Claude Skills
MarketplacesSpecificationSubmit
Sign inSign up
© 2026 Claude Skills·Learn more about Agent Skills

Claude Skills

aka. Agent Skills

Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.

Claude Code
OpenAI Codex
Gemini CLI
Cursor
GitHub Copilot
+more
1875 MarketplacesSpecification
13225 verified skills
#SkillStars
2501
#2501

cross-plugin-detective

verified
development

Use when integrating detective skills across plugins. Maps agent roles to appropriate detective skills (developer → developer-detective, architect → architect-detective). Reference this to connect agents with claudemem investigation capabilities.

MadAppGang/claude-code
221
2502
#2502

architect-detective

verified
development

Use when analyzing architecture and system design. Find design patterns, map layers, identify core abstractions via PageRank. Uses claudemem AST structural analysis for efficient architecture investigation.

MadAppGang/claude-code
221
2503
#2503

debugger-detective

verified
development

⚡ Debugging skill. Best for: 'why is X broken', 'find bug source', 'root cause analysis', 'trace error', 'debug issue'. Uses claudemem AST with context command for efficient call chain analysis.

MadAppGang/claude-code
221
2504
#2504

developer-detective

verified
development

⚡ Implementation analysis skill. Best for: 'how does X work', 'find implementation of', 'trace data flow', 'where is X defined', 'find all usages'. Uses claudemem AST with callers/callees for efficient code tracing.

MadAppGang/claude-code
221
2505
#2505

search-interceptor

verified
development

💡 Bulk file read optimizer. Suggests semantic search alternatives when reading multiple files. Helps reduce token usage by using claudemem's ranked results instead of sequential file reads.

MadAppGang/claude-code
221
2506
#2506

multi-agent-coordination

verified
development

Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to sub-agents, switching between specialized agents, or managing agent selection. Trigger keywords - "parallel agents", "sequential workflow", "delegate", "multi-agent", "sub-agent", "agent switching", "task decomposition".

MadAppGang/claude-code
221
2507
#2507

task-orchestration

verified
development

Track progress in multi-phase workflows with Tasks system. Use when orchestrating 5+ phase commands, managing iteration loops, tracking parallel tasks, or providing real-time progress visibility. Trigger keywords - "phase tracking", "progress", "workflow", "multi-step", "multi-phase", "tasks", "tracking", "status".

MadAppGang/claude-code
221
2508
#2508

test-coverage

verified
development

On-demand test coverage analysis. Use when identifying untested code, finding test gaps, measuring coverage metrics, or improving test quality. Trigger keywords - "test coverage", "coverage report", "untested code", "test gaps", "missing tests", "coverage metrics".

MadAppGang/claude-code
221
2509
#2509

help

verified
workflow

Get help with Conductor - commands, usage examples, and best practices

MadAppGang/claude-code
221
2510
#2510

setup

verified
workflow

Initialize Conductor with product.md, tech-stack.md, and workflow.md

MadAppGang/claude-code
221
2511
#2511

audit

verified
development

On-demand security and code quality audit. Use when checking for vulnerabilities, security issues, code smells, or compliance problems. Trigger keywords - "audit", "security check", "vulnerability scan", "code quality", "compliance", "security audit".

MadAppGang/claude-code
221
2512
#2512

memory-search

verified
productivity

PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and context BEFORE starting new work. Your memory is valuable - use it.

23blocks-OS/ai-maestro
220
2513
#2513

planning

verified
productivity

Use persistent markdown files for complex task execution. Creates task_plan.md, findings.md, and progress.md. Use when starting multi-step tasks, research projects, or any task requiring >5 tool calls. Solves the EXECUTION problem - staying focused during long-running tasks.

23blocks-OS/ai-maestro
220
2514
#2514

docs-search

verified
productivity

PROACTIVELY search auto-generated documentation when receiving ANY user instruction. Search for function signatures, API documentation, class definitions, and code comments BEFORE implementing anything. Your codebase documentation is valuable - use it first.

23blocks-OS/ai-maestro
220
2515
#2515

graph-query

verified
productivity

PROACTIVELY query the code graph database to understand relationships and impact of changes. Use this skill WHEN READING any file to understand context, when searching for files, when exploring the codebase, or when you need to understand what depends on a component. This is your primary tool for understanding code structure and avoiding breaking changes.

23blocks-OS/ai-maestro
220
2516
#2516

scheduler

verified

Schedules Claude Code tasks to run automatically at specific times using native OS schedulers (launchd on macOS, crontab on Linux, Task Scheduler on Windows). Handles one-time tasks like "today at 3pm remind me to deploy", "tomorrow morning run the test suite", "next Tuesday at 2pm review the API changes", "January 15th check the quarterly metrics". Also handles recurring tasks like "every weekday at 9am review yesterday's code", "daily at 6pm summarize what I accomplished", "every Monday at 10am check for security vulnerabilities", "every 4 hours check API health". Recognizes time formats like "at 9am", "at 1015am", "at 10:30pm", "at noon", relative times like "tomorrow", "tonight", "later", "next week", and dates like "January 15th". Use this skill instead of executing immediately whenever the user's request contains a time expression like "at Xam", "tomorrow", or any future time reference.

jshchnz/claude-code-scheduler
215
2517
#2517

gitflow-workflow

verified
development

Use this skill for GitFlow tasks: starting/finishing features, releases, hotfixes; managing branches; versioning; or general GitFlow operations.

FradSer/dotclaude
208
2518
#2518

commit

verified
development

This skill should be used when the user requests "commit", "git commit", "create commit", or wants to commit staged/unstaged changes following conventional commits format

FradSer/dotclaude
208
2519
#2519

start-hotfix

verified
development

Start new hotfix branch

FradSer/dotclaude
208
2520
#2520

quick

verified
productivity

Streamlined code review for rapid assessment and targeted feedback

FradSer/dotclaude
208
Previous
Page 126 of 662
Next