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
8,992 results · page 198 of 300
- View details
operator-brainSkillAI & models
Use when communicating, deciding, or reporting as a senior operator — 8 behavioral modules from Anthropic's Fable prompting guide. Not capability — pure behavior. Load for user-facing text quality.
Ready to connect★ 75
- View details
product-shotsSkillAI & models
Front-door router for the product-shots ecosystem. Clarifies underspecified visual creation requests through a 4-stage state machine, injects platform visual DNA (Amazon + 7 social platforms) and industry visual DNA (7 industries), enforces a unified Negative Constraints prompt patch, then routes to
Ready to connect★ 76
- View details
real-estate-compliance-rera-guardianSkillAI & models
Expert UAE real estate compliance agent ensuring all brokerage operations, outreach campaigns, property transactions, and marketing materials comply with RERA regulations, DLD requirements, UAE Federal laws, and anti-money laundering standards. The legal immune system of the operation.
Ready to connect★ 76
- View details
reasoningSkillAI & models
Controls oma's reasoning effort level to balance depth, rigor, latency, and token cost.
Ready to connect★ 76
- View details
rocket-fuelSkillAI & models
Runs Fable 5 and OpenAI Codex as co-founders on the Rocket Fuel operating system. Fable is the Visionary (vision, plan, standards, final review); Codex is the Integrator (filters the plan, executes the build, reports). Context-routed, one entry point, four functions: KICKOFF a new project, CLARITY B
Ready to connect★ 76
- View details
simmerSkillAI & models
Runs a goal loop - Codex implements fresh laps while Claude verifies each against a machine-checkable goal, until it passes or the budget runs out. Use only when the user explicitly asks for a loop ("simmer this", "loop until tests pass", "iterate until green") - it creates a branch and checkpoint c
Ready to connect★ 76
- View details
skill-maintainerSkillAI & models
Track upstream drift and sync adapted skill libraries
Ready to connect★ 75
- View details
skill-retrievalSkillAI & models
BM25-based skill retrieval plugin for Hermes Agent. Replaces the full skill list in the system prompt with a names-only compact view (~2K tokens) and injects top-K relevant skill descriptions per turn via BM25 retrieval (~300 tokens). Saves ~9K tokens/turn. Use when system prompt token overhead from
Ready to connect★ 75
- View details
tasteSkillAI & models
Cross-model code review - Codex reviews the diff read-only, then Claude validates every finding against the code before presenting it. Use when the user asks for a review, a second opinion, or a cross-model check. Offer it for large or risky diffs; invoke it directly only when the routing policy is
Ready to connect★ 76
- View details
tdd-specSkillAI & models
Generates or updates highly detailed, machine-readable technical specifications with API contracts, data models, pre-agreed test seams, and ADRs in the /spec/ directory.
Ready to connect★ 76
- View details
wf-reviewSkillAI & models
Review a change with an optional workflow contract using deterministic scope, adaptive cross-model reviewers, verified findings, fixes, and a gate. Use standalone or from wf-impl.
Ready to connect★ 76
- View details
claude-reviewSkillAI & models
Review code changes using Hyperlane monorepo coding standards. Use when reviewing PRs, checking your own changes, or doing self-review before committing.
Ready to connect★ 75
- View details
conjureSkillAI & models
Conjure a experimentalist agent — initialize and launch a new autonomous experiment
Ready to connect★ 75
- View details
distillSkillAI & models
Distill insights from a experimentalist agent's session histories — zero API calls
Ready to connect★ 75
- View details
doc-updateSkillAI & models
Capture-correction workflow: record valuable learnings from the current conversation into CLAUDE.md or the relevant SKILL.md so the same mistake never recurs. Reviews conversation for corrections, new conventions, and doc-reality mismatches; proposes targeted updates confirmed by user before writing
Ready to connect★ 75
- View details
pr-reviewer-agentSkillAI & models
Use when the parent pipeline routes a PR review request. Reads diff and produces a Pydantic ReviewReport.
Ready to connect★ 75
- View details
pr-summarizer-agentSkillAI & models
Use when the pipeline needs to compress reviewer output into a digest. Pure function over ReviewReport.
Ready to connect★ 75
- View details
steerSkillAI & models
Steer a experimentalist agent — review progress and redirect a running experiment
Ready to connect★ 75
- View details
you-discoverSkillAI & models
Route You.com integration planning through the you-discover MCP tool, Docs MCP, and direct API options.
Ready to connect★ 75
- View details
agent-justice-protocolSkillAI & models
Dispute resolution, forensic investigation, and risk assessment for autonomous AI agent transactions. Reconstruct provenance chains, adjudicate fault, generate actuarial risk profiles for agent insurance. The accountability layer of the Agent Trust Stack.
Ready to connect★ 74
- View details
analyzing-insurtech-modelsSkillAI & models
Evaluates insurtech business models with distribution innovation, underwriting technology, and claims automation. Use when analyzing insurtech, evaluating digital insurance, or assessing insurance technology.
Ready to connect★ 74
- View details
- View details
climate-risk-agricultureSkillAI & models
Analyze agricultural climate risk systems for weather impact modeling, crop insurance, drought/flood prediction, soil moisture, and carbon tracking. Use when: 'assess crop climate risk', 'evaluate weather yield models', 'review crop insurance integration', 'audit drought prediction', 'check carbon s
Ready to connect★ 74
- View details
complianceSkillAI & models
Regulatory compliance guidelines for life insurance policy administration transactions. Use when processing address changes (state-change impacts), beneficiary changes (community property, ERISA, minors), or any transaction that may trigger compliance review. Covers NAIC model regulations, state-spe
Ready to connect★ 74
- View details
cyber-insuranceSkillAI & models
USAP agent skill for Cyber Insurance. Assess cyber insurance coverage adequacy, identify coverage gaps, maintain claim-readiness evidence, and support renewal applications.
Ready to connect★ 74
- View details
deepSkillAI & models
Runs an iterative auto-fix loop on a chosen target — review, refactor, or coverage — dispatching the base skill into fresh subagent contexts per iteration, applying fixes automatically without per-change approval, running tests with bisection on failure, and checkpoint-committing until convergence o
Ready to connect★ 74
- View details
evidence-first-engineeringSkillAI & models
Apply evidence-first engineering discipline to any agent-built software project: fact discovery before action, evidence-calibrated status reporting, explicit change boundaries and stage gates, controlled confirmation for risky or external actions, sensitive-information redaction for anything shared
Ready to connect★ 73
- View details
execgo-agent-bridgeSkillAI & models
Route shell, runtime.command, runtime.script, mcp.call, cli.run, or task_graph.submit work through Secbot's ExecGo-backed control tools.
Ready to connect★ 74
- View details
gauntletSkillAI & models
Runs a Gauntlet Loop: turns an ambitious goal and optional quality references into a minimal builder/critic prompt judged against a concrete comparison bar, confirms with the user, then executes it as the lead agent until the output beats the bar or the user stops the run — or emits it as a paste-re
Ready to connect★ 74
- View details
liv-add-itemSkillAI & models
Add a new vault item (Project, Agent, or Chat) to the LivOS tree
Ready to connect★ 74
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.
54,624 of the 55,055 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.