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.
Filter by category
70,704 results · page 683 of 2,357
- View details
attribution-modelSkillDocs & knowledge
Lets your agent design a multi-touch attribution strategy with credit rules, setup steps, and tracking gaps.
Ready to connect★ 1k
- View details
attribution-reportSkillProductivity
Lets your agent run multi-touch attribution analysis comparing models to compute per-channel revenue and ROAS.
Ready to connect★ 1k
- View details
audience-intelligenceSkillAI & models
Lets your agent build detailed buyer personas, segmentation models, and buying-committee maps for audience research.
Ready to connect★ 1k
- View details
audience-profileSkillDocs & knowledge
Lets your agent create detailed buyer persona documents with demographics, motivations, and buyer journey maps.
Ready to connect★ 1k
- View details
audit-agency-continuitySkillDocs & knowledge
Run a read-only continuity and evidence audit of a persistent or autonomous agent workspace. Use when Codex must assess whether goals, memory, corrections, authority boundaries, commercial claims, schedules, or restart recovery are durable and verifiable; when an agent claims it can continue unatten
Ready to connect★ 1k
- View details
audit-agent-onboardingSkillFiles & storage
Use to lint a repo's agent onboarding files (AGENTS.md, CLAUDE.md, .claude/rules/*.md) for bloat, contradictions, duplication, stale or vague commands, missing sections, leakage, and secrets - or with --stats to view compression receipts. Read-only; reports findings and hands fixes to update-agent-o
Ready to connect★ 1k
- View details
audit-guideSkillDocs & knowledge
Interactive internal audit guide for ISO 9001:2015 and IATF 16949:2016 — walks through key clauses interactively, scores findings as Major NC / Minor NC / OFI, and generates a structured audit report. Use when conducting an internal audit and needing real-time finding documentation and a structured
Ready to connect★ 1k
- View details
audit-searchSkillSearch
Search AxonFlow audit trail for recent tool executions, policy decisions, and compliance evidence
Ready to connect★ 1k
- View details
authorSkillDocs & knowledge
Write a new doc in the right place with the right name. Use when asked to "write a doc", "where should this doc go", "add an ADR", "document this decision", "new spec", or "new feature plan".
Ready to connect★ 1k
- View details
authority-credibilitySkillCommerce & finance
Use when presenting or auditing expertise, credentials, certifications, advisory boards, expert quotes, trust badges, medical claims, legal claims, financial claims, institutional logos, titles, uniforms, or authority signals that could create undue deference.
Ready to connect★ 1k
- View details
autocad-tianzheng-hvacSkillDatabases & data
Use when controlling AutoCAD 2026 with Tianzheng HVAC T30 through the autocad_tianzheng MCP server, including connecting the THvac30V1 profile, reading or creating DWG engineering files, scanning layers/entities/blocks/text into SQLite/JSON/XLSX, running Tianzheng HVAC commands, loading Tianzheng AR
Ready to connect★ 1k
- View details
automation-builderSkillProductivity
Lets your agent run automation tasks inside an active Codex Project Autopilot project according to its plan.
Ready to connect★ 1k
- View details
autonomous-loopSkillDev tools
How Cavekit's autonomous execution loop works — state machine, stop hook, completion sentinel, lock, budgets, iteration cap. Read this skill any time you are about to run /ck:make, debug a stuck session, or write a new command that needs the loop. Trigger phrases: "how does the loop work", "stop hoo
Ready to connect★ 1k
- View details
autonomous-project-orchestratorSkillAI & models
Lets your agent run an autopilot that starts and continues multi-step coding projects on its own.
Ready to connect★ 1k
- View details
autopilot-statusSkillMonitoring & ops
Lets your agent check campaign health scores, auto-correction logs, and which ad campaigns need human attention.
Ready to connect★ 1k
- View details
b2b-reach-engineeringSkillDev tools
Build B2B reach systems that make a defined market aware of the company through named accounts, real buyers, controlled delivery channels, and first-touch saturation. Use when the right market may not know the company exists, outbound gets little signal, brand awareness is vague, the target market i
Ready to connect★ 1k
- View details
b2b-resonance-auditSkillCommunication
Audit and rewrite B2B sales messaging so the right buyers quickly understand the painful problem, concrete outcome, and mechanism behind the offer. Use when buyers see the company but do not remember it, cannot explain what it does, do not connect it to a trigger, or messaging sounds clever, vague,
Ready to connect★ 1k
- View details
b2b-sales-constraint-diagnosisSkillCommunication
Diagnose the single B2B sales constraint currently limiting pipeline or revenue and route to the right repair workflow. Use when sales feels stuck, pipeline is weak, leads ghost, outbound is not working, conversion is unclear, or the team is debating whether to fix reach, messaging, follow-up timing
Ready to connect★ 1k
- View details
b2b-timing-engineSkillMedia
Design recurring B2B buyer-presence systems that keep a company remembered until pain becomes urgent, using time-based visibility cadence instead of unreliable intent signals or linear funnel assumptions. Use when buyers know the company but deals stall, follow-up is inconsistent, the team waits for
Ready to connect★ 1k
- View details
b2b-trust-engineeringSkillDev tools
Engineer B2B buyer trust by reducing perceived risk, stacking relevant proof, simplifying next steps, and designing sales calls to confirm confidence rather than persuade from scratch. Use when qualified buyers take calls, request proposals, start trials, or show interest but then stall, ghost, choo
Ready to connect★ 1k
- View details
babok-analystSkillAI & models
BABOK v3 business analysis agent for IT projects in manufacturing, distribution, and services. Drives a 9-stage pipeline (Stage 0 charter gate + Stages 1–8) with human approval gates, Short Rationale + Evidence methodology, and MCP project lifecycle tools. Use when the user says "BABOK", "begin new
Ready to connect★ 1k
- View details
backend-builderSkillProductivity
Lets your agent run backend claude skill steps inside an approved Codex Project Autopilot plan.
Ready to connect★ 1k
- View details
backend-engineerSkillProductivity
Lets your agent connect an existing UI to a Supabase database, acting as a backend claude skill.
Ready to connect★ 1k
- View details
backlink-gapSkillDev tools
Finds domains linking to competitors but not to you, with ranked prospects and outreach lists.
Ready to connect★ 1k
- View details
backlog-groomingSkillProductivity
Lets your agent review planning tasks, prioritize them, group related work, and promote ready tasks to todo.
Ready to connect★ 1k
- View details
batch-product-researchSkillFiles & storage
Lets your agent research and rank many Amazon keywords in batch, with optional HTML and CSV report files.
Ready to connect★ 1k
- View details
be-seriousSkillDev tools
Use when the user invokes be-serious, $be-serious, or @be-serious; asks for serious scholarly or textbook-grade prose; or wants the current session to avoid slang, sycophancy, emoji, casual tone, marketing language, forced informality, anthropomorphization, or Chinese internet vernacular.
Ready to connect★ 1k
- View details
be-serious-reviewSkillDev tools
Use when the user asks to review, audit, score, repair, or rewrite prose against the be-serious scholarly textbook register; when checking for slang, sycophancy, emoji, casual tone, marketing language, AI tics, or Chinese internet vernacular; or when drafting a formal alternative.
Ready to connect★ 1k
- View details
beta-reader-feedbackSkillDev tools
Plan beta reading rounds for practical nonfiction and turn reader comments, abandonment, confusion, skepticism, and negative feedback into manuscript revisions. Use when recruiting beta readers, preparing reader instructions, synthesizing feedback, deciding whether a book is ready, or improving a dr
Ready to connect★ 1k
- View details
better-auth-integrationSkillSecurity
Guide only for applications using @dodopayments/better-auth, covering authenticated customer sync, checkout, portal access, usage ingestion, and verified webhook callbacks.
Ready to connect★ 1k
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
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.
68,574 of the 70,704 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 workspace 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.