74167 Skills Available

Find awesome
Agent Skills

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

Popular searches

agent-memory

Bootstrap skill that teaches Claude about the shared Agent-memory system for cross-session and cross-team knowledge

KienVu2368
KienVu2368
0

Plan Task (Architectural)

Use when the user asks for a plan or the task is complex/ambiguous. Enforces AGENTS.md workflow and encourages loading other relevant skills.

CheekyCodexConjurer
CheekyCodexConjurer
0

frontend-design-lumina

Design or redesign frontend interfaces in quant-lab with high-quality, production-ready UI/UX while preserving Lumina identity. Use when the user asks for UI polish, visual redesign, page/layout revamp, dashboard/chart UX improvements, interaction quality upgrades, or anti-generic "AI-looking" frontend output.

CheekyCodexConjurer
CheekyCodexConjurer
0

cupertino-ui-consistency

Maintain Cupertino + Lumina visual consistency for the AERA frontend. Use when creating or modifying UI, CSS/tokens, layouts, components, menus/overlays, tables, charts, or interaction states in this repo.

CheekyCodexConjurer
CheekyCodexConjurer
0

Create UI Component

Use this skill when creating a new React UI component. It provides a consistent Lumina-style template.

CheekyCodexConjurer
CheekyCodexConjurer
0

Create Strategy (LEAN)

Use this skill when you need to add a new LEAN QCAlgorithm strategy in Python.

CheekyCodexConjurer
CheekyCodexConjurer
0

skills_auditor

Detect incorrectly installed skills and report issues.

CheekyCodexConjurer
CheekyCodexConjurer
0

size_guard

Enforce line budgets and rotate or split large context files.

CheekyCodexConjurer
CheekyCodexConjurer
0

shadow_coder

Build parallel architectures safely without breaking current behavior.

CheekyCodexConjurer
CheekyCodexConjurer
0

safety_validation

Validate changes against .agentignore before commit.

CheekyCodexConjurer
CheekyCodexConjurer
0

safe_refactor_migration

Plan and execute large refactors with shadow mode and rollback.

CheekyCodexConjurer
CheekyCodexConjurer
0

response_style_selector

Ask the user to pick a response style and persist the preference.

CheekyCodexConjurer
CheekyCodexConjurer
0

repo_indexer

Build and maintain a fast navigation index of the repo.

CheekyCodexConjurer
CheekyCodexConjurer
0

refactor_gate

Ask whether to proceed with refactoring after architecture mapping.

CheekyCodexConjurer
CheekyCodexConjurer
0

quality_gates

Enforce Definition of Done checks from QUALITY_GATES.md.

CheekyCodexConjurer
CheekyCodexConjurer
0

pattern_miner

Extract recurring patterns from action logs and propose automations.

CheekyCodexConjurer
CheekyCodexConjurer
0

non_destructive_bootstrap

Install agent docs without overwriting or deleting existing content.

CheekyCodexConjurer
CheekyCodexConjurer
0

impact_analyzer

Analyze and document the impact of planned changes.

CheekyCodexConjurer
CheekyCodexConjurer
0

handoff_writer

Write a compact HANDOFF.md snapshot to restore context after session resets.

CheekyCodexConjurer
CheekyCodexConjurer
0

full_auth

When explicitly authorized, execute end-to-end with a phased plan in one run until Definition of Done is met.

CheekyCodexConjurer
CheekyCodexConjurer
0

execplan

Create and maintain PLANS.md for long-running or risky tasks.

CheekyCodexConjurer
CheekyCodexConjurer
0

detect_commands

Infer and verify install/test/lint/build commands for the repo.

CheekyCodexConjurer
CheekyCodexConjurer
0

context_compactor

Compress long-run context into handoff, backlog, and action logs.

CheekyCodexConjurer
CheekyCodexConjurer
0

command_guard

Enforce .agentpolicy rules before executing commands.

CheekyCodexConjurer
CheekyCodexConjurer
0

clarify_first

Ask clarifying questions and get approval before implementation.

CheekyCodexConjurer
CheekyCodexConjurer
0

cartographer

Maintain living architecture maps and interaction flows.

CheekyCodexConjurer
CheekyCodexConjurer
0

backlog_curator

Maintain a lightweight backlog of high-value tasks discovered during work.

CheekyCodexConjurer
CheekyCodexConjurer
0

autonomy_kickoff

Run the full autonomy bootstrap with minimal questions.

CheekyCodexConjurer
CheekyCodexConjurer
0

analyze_repo_capabilities

Detect repo tooling and patterns, then record a dynamic manifest.

CheekyCodexConjurer
CheekyCodexConjurer
0

agent_manager

Automatically manage agent lifecycle, proposals, and registry.

CheekyCodexConjurer
CheekyCodexConjurer
0

action_logger

Keep an audit trail of changes, commands, and verification.

CheekyCodexConjurer
CheekyCodexConjurer
0

ast_injection

Use AST-aware edits to reduce syntax errors and maintain structure.

CheekyCodexConjurer
CheekyCodexConjurer
0

archaeologist

Detect legacy patterns and guide compatibility decisions.

CheekyCodexConjurer
CheekyCodexConjurer
0

Verify Changes

Use this skill after implementing code to verify correctness before notifying the user.

CheekyCodexConjurer
CheekyCodexConjurer
0

verify-debug-mode

Confirm a requested feature change via AERA Debug mode (Debug view, console, logs). Use when validation must happen through Debug UI or when you need to add debug-only probes/commands to make a change observable.

CheekyCodexConjurer
CheekyCodexConjurer
0

Sync Documentation

Use this skill at the end of a task to ensure documentation matches the code.

CheekyCodexConjurer
CheekyCodexConjurer
0

Refactor/Slice File

Use this skill when a file exceeds ~350 lines (target) / approaches the 500-line hard cap, or has mixed responsibilities (UI + Logic + Types).

CheekyCodexConjurer
CheekyCodexConjurer
0

Create Backend Service

Use this skill when adding new backend functionality (API endpoints + business logic).

CheekyCodexConjurer
CheekyCodexConjurer
0

Create New Indicator

Use this skill when you need to add a new Python indicator to AERA.

CheekyCodexConjurer
CheekyCodexConjurer
0

skills_sync

Align Codex-native skills with documented skills safely.

CheekyCodexConjurer
CheekyCodexConjurer
0

debug-fix-first-run-resolution

Root-cause debugging and first-run bug fixes with reproduction-first workflow, explicit hypotheses, disciplined instrumentation, minimal changes, and validated fixes (repro + tests + feature verification). Use when diagnosing a bug and delivering a verified fix instead of shotgun debugging.

CheekyCodexConjurer
CheekyCodexConjurer
0

trust_layer_tdd

Enforce test-first changes and debug based on failing tests.

CheekyCodexConjurer
CheekyCodexConjurer
0

update_architecture

Refresh architecture maps after structural changes.

CheekyCodexConjurer
CheekyCodexConjurer
0

update_kit

Update this documentation kit safely from upstream.

CheekyCodexConjurer
CheekyCodexConjurer
0

write_adr

Document architectural decisions with context and consequences.

CheekyCodexConjurer
CheekyCodexConjurer
0

Create Interactive Menu

Use this skill when creating dropdowns, context menus, or overlays that need a polished UX (open/close animation, click-outside, Escape, etc.).

CheekyCodexConjurer
CheekyCodexConjurer
0

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.

Nsttt
Nsttt
0

video-transcript-downloader

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.

Nsttt
Nsttt
0

oracle

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

Nsttt
Nsttt
0

openai-image-gen

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Nsttt
Nsttt
0

Page 1458 of 1484 · 74167 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.