85212 Skills Available

Find awesome
Agent Skills

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

Popular searches

parallel-launch

Use when the request has multiple independent sub-tasks, cross-domain research, or parallelizable file or module work.

OutlineDriven
OutlineDriven
32

optimize

Use when the user asks to optimize something, reduce allocations, or fix a performance regression.

OutlineDriven
OutlineDriven
32

onboard

Use when the user asks to be onboarded, oriented, given a tour, or shown where to start in a repo.

OutlineDriven
OutlineDriven
32

mutual-sync

Use when user, agent, and codebase may hold different pictures of the current state: before substantive work after a gap, or mid-session when parties talk past each other. Triggers: "mutual sync", "sync up", "are we on the same page", stale user claims about the code, refuted agent assumptions.

OutlineDriven
OutlineDriven
32

minimalism-driven

Build the smallest version that fully does the job and makes its intent obvious — the right amount, not the fewest lines. Use when scope creep, speculative abstraction, or unneeded surface is a risk; before adding a helper, wrapper, config key, or dependency; or when the user says "minimal", "DRY this up", or "no gold-plating".

OutlineDriven
OutlineDriven
32

memory-update

Use when the user says save this to memory, or scan this session for memories.

OutlineDriven
OutlineDriven
32

memory-sanitize

Use when sanitizing memory for sharing, redacting PII, or scanning for credentials.

OutlineDriven
OutlineDriven
32

memory-clean

Use when the user asks to audit memory or find stale or duplicate memories.

OutlineDriven
OutlineDriven
32

loop-me

Use when the user wants to design a recurring personal or team workflow: capture loops, write specs in workflows/*.md, and run a stateful askme session until the spec is implementer-ready. Triggers: "loop me", "design a workflow", "automate this recurring task", morning routine, inbox processing.

OutlineDriven
OutlineDriven
32

llm-self-loop

Restructures human-gated workflows into autonomous LLM loops with file-based outputs. Use when a task needs a button click, dashboard check, or human verdict inside its iteration loop.

OutlineDriven
OutlineDriven
32

incremental

Use when a change spans multiple files, or you're about to write a lot of code at once.

OutlineDriven
OutlineDriven
32

improve-architecture

Surface deepening refactors that turn shallow modules into deep ones. Use when the user asks to improve architecture, find refactor candidates, raise testability, or make a codebase more agent-navigable.

OutlineDriven
OutlineDriven
32

ideate

Generate grounded, divergent ideas from the codebase. Use when the user says "let's brainstorm", "what should we build", or "any ideas for".

OutlineDriven
OutlineDriven
32

handoff

Snapshot the current session into a resumable handoff artifact so a cold session, agent, or person continues without replaying context. Use when the user says "write a handoff", "hand off", "snapshot this session", "I'm running low on context", "pause and pack this up for the next session", or "resume this later".

OutlineDriven
OutlineDriven
32

github-triage

Triage GitHub issues. Use when the user wants to triage incoming issues, prepare issues for an autonomous agent, or move an issue between workflow states.

OutlineDriven
OutlineDriven
32

github-solution-research

Find open-source solutions on GitHub. Use when facing a bug, integration failure, dependency issue, unclear API usage, implementation blocker, or tool capability need.

OutlineDriven
OutlineDriven
32

git-branchless

Use when doing multi-commit work, stack edits, rebases, fixups, stacked-PR publishing, or when the user mentions branchless, smartlog, git move, or git undo.

OutlineDriven
OutlineDriven
32

generate-my-taste

Generate a personal taste skill from local evidence and confirmation forks. Use when the user says "generate my taste skill", "make my taste skill", or "derive my taste spine".

OutlineDriven
OutlineDriven
32

frontend-ui

Build user-facing interfaces. Use when creating or modifying components, implementing layouts, managing state, or when the output must look hand-crafted rather than AI-generated.

OutlineDriven
OutlineDriven
32

fix

Use when the user says "fix", "make it pass", or "apply the findings", or hands a verifier failure or bug description.

OutlineDriven
OutlineDriven
32

explore

Explore the codebase to map structure, symbols, and dependencies. Use when the user says "explore", "find where X is", "how does X work in the code", or "map the codebase".

OutlineDriven
OutlineDriven
32

enhance

Audit and tighten agent/plugin surfaces. Use when the user asks to enhance a plugin config, agent definition, skill, or CLAUDE.md.

OutlineDriven
OutlineDriven
32

duet

Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.

OutlineDriven
OutlineDriven
32

drift-detect

Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project.

OutlineDriven
OutlineDriven
32

doubt-driven

Doubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes are high, a claim can't be checked by the type system or compiler, or verifying now is cheaper than debugging later.

OutlineDriven
OutlineDriven
32

spec-driven

Use when starting a new project or feature, requirements are unclear, or the change touches multiple modules and needs a shared spec.

OutlineDriven
OutlineDriven
32

source-driven

Use when writing code against a specific framework or library version, building boilerplate, implementing a framework's recommended pattern (auth, routing, forms, data fetching, state), verifying an API signature before writing framework-specific code from memory, or the user asks for a documented, verified, or "correct" implementation.

OutlineDriven
OutlineDriven
32

resolve-pr-feedback

Use on a GitHub PR when addressing review comments or resolving review threads.

OutlineDriven
OutlineDriven
32

research

Use when researching a named library, framework, SDK, API, or service, or finding a migration guide.

OutlineDriven
OutlineDriven
32

review-fix-grill-loop

Use when the user says "grill my changes" or wants their diff reviewed and fixed iteratively until clean.

OutlineDriven
OutlineDriven
32

audit-project

Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".

OutlineDriven
OutlineDriven
32

atomic-issues-prs

Publish a change-set as atomic GitHub issues or PRs. Use when the user says "atomic PRs" or wants one issue/PR per logical change.

OutlineDriven
OutlineDriven
32

batch-ask-me

Use when the user wants to walk a complex design space round by round: map the decision tree, fire the current frontier as batched single-select questions, and loop until shared understanding is reached. Triggers: multi-fork decisions, ambiguous requirements, unresolved prerequisites, "batch ask me", "clarify the design space".

OutlineDriven
OutlineDriven
32

brainstorm

Explore vague or ambitious ideas into a right-sized requirements-only plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning, not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or platform.

OutlineDriven
OutlineDriven
32

breaking-driven

Demolish bloated code and re-derive it clean, cutting every surface the rebuilt contract does not name. Use for a repo-wide bloat sweep, when patching a subsystem has stopped paying, or when the user says "this whole module is bloated", "rewrite this properly", or "break it and rebuild".

OutlineDriven
OutlineDriven
32

browser-testing

Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.

OutlineDriven
OutlineDriven
32

can-i-help

Route contributors to data-backed contribution opportunities. Use when the user asks "where can I help", "what can I contribute", "find a good first issue", or "what should I work on".

OutlineDriven
OutlineDriven
32

caveman

Switch to a verbosity-reduction response register. Use when the user says "caveman", "compact mode", "less tokens", "be brief", or context-window pressure calls for shorter replies.

OutlineDriven
OutlineDriven
32

ci-cd

Set up or modify CI/CD pipelines and deployment automation. Use when setting up build pipelines, automating quality gates, configuring test runners in CI, or establishing deployment strategies.

OutlineDriven
OutlineDriven
32

cleanup-codebase

Reduce internal duplication, dead code, and ceremony. Use when you spot dead fields, redundant wrappers, or speculative abstractions in code you are already editing.

OutlineDriven
OutlineDriven
32

ai-collab-protocols

Surface in-task AI collaboration protocols one tactic at a time. Use when the user refers to entities by colloquial labels, asks how to structure a Claude workflow, or describes a multi-step workflow without durable URLs.

OutlineDriven
OutlineDriven
32

commit-push-current

Commit working-tree changes and push to the current branch: no branch creation, no branch switch, no PR. Use when asked to push to the branch you are already on, including the default branch.

OutlineDriven
OutlineDriven
32

design

Use when starting UI work, defining palettes or design tokens, or when output looks AI-generic, vibe-coded, or default-framework sloppy.

OutlineDriven
OutlineDriven
32

commit-push-pr

Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.

OutlineDriven
OutlineDriven
32

commit-push

Use when asked to ship/publish commits without opening a PR.

OutlineDriven
OutlineDriven
32

commit

Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate, value-communicating message.

OutlineDriven
OutlineDriven
32

compound

Use when the user says "compound this", after a verified non-trivial outcome that should live in docs/solutions/ or CONCEPTS.md, or when a durable project term needs defining.

OutlineDriven
OutlineDriven
32

contract-driven

Design-by-Contract (DbC). Use when crossing public API boundaries, guarding complex state invariants, or hardening untrusted inputs and integration seams.

OutlineDriven
OutlineDriven
32

debug

Hypothesis-driven debugging. Use when a test fails, a crash or exception occurs, output is wrong, or an intermittent flake has no obvious cause.

OutlineDriven
OutlineDriven
32

deprecate-and-migrate

Use when removing old code, migrating users to a new implementation, or deciding whether to maintain or sunset something.

OutlineDriven
OutlineDriven
32

Page 860 of 1705 · 85212 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.