20554 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

dispatching-parallel-agents

Use when facing 3+ logically independent failures (different features, different root causes) that can be investigated concurrently - dispatches multiple agents to investigate in parallel; requires either parallel-safe test infrastructure OR sequential fix implementation

parallelismagent-orchestrationfailure-investigationconcurrent-debugging
samjhecht
samjhecht
1

locating-code

Finds WHERE code lives in a codebase - locates files by topic/feature, categorizes by purpose, organizes findings. Super grep/glob/ls tool for navigating unfamiliar codebases.

code-navigationcodebase-analysissearch-toolfile-organization
samjhecht
samjhecht
1

housekeeping

Perform comprehensive project housekeeping - update roadmap, reconcile issues with implementation reality, organize completed work, and identify drift. This is a workflow skill that coordinates multiple parallel subagents for efficiency. Use when user says something like "run housekeeping", "do your housekeeping" or "clean up project state".

project-planningissue-trackingprogress-trackingworkflow-automation
samjhecht
samjhecht
1

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by verifying work is complete (tests, requirements, code review, TDD compliance) and presenting structured options for merge, PR, or cleanup

branch-managementmerge-strategycode-reviewtest-driven-development
samjhecht
samjhecht
1

figma-design-workflow

Generate Figma mockups from wrangler specifications with hierarchical file structure and approval tracking

figmaworkflowmockupsapproval-tracking
samjhecht
samjhecht
1

organize-root-files

Clean up and organize markdown files dumped at project root. Routes files to appropriate directories (memos/, docs/, devops/docs/) or deletes obsolete content. Follows project file organization guidelines from CLAUDE.md.

markdownfile-organizationproject-structurecleanup
samjhecht
samjhecht
1

receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

code-reviewdeveloper-guidancetechnical-rigorfeedback-verification
samjhecht
samjhecht
1

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

frontendweb-componentshtml-cssjavascript
samjhecht
samjhecht
1

implement-spec

Orchestrate spec-to-PR workflow with session tracking, worktree isolation, and audit trail

workflow-automationsession-managementgit-worktreesaudit-trail
samjhecht
samjhecht
1

implement

Autonomously implement tasks from specs, plans, or issues using subagents with TDD and code review

autonomous-agentsubagentstddcode-review
samjhecht
samjhecht
1

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

gitversion-controlworkspace-managementfeature-branch
samjhecht
samjhecht
1

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

test-driven-developmenttest-first-developmentcode-qualitydeveloper-guidance
samjhecht
samjhecht
1

validating-roadmap

Validates specification consistency, identifies implementation gaps, reviews roadmap coherence. Ensures documentation aligns, tasks are realistic, and dependencies are clear.

roadmap-planningspecification-validationgap-analysisdependency-management
samjhecht
samjhecht
1

run-the-tests

Run the project's test suite and fix any failures. If no test runner is configured, sets up best-in-class testing infrastructure for the project's language/framework. Ensures all tests pass before completion.

test-runnertest-infrastructuretest-failurestesting-automation
samjhecht
samjhecht
1

root-cause-tracing

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

call-stackinstrumentationbug-tracingerror-analysis
samjhecht
samjhecht
1

sharing-skills

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

pull-requestversion-controlgitcontribution-guidelines
samjhecht
samjhecht
1

refining-specifications

Reviews existing specifications for ambiguity and missing decision points - uses structured taxonomy to detect gaps, generates prioritized clarification questions, reduces specification uncertainty.

specificationambiguity-detectiongap-analysisprioritization
samjhecht
samjhecht
1

researching-web-sources

Strategic web research using WebSearch and WebFetch - finds accurate, relevant information with multiple search angles, prioritizes authoritative sources, synthesizes findings with proper attribution.

web-searchinformation-synthesissource-evaluationattribution
samjhecht
samjhecht
1

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

root-cause-analysispattern-analysishypothesis-testingsystematic-debugging
samjhecht
samjhecht
1

verify-governance

Verify integrity and completeness of governance framework - checks all required files exist, are properly formatted, have current metrics, and align with each other

integrity-checkscompleteness-verificationfile-format-validationmetrics-alignment
samjhecht
samjhecht
1

testing-skills-with-subagents

DEPRECATED - Use writing-skills instead. This skill has been consolidated into writing-skills which now contains both skill creation and testing methodology.

deprecatedskill-consolidationwriting-skills
samjhecht
samjhecht
1

refresh-metrics

Auto-update status metrics across governance documents - scans MCP issues/specs to calculate current counts and percentages, updates README files and NEXT_STEPS with accurate data

auto-updatemetricsdocumentationstatus-tracking
samjhecht
samjhecht
1

design-system-setup

Initialize design systems for projects via Q&A and templates, with auto-detection when missing

design-systemproject-setuptemplatesauto-detection
samjhecht
samjhecht
1

worktree-isolation

Use when implementing features in git worktrees to ensure all changes stay in the correct worktree - prevents "bleeding" of changes back to main branch

gitworktreesbranch-managementcode-isolation
samjhecht
samjhecht
1

testing-anti-patterns

Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies

mockingtest-smellstest-isolationcode-quality
samjhecht
samjhecht
1

dependency-opportunity-scanner

Scan codebase to identify opportunities to replace custom implementations with well-maintained open source libraries. Creates worktree, implements changes, and submits PR for review. Multi-phase workflow with parallel analysis agents.

dependency-analysiscodebase-analysisopen-sourceautomation
samjhecht
samjhecht
1

using-wrangler

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

workflow-automationtask-toolstructured-workflowbrainstorming
samjhecht
samjhecht
1

initialize-governance

Initialize complete governance framework in a project - creates constitution, roadmap, directory READMEs, and issue/spec templates with guided setup process

governance-frameworksproject-setupdocumentationtemplates
samjhecht
samjhecht
1

reviewing-implementation-progress

Reviews in-progress implementation against feature specification and plan - provides structured compliance report with categorized issues for fixing. Mid-implementation checkpoint for quality.

implementationcompliance-reportquality-checkpointissue-categorization
samjhecht
samjhecht
1

brainstorming

Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation

socratic-questioningidea-evaluationincremental-validationalternative-exploration
samjhecht
samjhecht
1

finding-code-patterns

Finds similar implementations, usage examples, and existing patterns in the codebase - shows concrete code examples for modeling new work. Pattern librarian documenting what exists without judgment.

code-searchpattern-librarycode-examplescodebase-analysis
samjhecht
samjhecht
1

constitution

Develop, refine, and maintain project constitutional principles - uses Socratic questioning to eliminate ambiguity and ensure perfect clarity on design values and non-negotiables

socratic-dialogueclarity-adjustmentdesign-decisionsproject-guidelines
samjhecht
samjhecht
1

readme-generator

Generate and improve README files for software projects. Triggers on: 'create readme', 'generate readme', 'write readme', 'improve readme', 'update readme', 'fix readme', 'readme for this project'. Supports Rust (libraries, CLI tools, services), TypeScript/JavaScript (npm packages), and Python (PyPI packages). Applies ecosystem-specific conventions: badges, installation sections, MSRV for Rust, feature flags documentation.

readmedocumentation-generationecosystem-conventionsrust
bug-ops
bug-ops
1

AILANG Debug

Debug AILANG code errors. Use when you encounter type errors, parse errors, or runtime failures in AILANG programs.

debuggingtype-errorsruntime-failureparse-errors
sunholo-data
sunholo-data
1

AILANG Inbox

Cross-agent communication system with semantic search and GitHub sync. Check messages, find similar content, deduplicate, and sync with GitHub Issues for AI workflows across sessions.

cross-agent-communicationsemantic-searchgithub-syncworkflow-automation
sunholo-data
sunholo-data
1

AILANG

Write AILANG code. ALWAYS run 'ailang prompt' first - it contains the current syntax rules and templates.

domain-specific-languagesyntax-rulescode-generationprompt-engineering
sunholo-data
sunholo-data
1

consulting-agents

Use when you need information you don't have, expertise outside your comfort zone, or fresh eyes on code - dispatches agents to research, advise, or review. NOT for implementation delegation (see subagent-driven-development).

autonomous-agentresearchadvisingcode-review
snits
snits
12

tracking-technical-debt

Use when you notice code problems while working on something else - links code markers to beads so issues don't get lost. Triggers on "I see a problem but can't fix it now."

technical-debtcode-smellissue-trackingcode-markers
snits
snits
12

spawning-agents-on-the-command-line

Use when subagents need to delegate work but can't use Task tool, or when needing to test skills in isolated context - spawns Claude instances via CLI backgrounding with JSON responses

spawningclibackground-processingjson
snits
snits
12

domain-review-before-implementation

BEFORE dispatching any implementation agent or starting to code - if you're about to write "Task(subagent_type=..., prompt=...)" for implementation, or about to implement a plan yourself, STOP and review first. The prompt you're about to send IS a brief - review it for design flaws before the agent implements garbage.

developer-guidanceimplementation-workflowcritical-thinkingquality-assurance
snits
snits
12

skill-builder

Build efficient, scalable Claude Code skills using progressive disclosure and token optimization. Use when creating new skills, optimizing existing skills, or learning skill development patterns. Provides templates, checklists, and working examples.

progressive-disclosuretoken-optimizationtemplateschecklists
resolve-io
resolve-io
11

jira

Jira integration for fetching issue context (Epics, Stories, Bugs) to enhance development workflows. Use for automatic issue detection, retrieving ticket details, acceptance criteria, and linked dependencies.

jiraissue-trackingacceptance-criteriaworkflow-automation
resolve-io
resolve-io
11

hooks-manager

Manage Claude Code hooks for workflow automation. Create, configure, test, and debug hooks that execute at various lifecycle points. Supports all hook events (PreToolUse, PostToolUse, SessionStart, etc.) with examples and best practices.

workflow-automationhook-systemclaude-codetesting
resolve-io
resolve-io
11

agent-builder

Create custom Claude Code sub-agents with specialized expertise and tool access. Use when you need to build reusable agents for specific tasks like code review, debugging, data analysis, or domain-specific workflows.

agent-frameworkagent-builderreusable-agentsworkflow-automation
resolve-io
resolve-io
11

context-memory

Python utility API for storing and retrieving project context in Obsidian vault markdown notes

pythonapiobsidianmarkdown
resolve-io
resolve-io
11

mental-saccade-execution

Execute rapid attention shifts between cognitive focus points.

attention-mechanicsmental-processingcognitive-focusrapid-shifting
starwreckntx
starwreckntx
1

enforce-security-vigilance

Enforce continuous security vigilance and threat monitoring.

threat-monitoringcontinuous-vigilancesecurity-enforcementsecurity-policies
starwreckntx
starwreckntx
1

engine-superpower-profiling

Profile AI engine superpowers and capability boundaries.

capability-assessmentengine-profilingsuperpowers
starwreckntx
starwreckntx
1

axiom-injection-methodology

Inject axioms into operational context using structured methodology.

formal-methodsaxiomsstructured-methodologyoperational-context
starwreckntx
starwreckntx
1

aegis-protocol-ratification

Ratify AEGIS protocol governance frameworks.

aegis-protocolratificationgovernancepolicy-approval
starwreckntx
starwreckntx
1

Page 334 of 412 · 20554 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.