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
8,898 results · page 287 of 297
- View details
go-concurrency-patternsSkillAI & models
Teaches your agent Go concurrency patterns like goroutines, channels, and worker pools when writing or debugging Go code.
Ready to connect
- View details
hermes-tweetSkillAI & models
Use Hermes Tweet with Hermes Agent for X/Twitter endpoint discovery, public reads, private action-gated reads, audience analysis, thread planning, and guarded publishing. Use when a project needs Hermes-native social research or publishing workflows.
Ready to connect
- View details
holochainSkillAI & models
Holochain hApp development assistant covering coordinator/integrity zome architecture, Rust HDK/HDI patterns, entry/link types, CRUD, validation, cross-zome calls, Sweettest testing, TypeScript client integration, DNA migration and init properties, and Nix dev environments. USE WHEN writing zome cod
Ready to connect
- View details
hundred-minds-collectiveSkillAI & models
Triggered when the agent needs to solve complex, multi-faceted problems by simulating the collective intelligence of 100 specialized minds divided into 6 functional teams (Strategy, Domain Experts, Red Team, Empirical Testers, Consensus Council, and Execution Ops) within a single agent session.
Ready to connect
- View details
Inversion ExerciseSkillAI & models
Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"
Ready to connect
- View details
lab_interpreterSkillAI & models
Use this skill when the user shares lab test values (血常规, 血生化, 甲功, 凝血 etc.) and asks what they mean, whether they are normal, or what action to take. Triggered by phrases like "帮我看看化验单", "我的血红蛋白偏低是什么意思", "这个指标正常吗". Primarily used by report_agent; also available to clinic_agent when symptoms co-occur
Ready to connect
- View details
library-quality-auditSkillAI & models
RAG-backed. Audit DipTrace component and pattern libraries for pin, pad, mapping, geometry, and identity defects without mutating native libraries. Use when the user says “Audit these DipTrace component and pattern libraries.”
Ready to connect
- View details
lofn-orchestrationSkillAI & models
Orchestrate Lofn panels, metaprompts, assignments, and multi-agent creative pipeline handoffs. Use after core seed/research exists. Do NOT use for QA cleanup, direct song generation, or final scoring.
Ready to connect
- View details
market-sizing-analysisSkillAI & models
Lets your agent calculate market sizes like TAM, SAM, and SOM for a startup idea.
Ready to connect
- View details
medication_calculatorSkillAI & models
Use this skill when the user asks about medication dosing, how much of a drug to take based on their weight or age, or when a pharmacy_agent or clinic_agent needs to verify safe dosage ranges. Triggered by phrases like "我体重60公斤该吃多少剂量", "儿童用量怎么算", "这个药的最大剂量是多少", or "按体重算应该用多少". Supports weight-based
Ready to connect
- View details
Meta-Pattern RecognitionSkillAI & models
Spot patterns appearing in 3+ domains to find universal principles
Ready to connect
- View details
migration-refactor-specialistSkillAI & models
Skill for migrations, legacy modernization, and structural refactors. Use when you need to perform major upgrades, incremental extraction, strangler pattern, transition compatibility, and safe rollout. Triggers on: "migracao de framework", "modernizacao de legacy", "strangler pattern", "refactor est
Ready to connect
- View details
mobile-tauriSkillAI & models
Optional skill for the Mobile/Desktop Developer to create native apps using Tauri v2. Use when you need to generate an Android APK, a Windows/macOS/Linux executable, or adapt a web frontend to native platforms. Trigger words: "mobile", "Tauri", "APK", "app nativo", "desktop app", "Windows app", "mac
Ready to connect
- View details
model-delegationSkillAI & models
Apply when deciding whether to implement in-session or delegate, and when writing a delegation prompt. Esposter model-delegation conventions — the main session does all thinking (specs, proposals, architecture, review); mechanical implementation is delegated to background subagents with self-contain
Ready to connect
- View details
model-registry-refreshSkillAI & models
Re-verify and extend catalog/model-registry.json — the fail-closed model-name and reasoning-effort matrix scripts/model-policy.mjs validates against — via delegated Context7-backed research, orchestrator-owned registry edits, and the full validation chain; use when a policy check fails on an unregis
Ready to connect
- View details
oc-resumeSkillAI & models
Resume ClawedBack after a restart. Starts the web server, resumes polling, and rebuilds config if missing. Use when starting a new Claude session in an existing ClawedBack install, or when the user says 'resume', 'start', 'restart', 'begin polling', or 'oc-resume'.
Ready to connect
- View details
opencodeSkillAI & models
Invoke OpenCode CLI as a sub-agent to leverage alternative AI models (GPT-5.x, Codex, local models) for code implementation, review, debugging, research, and second opinions. Use when the user asks to "use opencode", "get a second opinion from GPT/Codex", "implement with opencode", "review with open
Ready to connect
- View details
paraphrasing-expertSkillAI & models
Critical paraphrasing skills to restate text in original words while preserving meaning, avoiding plagiarism, and adapting tone across academic, professional, and popular contexts.
Ready to connect
- View details
persona-driven-issue-auditSkillAI & models
Skill for bulk auditing via simulated personas: infers proto-personas from the repository, confirms with the human without blocking, and runs up to the PR — finds bugs, opens issues with dedup, an analyst comments on the solution, a parallel fleet opens a PR where confidence is high or comments wont
Ready to connect
- View details
plan-synthesizeSkillAI & models
Synthesize competing plans from multiple frontier models into a single best-of-all-worlds hybrid. Use after /plan has produced 2+ competing plans in .flywheel/plans/.
Ready to connect
- View details
Preserving Productive TensionsSkillAI & models
Recognize when disagreements reveal valuable context, preserve multiple valid approaches instead of forcing premature resolution
Ready to connect
- View details
prompt-auditSkillAI & models
Audit a prompt the user is about to send to Claude (or another coding AI) for completeness and effectiveness. Use this skill whenever the user shares a prompt and asks for feedback — phrases like "is this prompt good", "audit my prompt", "review this prompt", "will Claude understand this", "improve
Ready to connect
- View details
querySkillAI & models
Query integrated indexes using text with Pinecone MCP. IMPORTANT - This skill ONLY works with integrated indexes (indexes with built-in Pinecone embedding models like multilingual-e5-large). For standard indexes or advanced vector operations, use the CLI skill instead. Requires PINECONE_API_KEY envi
Ready to connect
- View details
reality-checkSkillAI & models
Break the spell of local productivity. Ask whether completing all open beads actually closes the gap to the project goal. Use at milestones or when busy agents feel directionally off.
Ready to connect
- View details
research-prepSkillAI & models
Collects and organizes multi-source technical information before writing docs, PRDs, ADRs, or articles. Searches: official docs, GitHub (repos + issues), Stack Overflow, papers, and reference blogs. Ranks sources by authority (official 40% + recency 30% + depth 20% + community 10%). Output: mem
Ready to connect
- View details
responsive-conversionSkillAI & models
Skill for converting web interfaces to mobile and fixing broken layouts. Use when a component doesn't take up 100% of the width, gets cut off mid-screen, breaks on small screens, has unintended horizontal scrolling, a modal overflowing the viewport, or when you need to define confirmation standards
Ready to connect
- View details
revenue-recognition-advisorSkillAI & models
Apply the ASC 606 / IFRS 15 five-step revenue recognition model to described arrangements. Provides the complete five-step framework with paragraph citations, judgment-area reference tables, confidence-scoring guidance, common restatement triggers, GAAP/IFRS delta checklist, and official documentati
Ready to connect
- View details
schematic-erc-reviewSkillAI & models
RAG-backed. Review a DipTrace schematic with bounded ERC, logical connectivity, metadata, and BOM checks before layout. Use when the user says “Review this DipTrace schematic before layout.”
Ready to connect
- View details
session-summarySkillAI & models
Session summary skill for handoff between sessions. Consolidates what was done, decisions made, artifacts produced, pending items, and next steps. Facilitates continuity without losing context. Trigger words: "resumo", "summary", "o que foi feito", "handoff retrospectivo", "encerrar sessão", "salvar
Ready to connect
- View details
signal-integrity-reviewSkillAI & models
RAG-backed. Review DipTrace PCB impedance, stackup, routed geometry, return paths, and configured external-solver evidence without inventing targets. Use when the user says “Review impedance and return-path evidence for these PCB nets.”
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.
53,789 of the 54,221 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.