, or format text documents.
majiayu000/claude-skill-registry 163
-
task-router-mcp
Multi-agent task orchestration MCP server. Queue-based workflow where Claude Desktop assigns tasks → agents claim → execute → report completion → next task auto-assigned.
majiayu000/claude-skill-registry 163