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: Productivity
2,697 results · page 77 of 90
- View details
resumeSkillProductivity
Resume a paused, interrupted, or crashed RePPITS workflow by reconstructing state from tasks. Use when continuing prior workflow work after a break.
Ready to connect
- View details
test-apiSkillProductivity
Use when running QA / regression tests against PuPu, when verifying a code change actually works in the running app, or when reading PuPu UI/state without screenshotting manually. Triggers on tasks like \"test that PuPu still creates chats correctly\", \"verify the new model selector works end-to-en
Ready to connect
- View details
aweskillSkillProductivity
Use when managing aweskill store, bundle, and agent workflows that are not repair-first: routine commands, bundle template work, multi-agent or multi-scope projection planning, recover flows, skill migration, install/remove/configure tasks. 中文触发词：技能管理、导入技能、投影技能、启用/禁用技能、安装/移除技能、bundle、agent、aweskill、
Ready to connect
- View details
devSkillProductivity
Implement features, fix bugs, and keep the codebase healthy and maintainable. Works from a defined PBI, issue, or task description.
Ready to connect
- View details
ecoSkillProductivity
Token-frugal mode - minimize token consumption (concise replies, lean tool use, cheap delegation) at full task quality. Use when the user mentions tokens, cost, budget, quota, or economical operation, in any language. Invoke once; applies for the rest of the session. "/eco setup" configures permanen
Ready to connect
- View details
eco-maxSkillProductivity
Maximum-savings variant of /eco - the same frugality rules PLUS a low reasoning-effort override for the invoked task. Use for routine chores (rename, small fix, quick question, boilerplate) when the user wants absolute minimum token spend; prefer plain /eco for hard or high-stakes work. Works in any
Ready to connect
- View details
glmSkillProductivity
Run Claude Code against the z.ai GLM models with the measured, working parameters — one-shot `-p` calls, batch loops, or an interactive session. Use when the user asks to run something on GLM, on a non-Anthropic model, or to compare models on the same task (an A/B run), and when a GLM run behaves st
Ready to connect
- View details
knowledge-graphSkillProductivity
Build and maintain the project's knowledge graph — a tiered set of nodes under docs/graph/ that lets an agent load only the few facts a task needs instead of the whole codebase. Use when adopting a project, when a fact changes, when a node grows too large, or when a task should have matched a node's
Ready to connect
- View details
leadSkillProductivity
Produce written specs and atomic PBIs that an implementation agent can execute independently. Authors specs and Linear issues.
Ready to connect
- View details
molecular-dockingSkillProductivity
Molecular docking pipeline using AutoDock Vina for structure-based drug discovery. Triggers on docking, AutoDock Vina, receptor preparation, ligand preparation, PDBQT, grid box, virtual screening, binding affinity, pose prediction, structure-based virtual screening, "redocking RMSD", "Vina score", "
Ready to connect
- View details
next-taskSkillProductivity
Pick the next task from the Linear backlog with the best speed/value ratio
Ready to connect
- View details
nxSkillProductivity
Nx build system and monorepo tools. Advanced task orchestration, generators, and plugins. Use for complex enterprise monorepos with multiple technologies.
Ready to connect
- View details
prep-for-launchSkillProductivity
Pick a Linear PBI, spec it, assemble it, then hold at the gate with a Boeing list for HITL clearance. Does NOT ship.
Ready to connect
- View details
schema-guided-reasoningSkillProductivity
Schema-Guided Reasoning (SGR) pattern for solving LLM-based tasks using structured output, constrained decoding, and Pydantic models. Use when you need: structured output, JSON schema, reproducible reasoning, testable intermediate steps, or directed model reasoning.
Ready to connect
- View details
action-validatorSkillProductivity
Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
Ready to connect
- View details
beads-workflowSkillProductivity
AI-native issue tracking with Beads. Use when managing work items, tracking issues, or coordinating tasks in multi-agent workflows. Covers bd commands, dependencies, and sync patterns.
Ready to connect
- View details
breezingSkillProductivity
Use when running the full team/breezing flow end-to-end — all tasks with parallel workers. Do NOT load for: single-task implementation, planning, review, release, or setup.
Ready to connect
- View details
context-injectionSkillProductivity
Injects contextual information into prompts using structured templates to improve AI model accuracy, grounding, and task performance.
Ready to connect
- View details
decomposing-tasksSkillProductivity
Break down large tasks into smaller, actionable items. Use when planning sprints, estimating work, or creating implementation plans. Covers task breakdown strategies.
Ready to connect
- View details
dev-lead-routingSkillProductivity
Routes development tasks to the correct language or framework expert agent. Use when user requests code review, implementation, refactoring, or debugging.
Ready to connect
- View details
estimating-workSkillProductivity
Estimate effort for development tasks. Use when planning sprints, roadmaps, or project timelines. Covers story points, relative estimation, and uncertainty.
Ready to connect
- View details
ets-runtime-devSkillProductivity
Plan, implement, review, and validate general ets_runtime changes with a planner/worker/reviewer workflow. Use when working under arkcompiler/ets_runtime, or when handling ets_runtime feature work, bug fixes, refactors, test additions, and compile-validation tasks.
Ready to connect
- View details
harness-evalSkillProductivity
Structured SE task evaluation using 15 benchmark definitions from claude-code-harness research
Ready to connect
- View details
harness-ralph-loopSkillProductivity
Runs iterate-until-pass loops with ralph-worker agents in a worktree. Use when running [ralph]-marked tasks or looping until verify passes.
Ready to connect
- View details
harness-schedule-runSkillProductivity
Use when running Plans.md tasks on a scheduled cadence (fresh context per wake-up, sprint-contract flow, plateau detection, flock guard). Do NOT load for: single-task work (harness-work), planning, review, release.
Ready to connect
- View details
hmos-multidevice-avoid-areasSkillProductivity
Handle HarmonyOS avoid-area adaptation through a declarative scene and resource index. Use when the task involves safe area expansion, status bar or navigation bar avoidance, notch or cutout handling, immersive full-screen layouts, or soft keyboard overlap handling.
Ready to connect
- View details
hmos-multidevice-fold-stateSkillProductivity
Validate and route HarmonyOS foldable-device adaptation tasks (including bi-fold, multi-fold, and special-ratio form factors) through a declarative scene and resource index. Use when the task involves FoldStatus, hover layouts, crease avoidance, fold continuity, multi-fold state mapping (for example
Ready to connect
- View details
hmos-multidevice-hardware-accessSkillProductivity
Handle HarmonyOS hardware-capability adaptation through a declarative scene and resource index. Use when the task involves camera selection, camera rotation/stride/foldable adaptation, sensor availability, canIUse or SysCap checks, hardware fallback strategy, external device access, or multi-device
Ready to connect
- View details
- View details
Meeting SchedulerSkillProductivity
Schedules meetings with internal and external stakeholders by parsing natural language requests, resolving time zones, checking calendar availability, proposing optimal slots, and managing invitations and RSVPs.
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.