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
2,684 results · page 62 of 90
- View details
lov-add-taskSkillProductivity
Appends items to the current task list by priority and position while preserving existing statuses. Supports explicit input and result read-back. Use to add an item to the current
Ready to connect★ 66
- View details
lov-feedback-loopSkillProductivity
Turns users' passive sentiment toward the Agent as well as active likes, dislikes, and ratings into countable feedback events, iterating at the smallest scope of task, skill, rule, or global Prompt, and generating a satisfaction retrospective report. Use when the user rates a run, asks for satisfact
Ready to connect★ 66
- View details
lov-open-codex-sessionSkillProductivity
Open a target task directly in the Codex main window using a Codex thread UUID, deeplink, or a confirmed retrieval hit. Use for requests like "open this session", "open the Codex session you just found", and open this Codex session.
Ready to connect★ 66
- View details
modelSkillProductivity
Linear programming model layer standards — constraints, costs, decision variables, connection segments, reactive parameter tracking, shadow prices, and the HiGHS solve strategy. Use when working under custom_components/haeo/core/model/, when optimization results look wrong, when the model is infeasi
Ready to connect★ 66
- View details
parallel-workSkillProductivity
Shapes for running many sub-agents at once — fan-out with a barrier, maker/checker, generate-and-filter, tournaments for ranking, hypothesis fan-out for root cause, and loops that stop on a condition with a cap. Use when a phase has several independent targets, when a task is too large or too repeti
Ready to connect★ 66
- View details
planner-rt-icaSkillProductivity
Same reverse-thinking method as dh:rt-ica (see dh:rt-ica or dh-glossary for the definition), but localizes any MISSING input to the affected task only, as a non-blocking information-completeness pre-pass before task decomposition and plan generation. Use when grooming backlog items, generating plans
Ready to connect★ 66
- View details
pm-featureSkillProductivity
Use when: you need to refine feature implementation details, break down complex features, prepare detailed tasks for development, or describe feature points across multiple dimensions. Do NOT use when: the feature is simple enough to go straight into development, or you only need a feature list with
Ready to connect★ 66
- View details
pm-iterationSkillProductivity
Use when: you need to plan iteration content, create iteration schedules, clarify iteration priorities, or turn requirements into a concrete schedule. Do NOT use when: the iteration has already been planned by the team and requires no systematic management.
Ready to connect★ 66
- View details
pm-selfcheckSkillProductivity
Use when: checking super-pm skills health status, performing periodic maintenance audits, or verifying metadata integrity. Do NOT use when: actively using a functional skill or simply executing product management tasks.
Ready to connect★ 66
- View details
pm-user-storySkillProductivity
Use when: requirements need to be turned into user stories, agile development tasks are being prepared, requirements need to be broken down, or acceptance criteria need to be written. Do NOT use when: requirements can go straight into development, or the team does not use the user story format.
Ready to connect★ 66
- View details
praise-before-workSkillProductivity
Implements the user's personal collaboration preference: "praise me before doing any work for me". Before starting a new task, give the user clear, specific praise first, then begin the work. When this Skill is invoked explicitly, deliver a clearly noticeable compliment even if the user only says "h
Ready to connect★ 66
- View details
prepare-walkthrough-presentationSkillProductivity
Transforms validated /linear-walkthrough artifacts into one presentation-ready deck outline per major codebase component. Use when the user asks to create a presentation, prepare a walkthrough deck, build an onboarding deck, produce an architecture review deck, or summarize a codebase for a technica
Ready to connect★ 66
- View details
quick-workSkillProductivity
Fast single-task execution — one shot, done. Use for small tasks that don't need full brainstorm/plan/work flow.
Ready to connect★ 66
- View details
receiving-pr-reviewsSkillProductivity
Work through every unresolved review thread on a PR to completion — validate, fix if warranted, reply, resolve, then re-check on a bounded schedule. Use after pushing a commit to a PR, or when asked to check or address PR reviews.
Ready to connect★ 66
- View details
start-super-pmSkillProductivity
Use when starting any product management task - automatically detects task type and invokes appropriate PM skill using intelligent routing
Ready to connect★ 66
- View details
surgical-changesSkillProductivity
Enforces minimal code modifications — touch only what you must. Prevents drive-by refactoring, comment deletions, and style changes unrelated to the task.
Ready to connect★ 66
- View details
unipi-subagentsSkillProductivity
Delegate work to builtin or custom subagents with single-agent, parallel, scripted-chaining, async, forked-context, and coordinated workflows. Use for advisory review, implementation handoffs, and multi-step tasks where a single agent should stay in control while other agents contribute context, pla
Ready to connect★ 66
- View details
verify-doneSkillProductivity
Rigorous self-assessment checklist before marking any task as complete. Use when about to claim task completion, before final commit, when user asks "is it done?", or when transitioning from implementation to reporting. Prevents premature completion claims by requiring evidence for every assertion.
Ready to connect★ 66
- View details
audit-modelSkillProductivity
Audit one existing ModernTSF model against its card, paper, official-code facts, local implementation, component decisions, and unified verification evidence. Use for a focused review; batch ownership belongs in a task harness.
Ready to connect★ 65
- View details
batchSkillProductivity
Process multiple features or tasks in parallel. Batch execution of PDCA commands across features.
Ready to connect★ 65
- View details
office-web-ui-systemSkillProductivity
Coordinator-routed implementation specialist for admin dashboards, internal tools, CRM/ERP management, back-office, CRUD, and reporting UI. Use after project-development-mindset makes an operational dashboard primary, or directly when explicitly invoked or installed standalone. Owns dashboard screen
Ready to connect★ 65
- View details
planeSkillProductivity
Plane.so project management interface via direct API scripts. Use when user says 'plane', 'check plane', 'update plane', 'GP-42', 'plane status', 'sync to plane', 'look up task', or any Plane-related project management action.
Ready to connect★ 65
- View details
run-reviewable-subtask-loopSkillProductivity
Explicit-opt-in delivery specialist for executing a large plan, migration, refactor, or roadmap as sequential reviewable commits on one integration branch. Use only when directly requested or explicitly accepted after a project-development-mindset proposal; never infer activation from size, an inter
Ready to connect★ 65
- View details
subagent-coordinatorSkillProductivity
Launches multiple subagents in parallel and automatically assembles their results into a single report. Use for independent tasks that can be executed simultaneously. Triggers: 'параллельно', 'несколько субагентов', 'запусти агентов', 'исследуй рынок', 'проанализируй конкурентов'.
Ready to connect★ 65
- View details
subagent-runnerSkillProductivity
Automatically launches and manages subagents for parallel task processing. Breaks large tasks into subtasks, runs subagents in parallel, and collects results.
Ready to connect★ 65
- View details
zohoSkillProductivity
Interact with Zoho CRM, Projects, and Meeting APIs. Use when managing deals, contacts, leads, tasks, projects, milestones, meeting recordings, or any Zoho workspace data.
Ready to connect★ 65
- View details
accept-no-substitutesSkillProductivity
This skill should be used when agents generate placeholder tokens like "pseudo-", "mock-", "temporary", "TODO", "demo-", or similar incompleteness markers. Detects substitution patterns in agent OUTPUT and triggers mandatory user interview instead of accepting incomplete work. Activates automaticall
Ready to connect★ 64
- View details
cc-agySkillProductivity
Delegates coding/research tasks to the Google Antigravity CLI (`agy`) for external-model execution (Gemini 3.x, Claude Sonnet/Opus 4.6, GPT-OSS). Replaces the broken `collaborating-with-gemini` skill. Use when: (1) External-model delegation via Antigravity, (2) Multi-model prototyping (switch model
Ready to connect★ 64
- View details
codex-ccSkillProductivity
Delegates coding tasks from Codex to local Claude Code in print mode while preserving Claude's normal runtime customizations by default. Use when: (1) You want Codex to call Claude Code locally, (2) You need Claude-side skills, plugins, MCP servers, custom commands, CLAUDE.md rules, or workspace set
Ready to connect★ 64
- View details
effect-tsSkillProductivity
Effect-TS expert — write, debug, refactor, and explain code using the Effect ecosystem (effect, @effect/platform, @effect/rpc, @effect/cli, @effect/schema, @effect/cluster). Use this skill whenever the user works with Effect-TS code, mentions Effect services/layers/fibers/streams/schedules, asks abo
Ready to connect★ 64
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.