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
8,868 results · page 220 of 296
- View details
divergeSkillAI & models
Generate 3-5 conceptually distinct approaches labeled by creativity dimension (Novel, Surprising, Diverse, Conventional) and hold for selection instead of implementing the first idea; the --codex mode delegates the brainstorm to a fresh Codex subagent for a clean, unanchored context and hands it the
Ready to connect★ 55
- View details
- View details
external-model-reviewSkillAI & models
external-model-review — Run reproducible independent reviews of plans, architectures, major content, and release candidates through named external models; preserve provenance, verify findings against source, and amend artifacts safely.
Ready to connect★ 57
- View details
fable-orchestrationSkillAI & models
Delegation policy for a multi-model agent stack where the main loop runs on a scarce top-tier model (e.g. Claude Fable) and cheaper/unlimited tiers do the mechanical work. The main loop owns architecture and judgment; sub-agents (Opus) and Codex lanes execute. Load whenever spawning sub-agents (Agen
Ready to connect★ 57
- View details
gptpro-handoffSkillAI & models
Run the research/audit handoff loop between an agentic coding harness and a slow, non-agentic frontier reasoning model (GPT Pro on the ChatGPT web UI, or equivalent) with the codebase pre-loaded as split zip bundles. Author a high-signal prompt, then later take the returned report, verify every find
Ready to connect★ 57
- View details
hermes-agent-skill-authoringSkillAI & models
hermes-agent-skill-authoring — Author in-repo SKILL.md: frontmatter, validator, structure.
Ready to connect★ 57
- View details
hermes-plugin-evaluationSkillAI & models
hermes-plugin-evaluation — Evaluate third-party Hermes Agent plugins before installation: cost, licensing, required services, data flow, dependencies, and setup risk.
Ready to connect★ 57
- View details
hermes-self-evaluationSkillAI & models
hermes-self-evaluation — Use when the user asks to evaluate, audit, or optimize Hermes itself — analyzing session history, skill library, costs, and architecture to identify improvements, automation opportunities, and system optimizations. Covers generating structured analyst prompts for external (s
Ready to connect★ 57
- View details
hermes-session-maintenanceSkillAI & models
hermes-session-maintenance — Maintain Hermes Agent session history: inspect size, export backups, prune old ended sessions, and configure safe auto-prune retention.
Ready to connect★ 57
- View details
hf-model-card-researchSkillAI & models
hf-model-card-research — Pull structured benchmark metadata, download stats, and quality claims from HuggingFace model cards for comparison across model variants.
Ready to connect★ 57
- View details
integration-gateSkillAI & models
IntegrationGate — a mandatory checklist (4 steps) for designing a new tool, agent, detector, or system. Load on triggers: new tool / agent / detector / system / method / integration.
Ready to connect★ 57
- View details
iwe-updateSkillAI & models
Update IWE with change explanations. Agent calls update.sh, parses CHANGELOG, explains what changed, helps adapt updates to user customizations.
Ready to connect★ 57
- View details
local-model-selectionSkillAI & models
local-model-selection — Choose and recommend local LLM models for Hermes Agent — VRAM-tier recommendations, uncensored/abliterated variants, quant selection, model family naming conventions, dual-GPU setups, and auxiliary model selection.
Ready to connect★ 57
- View details
model-committeeSkillAI & models
Run one consequential, contestable decision through a deliberative committee of GPT-5.6 and Claude Opus 5, chaired by opus (default), fable, or sol. Not for factual lookups, brainstorming, routine implementation, independent-coder reliability, or final professional judgment. Use when several options
Ready to connect★ 55
- View details
paper-review-liteSkillAI & models
Run a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistration, and replication readiness. Add --codex for a cross-model pass in which Codex and Claude review independently and verify each other's findings.
Ready to connect★ 55
- View details
re-fp-runtimeSkillAI & models
Functional language runtime reverse engineering (Haskell/OCaml): closure/heap object models, calling conventions, data-flow-first strategy. Trigger words: Haskell reverse engineering, OCaml reverse engineering, GHC RTS, thunk, STG, OCaml runtime, closure, functional artifacts.
Ready to connect★ 57
- View details
re-kernelSkillAI & models
Kernel reverse engineering (cross-platform): Windows drivers (.sys/IRP/SSDT), Linux kernel modules (.ko/ET_REL/LKM/rootkits), macOS KEXT and System Extension/DriverKit, Android GKI/vendor modules, seL4 (capability system), Fuchsia/Zircon (handle model + DFv2 userspace driver framework), FreeBSD (lin
Ready to connect★ 57
- View details
setup-wakatimeSkillAI & models
Set up WakaTime time-tracking for Claude Code and VS Code.
Ready to connect★ 57
- View details
- View details
skill-id # kebab-case, уникален в skills-catalog.yamlSkillAI & models
One line — used in CLAUDE.md system-reminder and the skill catalog.
Ready to connect★ 57
- View details
standards-javascriptSkillAI & models
This skill provides JavaScript coding standards and is automatically loaded for JavaScript projects. It includes modern ES2025 patterns, async handling, and recommended tooling.
Ready to connect★ 57
- View details
standards-kotlinSkillAI & models
Kotlin coding standards for modern applications. Includes naming conventions, coroutines, flows, modern Kotlin 2.3.0 features, and recommended tooling.
Ready to connect★ 57
- View details
standards-pythonSkillAI & models
This skill provides Python coding standards and is automatically loaded for Python projects. It includes naming conventions, best practices, and recommended tooling.
Ready to connect★ 57
- View details
standards-shellSkillAI & models
This skill provides Shell/Bash coding standards and is automatically loaded for shell projects. It includes defensive scripting patterns, best practices, and recommended tooling.
Ready to connect★ 57
- View details
standards-typescriptSkillAI & models
This skill provides TypeScript coding standards and is automatically loaded for TypeScript projects. It includes naming conventions, best practices, and recommended tooling.
Ready to connect★ 57
- View details
text-classificationSkillAI & models
Designs and validates LLM-based text classification for research data — codebook construction, choice of learning regime, model selection and reproducibility, prompt construction, pilot validation against human coding with agreement statistics (kappa, F1), hybrid human-LLM workflows, and reporting m
Ready to connect★ 55
- View details
topic-modelingSkillAI & models
Specifies and diagnoses structural topic models for survey and experimental text — choosing among STM, LDA, and BERTopic, preprocessing decisions and their consequences, prevalence and content formulas with spectral initialization and a recorded seed, selecting the topic count across semantic cohere
Ready to connect★ 55
- View details
vapiSkillAI & models
Build AI voice assistants and phone agents with Vapi. Use this skill when users want to create voice agents, phone bots, IVR systems, outbound calling campaigns, or any voice-based AI application.
Ready to connect★ 57
- View details
<skill-name>SkillAI & models
<One paragraph. WHAT this skill does and WHEN an agent should reach for it. This is the host's activation signal, so be concrete and self-contained — an agent decides whether to load the skill from this text alone.>
Ready to connect★ 56
- View details
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.
53,585 of the 54,017 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.