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
8,942 results · page 167 of 299
- View details
unlimited-powerSkillAI & models
Self-terminating recursive orchestrator. Dispatches waves of subagents until a verifiable done-condition passes or the budget caps. Power with a kill-switch.
Ready to connect★ 108
- View details
vibe-coding-harnessSkillAI & models
QA Agent: checks whether outputs from the other Skills in vibe-coding-kit comply with governance standards. Use this Skill for compliance checks when the user says things like "check the output", "is it compliant", "QA check", "validate the PRD", "check the project spec", or after any Skill complete
Ready to connect★ 109
- View details
vibe-coding-prdSkillAI & models
An "interview-style" requirements Agent: through one-question-one-answer exchanges plus suggestions at decision points, it guides someone who can't articulate their requirements toward a PRD that AI can start working from directly. Use this Skill when the user says things like "I want to build an XX
Ready to connect★ 109
- View details
compozySkillAI & models
Explains Compozy capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and extensions. Use when the user asks how to use Compozy, what commands are available, how the workflow pipeline works, or how to configure a workspace.
Ready to connect★ 108
- View details
family-history-researchSkillAI & models
Provides assistance with planning family history and genealogy research projects.
Ready to connect★ 108
- View details
say-it-straightSkillAI & models
Use only after explicit Codex `$superloopy:say-it-straight` or Claude Code `/superloopy:say-it-straight` invocation to make supplied or requested prose direct, concise, and natural without changing facts or protected text.
Ready to connect★ 108
- View details
superloopy-doctorSkillAI & models
Use when diagnosing Superloopy doctor, install, wrapper, plugin cache, hook bootstrap, bundled agents, marketplace, Codex, Claude Code, stale-version, evidence-floor, or host-wiring health problems.
Ready to connect★ 108
- View details
tlon-workflow-doctorSkillAI & models
Use when setting up a machine for mobile agent work on this repository, when the tlon-workflow skill's prerequisite check fails, or when stim, agent-device, gh, or their skills are missing, outdated, or installed under an old name.
Ready to connect★ 108
- View details
fcp-mcp-serverSkillAI & models
MCP server for Final Cut Pro XML. Lets Claude read, edit and generate real timelines: cut detection, markers, roles, transcript-based editing. Published on PyPI as fcp-mcp-server.
Ready to connect★ 107
- View details
configure-agent-pr-attestationSkillAI & models
Use when asked to set up PR attestation, install harness-scs attestation hook, configure agent attestor, troubleshoot why agent attestation isn't uploading, or reconfigure an existing attestation hook (different SCM, new cosign key, updated Harness identity). Trigger phrases: set up PR attestation,
Ready to connect★ 106
- View details
fable-modeSkillAI & models
A work-discipline protocol that makes Opus 4.8 (or any non-frontier model) operate at Fable-5-grade quality. Core idea — output quality = model capability x work discipline: spend extra orchestration to buy single-pass quality via six levers (plan gate, small-card execution, adversarial self-check,
Ready to connect★ 106
- View details
sync-parity-workerSkillAI & models
Extends ADE desktop sync contracts, shared payloads, and iOS models/services when tab parity requires backend work
Ready to connect★ 106
- View details
anchor-vizSkillAI & models
Draw a faithful architecture or structure diagram of a real codebase or project by scanning the actual repo, never guessing. Use for system architecture, request lifecycle, data model, state transitions, type structure, draw the architecture, map this project, 画架构图.
Ready to connect★ 105
- View details
generate-ideaSkillAI & models
Generate and rank research ideas given a broad direction. Use when user input "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
Ready to connect★ 105
- View details
generate-reportSkillAI & models
Consolidates literature review, idea discovery, refined proposal, experiment plan, experiment results, and automated review into a single NARRATIVE_REPORT.md that is rich enough to drive the downstream paper-writing-pipeline (paper-plan → paper-figure-generate → paper-draft → paper-review-loop → pap
Ready to connect★ 105
- View details
lit-reviewSkillAI & models
Retrieves papers from local folder or ArXiv and Semantic Scholar using domain-aware keyword expansion, builds synthesis matrix, identifies gaps. Calls tools/arxiv_fetch.py and tools/semantic_scholar_fetch.py. Writes to output/paper-cache/ and output/LIT_REVIEW_REPORT.md.
Ready to connect★ 105
- View details
paper-review-loopSkillAI & models
Reviews the manuscript produced by `paper-draft` (in `output/manuscript/`) as a demanding IJGIS / ISPRS JPRS reviewer-editor, cross-checks it against `output/PAPER_PLAN.md` and its evidence artifacts, then revises it into a stronger draft. Produces a reviewed manuscript, a revised manuscript, a stru
Ready to connect★ 105
- View details
pr-checklistSkillAI & models
Pre-PR review checklist for the claude-code-gui-jetbrains project. Verifies a change is ready to open a pull request against main — rebased onto the latest main, feature docs written for feature PRs, no marketplace-forbidden Internal/ Deprecated JetBrains APIs, all three test layers passing, the pro
Ready to connect★ 105
- View details
spatial-analysisSkillAI & models
Guideline-driven spatial analysis skill. Given a research question and data context, provides decision frameworks for selecting appropriate spatial methods, diagnostics, and interpretation strategies. Adapts to available data, spatial units, and analytical objectives — Claude Code determines the opt
Ready to connect★ 105
- View details
submit-checkSkillAI & models
Validates a manuscript against target journal requirements before submission. Checks word count, section structure, figure/table count, reference format, and geo-specific reporting standards. Writes a PASS/FAIL checklist report to output/reports/.
Ready to connect★ 105
- View details
WritingSkillAI & models
Iterative critique and improvement of long-form content (guidebooks, playbooks, essays). Launches parallel judge subagents for multi-dimensional critique, synthesizes findings, presents proposals for user approval. Never edits without consent.
Ready to connect★ 105
- View details
add-modelSkillAI & models
Integrate a new model architecture into the FlashRec engine (new HF checkpoint / non-Qwen3 structure). Covers model definition, weight merging and loading, FP8 dual paths, fused kernel wiring, CUDA graph compatibility, precision validation, and a closed loop of stress testing plus trace verification
Ready to connect★ 104
- View details
execution-self-checkSkillAI & models
Pre-submit self-check — must run before the envelope is submitted to the commit gate. An independent OPUS fork evaluates each blocking check (the checklist is injected via the dispatch prompt); the executor cannot self-assess (athletes don't referee themselves).
Ready to connect★ 104
- View details
godot-autoload-patternsSkillAI & models
Best practices for Godot 4 Autoload singleton patterns, covering global managers, event buses, and signal communication.
Ready to connect★ 104
- View details
godot-buff-systemSkillAI & models
A complete Buff system implementation for Godot 4, supporting status effect management, durations, looping effects, stacking mechanics, and more. Uses a Resource+Component architecture.
Ready to connect★ 104
- View details
godot-building-systemSkillAI & models
Godot 4 building system implementation, including GridMap block management, first-person view, and raycast interaction.
Ready to connect★ 104
- View details
godot-interactive-systemSkillAI & models
Godot 4 可交互组件设计，包含InteractiveComponent代理组件、NPC对话、区域触发。
Ready to connect★ 104
- View details
godot-navigation-systemSkillAI & models
NavigationAgent2D usage, AStarGrid2D algorithm, custom A* implementation, flow-field pathfinding, and performance optimization. For scenarios such as 2D/3D navigation systems, dynamic obstacle avoidance, and game AI navigation.
Ready to connect★ 104
- View details
godot-online-multiplayerSkillAI & models
Core multiplayer game patterns for Godot 4, including scene management, player lifecycle, and death/respawn mechanics.
Ready to connect★ 104
- View details
godot-shader-fundamentalsSkillAI & models
Godot 4 shader fundamentals: syntax and math, covering the type system, Uniform variables, built-in functions, and practical tips.
Ready to connect★ 104
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.
54,082 of the 54,514 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.