Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
8,942 results · page 168 of 299
- View details
godot-shader-patternsSkillAI & models
Common Godot 4 shader effect examples, including outlines, pixelation, dissolve, water waves, blur, and more.
Ready to connect★ 104
- View details
godot-spawn-systemSkillAI & models
Godot 4 monster spawn system featuring wave spawning, spawn point management, level-driven configuration, and drop mechanics.
Ready to connect★ 104
- View details
HA Integration DevSkillAI & models
Home Assistant custom integration development in Python. Covers custom_components, DataUpdateCoordinator, config_flow, OAuth2, conversation agent, HACS publishing, device registry, entity platforms, services, repair issues, diagnostics, Bluetooth integrations, and multi-coordinator patterns.
Ready to connect★ 104
- View details
recif-evalSkillAI & models
Run RecIF beam×concurrency eval and FlashRec vs SGLang/vLLM/TRT-LLM baselines. Use when the user asks to 评测, 对照, 压测, matrix, RecIF, recall@32, invalid_rate, run_sglang_flashrec_matrix, bench_sglang_compare, or eval_beam_matrix.
Ready to connect★ 104
- View details
unity-csharp-referenceSkillAI & models
Browse Unity Technologies' official UnityCsReference C# source as a read-only local cache. Use when the user asks about the exact signature, behavior, or internal implementation of a Unity API, when comparing API differences between Unity versions, or when validating LLM-suggested Unity code against
Ready to connect★ 103
- View details
ad-copy-writerSkillAI & models
Generate ad copy variations for Google, Meta, and LinkedIn Ads
Ready to connect★ 102
- View details
agent-integration-testingSkillAI & models
Use when the user requests integration testing, feature validation, or test plan execution
Ready to connect★ 102
- View details
annealSkillAI & models
Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration
Ready to connect★ 102
- View details
bughuntSkillAI & models
Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with subagents, then audit all fixes against repo constraints and target platforms. Runs end-to-end without user interaction.
Ready to connect★ 102
- View details
coordinate-reviewSkillAI & models
Review a Coordinate Agents implementation as the Codex Reviewer. Verify the real commit, diff, tests, validation evidence, and specification without modifying the Implementer's product code.
Ready to connect★ 99
- View details
coordinate-setupSkillAI & models
Discover coding CLIs on the current computer and configure a Coordinate Agents implementation agent. Use for setup, executable checks, registered agents, user-level configuration, and project-over-user precedence.
Ready to connect★ 99
- View details
dataviz-aiSkillAI & models
Generate data visualization charts (line, scatter, bar, stem, fill-between, stackplot, stairs) from natural language descriptions using an LLM-powered matplotlib pipeline. Supports 7 chart types via OpenAI-compatible APIs.
Ready to connect★ 102
- View details
deliverability-checkSkillAI & models
Audit a sending domain's deliverability — SPF, DKIM, DMARC, MX, BIMI, blocklists — with a prioritized fix order
Ready to connect★ 102
- View details
demand-gen-auditSkillAI & models
Google Ads Demand Gen audit — audience strategy, creative format diversity, creative freshness, placements, CPA vs goal
Ready to connect★ 102
- View details
ga4-eventsSkillAI & models
GA4 Event Implementation Reference — complete event taxonomy, parameter lists, implementation patterns (gtag.js, GTM, Measurement Protocol), and validation techniques
Ready to connect★ 102
- View details
ga4-measurement-planSkillAI & models
Build a GA4 measurement plan from a site URL — event taxonomy, parameters, custom dimensions, and key events to mark as conversions
Ready to connect★ 102
- View details
gaql-referenceSkillAI & models
Google Ads Query Language (GAQL) Reference — complete syntax, resource types, fields, operators, date macros, and ready-to-use query patterns
Ready to connect★ 102
- View details
google-ads-auditSkillAI & models
Comprehensive Google Ads account audit — campaign structure, budget pacing, conversion tracking, wasted spend — across every campaign type, ranked by estimated $ impact
Ready to connect★ 102
- View details
google-ads-scriptsSkillAI & models
Google Ads Scripts Reference — JavaScript automation, AdsApp object model, selectors, GAQL queries, 10+ working script patterns, MCC parallel processing, Sheets integration
Ready to connect★ 102
- View details
gtm-auditSkillAI & models
Google Tag Manager container audit — tag health, orphaned and paused tags, duplicate GA4 config, trigger coverage, Consent Mode, naming, workspace hygiene
Ready to connect★ 102
- View details
gtm-setupSkillAI & models
GTM Event Tracking & Setup Reference — dataLayer fundamentals, trigger types, variable types, GA4 tag configuration, debug mode, and best practices
Ready to connect★ 102
- View details
gtm-tracking-planSkillAI & models
Turn a measurement plan into a Google Tag Manager spec — tags, triggers, variables, and copy-paste dataLayer snippets for every event
Ready to connect★ 102
- View details
ideateSkillAI & models
Timeboxed ideation on a topic using propose-and-critique subagent pairs. Use when the user wants to brainstorm, explore ideas, discover features, generate options, or think through possibilities for a specified duration. Triggers on requests like "brainstorm X for 30 minutes", "ideate on X", "spend
Ready to connect★ 102
- View details
landing-page-reviewSkillAI & models
CRO review of a landing page with specific conversion recommendations
Ready to connect★ 102
- View details
lead-qualificationSkillAI & models
Research and qualify business leads against your ICP
Ready to connect★ 102
- View details
linkedin-ads-auditSkillAI & models
Full LinkedIn Ads account audit — campaign structure, targeting, creative performance, spend efficiency
Ready to connect★ 102
- View details
meta-ads-auditSkillAI & models
Meta Ads audit — audience analysis, creative fatigue, budget pacing, lead quality
Ready to connect★ 102
- View details
meta-capiSkillAI & models
Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM, and testing
Ready to connect★ 102
- View details
non-commodity-contentSkillAI & models
Interview the user for specific client stories, anecdotes, refusals, and real numbers — then turn them into non-commodity SEO content Google actually wants to rank. Kills generic listicle output at the source.
Ready to connect★ 102
- View details
selfSkillAI & models
Answer questions about how 'mi' works, write new tools, or modify the harness. Use for "how do you work", "write a tool", "add a tool", "create a tool", "extend yourself", "edit yourself", "what tools do you have", or any introspection/modification of the running agent.
Ready to connect★ 102
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,082 of the 54,514 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.