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
9,017 results · page 239 of 301
- View details
Restore-Test VerificationSkillAI & models
Whether a backup is actually recoverable rather than merely present: the ranked hierarchy of restore evidence (actual restore performed, full boot/virtualization verification, screenshot verification, spot-check restore drill, no evidence at all), adequate test cadence per data-criticality tier, and
Ready to connect
- View details
- View details
source-evaluationSkillAI & models
Judge whether a source can carry the weight you are about to put on it — trace it upstream to something primary, check its date and version, name who benefits if you believe it, test whether corroboration is actually independent, and cite it so a reader can reopen exactly what you read. Use before r
Ready to connect
- View details
Standards Drift DetectionSkillAI & models
Detecting configuration drift against an established baseline: CIPP standards checks and Best Practice Analyser results, Liongard change detections and inspection timelines, the three conditions that make a diff real drift rather than noise, the signals that separate intentional or authorized change
Ready to connect
- View details
tailwindSkillAI & models
Work inside an existing Tailwind codebase without degrading it — use the project's theme tokens instead of arbitrary values, extend the theme when a token is genuinely missing, extract repetition into components rather than @apply, resolve class conflicts with the project's merge helper, and make da
Ready to connect
- View details
test-strategySkillAI & models
Decide what to test and at which level before any tests get written — enumerate failure modes by consequence, give each one the cheapest level that can actually observe it, and name what is deliberately left uncovered. Use when starting testing on a feature or a codebase, when asked for a test plan
Ready to connect
- View details
visual-verificationSkillAI & models
Prove a UI looks right across every state and viewport it has to survive — enumerate the state matrix, make captures deterministic, compare against a baseline captured the same way, and triage every diff. Use before calling a visual change, a style refactor or a redesign done, when running or trusti
Ready to connect
- View details
webhooksSkillAI & models
Receive or send HTTP webhooks correctly — signature verification on the raw body, fast acknowledgement, deduplication, out-of-order handling, retry and dead-letter behaviour, and the delivery contract a consumer needs. Use when adding or debugging a webhook endpoint, when integrating a provider's ev
Ready to connect
- View details
write-inferencex-blogSkillAI & models
Author an InferenceX benchmark blog post in MDX. Codifies the structure, numeric-verification workflow, frontmatter, MDX components, dashboard links, and FAQ JSON-LD pattern used by published InferenceX posts. Use when asked to draft, write, or scaffold a new blog post comparing GPUs/frameworks/prec
Ready to connect
- View details
ccSkillAI & models
Sync cc-settings with Claude Code and Codex upstreams, update a local install, or migrate a project's CLAUDE.md to AGENTS.md. Triggers "sync with claude code", "update cc-settings", "migrate to agents.md".
Ready to connect
- View details
consolidateSkillAI & models
Audit and prune rules, skills, and learnings to cut context bloat. Triggers "consolidate", "clean up rules", "what's redundant", or degraded agent performance from oversized instructions.
Ready to connect
- View details
dr-initSkillAI & models
Initialize a new Darkroom project from the satus or novus starter. Triggers "new darkroom project", "satus", "novus", "scaffold from starter". Not the native /init, which writes CLAUDE.md.
Ready to connect
- View details
freezeSkillAI & models
Lets your agent lock a big decision for a set number of days so it can't be second-guessed on impulse.
Ready to connect
- View details
h3SkillAI & models
Heavy3 Code Audit - Multi-model code review for coding agents (Sponsored by Heavy3.ai)
Ready to connect
- View details
macos-appkit-bridgeSkillAI & models
macOS SwiftUI-AppKit bridges: implement NSViewRepresentable, NSViewControllerRepresentable, NSWindow, panels, responder chains, or menus only where pure SwiftUI cannot model the behavior.
Ready to connect
- View details
projectSkillAI & models
GitHub Issues as the plan of record; agents read and update them. Auto-invoke on issue-linked branches. Triggers "what's the plan", "project status", "sync with github", "close the issue".
Ready to connect
- View details
review-batchSkillAI & models
Batch-review diffs from several agents with per-change re-entry cards and abridged reading diffs. Triggers "review batch", "what's pending review", "reading diff", or after fanning out several agents.
Ready to connect
- View details
ashrae-baseline-guideSkillAI & models
ASHRAE 90.1 Appendix G baseline system selection criteria. Use when recommending HVAC system types, creating baseline models, or answering questions about ASHRAE 90.1 compliance.
Ready to connect
- View details
attribute-space-typesSkillAI & models
Attribute OpenStudio standards space types (Template/Building Type/Space Type) to conditioned spaces, typically after a gbXML import. Use when a model has geometry but no space types, or when asked to "attribute space types", "assign standards space types", or "run the space type wizard".
Ready to connect
- View details
continuous-improvementSkillAI & models
Protocol for updating skills based on user feedback and root-cause analysis to prevent recurring mistakes. Use this skill when deciding HOW and WHEN to evaluate or update other agent skills.
Ready to connect
- View details
explain-visuallySkillAI & models
Build a self-contained, responsive HTML page that explains a concept, system, change, or decision with accurate writing and diagrams. Use when asked to visualize, diagram, or explain a repository, architecture, specification, pull request, process, or technical idea as an HTML page.
Ready to connect
- View details
foundation-modelingSkillAI & models
Choose and apply a ground heat transfer method — EPW ground temperatures for a fast approximate answer, or EnergyPlus Kiva for real slab-edge heat transfer. Use when a model has no ground temperatures, when slab or basement heat loss matters, or when the user asks about foundations, slabs, basements
Ready to connect
- View details
herdr-issue-coordinatorSkillAI & models
Coordinates a batch of GitHub issues through separate Claude Code sessions running in visible Herdr tabs, with tested pull requests, review loops, and gated merges. Use when the user asks one Claude session to sequence several coding sessions, or to complete a parent issue, milestone, or issue batch
Ready to connect
- View details
measure-authoringSkillAI & models
Create, test, and apply custom OpenStudio measures. Use when user asks to "write a measure", "create a custom measure", "modify the model with Ruby/Python code", or needs logic beyond what existing tools provide.
Ready to connect
- View details
new-buildingSkillAI & models
Create a complete building model from scratch — geometry, envelope, loads, HVAC, weather, and simulation. Use when user wants to "create a building", "build a model", or "start a new model".
Ready to connect
- View details
openstudio-patternsSkillAI & models
OpenStudio model object relationships, tool dependencies, and common error patterns. Use when building or modifying models to ensure correct tool ordering.
Ready to connect
- View details
qaqcSkillAI & models
Run model quality checks before simulation. Use when user asks to "check the model", "validate", "QA/QC", or before running a simulation.
Ready to connect
- View details
refactor-featureSkillAI & models
Autonomous refactoring via spec-driven development. Orchestrates contract tests, batch planning, and incremental implementation with regression checks. Reuses feature-planner and feature-implementer agents.
Ready to connect
- View details
review-exampleSkillAI & models
Example code review skill for Claude Review Automation. Customize this template for your project's review standards.
Ready to connect
- View details
review-followup-exampleSkillAI & models
Example follow-up review skill for Claude Review Automation. Used to verify fixes after initial review.
Ready to connect
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.
55,004 of the 55,435 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.