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: Files & storage
4,446 results · page 64 of 149
- View details
orca-ircSkillFiles & storage
Generate ORCA input files for IRC (Intrinsic Reaction Coordinate) calculations and post-process the results. Use this skill whenever the user asks about IRC calculations, reaction path following, confirming transition state connectivity, or tracing a minimum energy path from a TS in ORCA. Also trigg
Ready to connect★ 198
- View details
orca-uv-visSkillFiles & storage
Generate ORCA input files for TD-DFT UV-Vis calculations and parse/plot the resulting absorption spectrum. Use when the user asks about UV-Vis spectra, absorption spectra, TD-DFT calculations, excited state calculations in ORCA, or wants to plot results from an ORCA TD-DFT output file. Also trigger
Ready to connect★ 198
- View details
humanizerSkillFiles & storage
Detects characteristic AI-generated patterns in Korean text and converts it into natural human writing. Based on scientific linguistics research (KatFishNet paper, 94.88% AUC accuracy). Analyzes 40 patterns with S1/S2/S3 severity levels, including excessive commas, rigid spacing, part-of-speech dive
Ready to connect★ 196
- View details
leadSkillFiles & storage
Use when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with one pull request. The Lead is a provider-neutral orchestrator that makes decisions but never writes code, edits files, runs commands, or review
Ready to connect★ 197
- View details
libreoffice-calcSkillFiles & storage
How to programmatically create, modify, and verify LibreOffice Calc (.xlsx) files using Python openpyxl. For setup-gen and reward-gen agents.
Ready to connect★ 197
- View details
libreoffice-impressSkillFiles & storage
How to programmatically create, modify, and verify LibreOffice Impress (.pptx) files using Python python-pptx. For setup-gen and reward-gen agents.
Ready to connect★ 197
- View details
libreoffice-writerSkillFiles & storage
How to programmatically create, modify, and verify LibreOffice Writer (.docx) files using Python python-docx. For setup-gen and reward-gen agents.
Ready to connect★ 197
- View details
openshotSkillFiles & storage
How to programmatically set up, manipulate, and verify OpenShot Video Editor project state using Python (JSON .osp files, libopenshot API, FFmpeg/FFprobe, OpenCV). For setup-gen and reward-gen agents.
Ready to connect★ 197
- View details
osSkillFiles & storage
How to programmatically set up, modify, and verify OS-level configurations (files, GNOME settings, audio, permissions, system config) using Python. For setup-gen and reward-gen agents.
Ready to connect★ 197
- View details
vs-codeSkillFiles & storage
How to programmatically configure, modify, and verify VSCode settings, keybindings, extensions, and workspace files using Python. For setup-gen and reward-gen agents.
Ready to connect★ 197
- View details
ops-add-new-chainSkillFiles & storage
Internal — for Boundless team members only. Deploy Boundless infrastructure to a new blockchain. Creates Pulumi stacks, config files, updates ChainId enum, and wires CI/CD pipelines for staging and prod environments. Use when adding a new chain, deploying to a new network, or setting up new chain in
Ready to connect★ 195
- View details
requestingSkillFiles & storage
Submit proof requests on the Boundless ZK proof marketplace. Covers wallet setup, CLI configuration, building or discovering guest programs, self-hosting via Cloudflare Quick Tunnels (no Pinata/S3 needed), submitting, and retrieving results. Use when a developer wants to request a ZK proof, submit a
Ready to connect★ 195
- View details
team-executeSkillFiles & storage
Two-phase Agent Teams execution — replaces the old /team-implement and /team-review skills. Phase 1 IMPLEMENT (formerly /team-implement): parallel implementation with teammates per module/layer, file-ownership separation, and a shared task list with dependencies. Run after /feature plan approval. Ph
Ready to connect★ 195
- View details
hz-platform-sdkSkillFiles & storage
Guides integration of the Horizon Platform SDK for Meta Quest and Horizon OS Android/Kotlin apps — achievements, IAP, users, leaderboards, presence, notifications, abuse reporting, entitlements, asset files, application lifecycle, consent, device integrity, language packs, user age categories, and r
Ready to connect★ 193
- View details
hz-unity-fbx-importSkillFiles & storage
Ensures complete FBX URLs or absolute paths are used when importing external 3D models into Unity projects targeting Meta Quest and Horizon OS. Use when adding FBX files, 3D models, or external assets.
Ready to connect★ 193
- View details
hz-unity-platform-sdkSkillFiles & storage
Guides integration of the Horizon Platform SDK for Meta Quest and Horizon OS Unity/C# apps — achievements, IAP, users, leaderboards, challenges, presence, notifications, abuse reporting, entitlements, asset files, application lifecycle, consent, device integrity, language packs, user age categories,
Ready to connect★ 193
- View details
openclawSkillFiles & storage
Windows Remote MCP Server — 40+ tools for desktop automation, process management, file operations via FastMCP
Ready to connect★ 192
- View details
slay-artifactsSkillFiles & storage
Manage task artifacts (files, folders) via the slay CLI
Ready to connect★ 192
- View details
slay-contextSkillFiles & storage
Ensure root instruction files include SlayZone environment context
Ready to connect★ 192
- View details
ui-systemSkillFiles & storage
Reuse existing UI primitives, CSS vars, and DESIGN.md patterns instead of inventing new buttons, colors, borders, shadows, or helpers — including when implementing a Figma file, mock, or screenshot. Use for Desktop/web/TUI UI work, redesigns, or when the user mentions shared primitives, tw4, Figma,
Ready to connect★ 192
- View details
skill-forgeSkillFiles & storage
Create a new Lattice skill — atom, molecule, or refiner — following all framework conventions. Writing skill files manually almost always produces convention violations: wrong section order, missing confirmation gates, defaults.md without the right structure. This skill knows all of that and guides
Ready to connect★ 190
- View details
skill-validateSkillFiles & storage
Validate any Lattice SKILL.md against all tier conventions — atoms, molecules, and refiners. Catches structural errors, broken cross-references, and convention violations before they reach the repo. If you just wrote or modified a Lattice skill file and haven't run this yet, run it now — manual revi
Ready to connect★ 190
- View details
merge-prepSkillFiles & storage
Pre-merge analysis and preparation. Analyzes source branch vs target branch: commit stats, conflict detection, file impact. Analysis-only v1 — outputs report + suggested commands, does not auto-merge. Use when: user says 'merge prep', 'pre-merge', 'merge analysis', or /merge-prep
Ready to connect★ 188
- View details
plan-reviewSkillFiles & storage
Pre-ExitPlanMode adversarial plan review loop via Codex MCP. Use when: in plan mode, before presenting a plan to the user; reviewing an in-context plan draft. Not for: .md file review (use doc-review), code review (use codex-code-review), lifecycle spec review (use review-spec). Output: review trail
Ready to connect★ 188
- View details
post-dev-testSkillFiles & storage
Post-development test completion. Use when: checking test coverage after feature-dev, writing missing integration/e2e tests. Not for: unit test generation (use codex-test-gen), test review (use test-review). Output: test files + coverage report.
Ready to connect★ 188
- View details
repo-intakeSkillFiles & storage
Project initialization inventory (one-time). Use when: first onboarding a project, rebuilding cache after structural changes. Not for: day-to-day development (read cache directly), finding specific files (use code-explore). Output: project map with entrypoints + test map + next steps.
Ready to connect★ 188
- View details
shopify-admin-customer-timeline-exportSkillFiles & storage
Read-only: exports a complete chronological history for a single customer — orders, refunds, returns, addresses, notes, tags, marketing consent, and lifetime spend — as one consolidated CSV.
Ready to connect★ 188
- View details
shopify-admin-file-storage-auditSkillFiles & storage
Read-only: lists every file in CDN storage, cross-references usage on products, pages, and articles, and flags orphaned/unreferenced assets.
Ready to connect★ 188
- View details
instruction-tuningSkillFiles & storage
Use sub-agents as test subjects to iteratively improve .claude/ instruction files. Run agent → inspect → fix instructions → re-run until agents follow the protocol correctly without hints.
Ready to connect★ 187
- View details
code-engineeringSkillFiles & storage
Invoke when a system prompt targets a Coding Agent scenario. Suitable for building system prompts for code editing, file operations, Git workflows, and automated coding assistants. Not for code explanation or teaching scenarios (no file modification), not for DevOps infrastructure configuration (not
Ready to connect★ 186
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.
54,764 of the 55,196 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.