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
2,548 results · page 38 of 85
- View details
meeting-briefingSkillProductivity
Prepare structured briefings for meetings with legal relevance and track resulting action items. Use when preparing for contract negotiations, board meetings, compliance reviews, or any meeting where legal context, background research, or action tracking is needed.
Ready to connect★ 200
- View details
onboarding-plannerSkillProductivity
TRIGGER THIS when preparing for new hires, planning first-day/week/month activities, creating onboarding schedules, building 30-60-90 day plans, designing welcome programs, organizing training schedules, or setting up buddy/mentorship programs. Designs comprehensive, engaging onboarding experiences
Ready to connect★ 200
- View details
dexSkillProductivity
Manage tasks via dex CLI. Use when breaking down complex work, tracking implementation items, or persisting context across sessions.
Ready to connect★ 203
- View details
crmSkillProductivity
The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.
Ready to connect★ 199
- View details
sylph-setup-agentSkillProductivity
Set up an AI agent by validating her scope, schedule, and delivery channel. Run as `/sylph-setup-agent <agent-name>` or `/sylph-setup-agent all`.
Ready to connect★ 199
- View details
catgo-master-routerSkillProductivity
Route computational chemistry requests to the correct software and task skill. Entry point for all CatGo agent interactions.
Ready to connect★ 198
- View details
introSkillProductivity
Public English guide to the Manor AI OSS self-hosted product, its visible capabilities, and end-user workflows. Use for external Manor AI introductions, feature questions, onboarding, Chat, Workspaces, Tasks, Agents, Skills, Knowledge, Flows, Automations, Integrations, reports, settings, and safe us
Ready to connect★ 164
- View details
manor-workspace-architectureSkillProductivity
Use when changing, debugging, reviewing, documenting, or testing Manor Workspace behavior, especially when a change crosses chat, Strategist, Proposal, Task, Plan, Workflow, automation, approval, artifact, Knowledge, credits, lifecycle, or Blueprint boundaries.
Ready to connect★ 164
- View details
manor-workspace-blueprintSkillProductivity
Use when creating, exporting, hand-authoring, installing, upgrading, reverting, reviewing, or debugging any Manor Workspace Blueprint, especially when Workspace behavior differs from its Blueprint or when workflows, tasks, automations, artifacts, approvals, or runtime requirements are involved.
Ready to connect★ 164
- View details
mcp_google_calendarSkillProductivity
Read and manage the user's Google Calendar through the Google Calendar MCP. Use when the user asks to check their schedule, find a free slot, create / move / update / cancel events, or respond to a meeting invite.
Ready to connect★ 164
- View details
mcp_manor_mcp_calendarSkillProductivity
Manage Manor's first-party calendar settings, booking links, working hours, stored bookings, and daily agenda through the Manor Calendar MCP.
Ready to connect★ 164
- View details
mcp_ms_calendarSkillProductivity
Read and manage the user's Microsoft / Outlook Calendar through the Microsoft Calendar MCP. Use when the user asks to check their schedule, find a free slot or meeting time, create / update / cancel events, or accept/decline a meeting invite on their Microsoft 365 calendar.
Ready to connect★ 164
- View details
relationship-ledgerSkillProductivity
Read, query, and record people, organizations, contact routes, relationship state, interactions, follow-ups, consent, and evidence in the active Workspace Relationship Ledger. Use whenever a task relies on CRM-style relationship data or must update it after a verified action.
Ready to connect★ 164
- View details
siestaSkillProductivity
Generate and manage SIESTA DFT calculations. Use when the user requests SIESTA, numeric atomic orbital (NAO) DFT, or linear-scaling DFT for large systems.
Ready to connect★ 198
- View details
vasp-routerSkillProductivity
Route VASP calculation requests to the correct task type. Enforces VASP-specific policies for POTCAR, ENCUT, k-points, and slab handling.
Ready to connect★ 198
- View details
workflow_errorsSkillProductivity
Diagnose and fix CatGo workflow engine errors including HPC connection failures, missing POTCARs, stuck tasks, and REMOTE_ERROR states.
Ready to connect★ 198
- View details
overleafSkillProductivity
How to set up and manipulate Overleaf CE project state via HTTP APIs for CUA-Gym tasks. For setup-gen and reward-gen agents.
Ready to connect★ 197
- View details
agent-prompts-warmupSkillProductivity
Audit and sync agent instruction files across all coding agent formats. FRE (first-run) checks scaffolding completeness; ongoing use keeps files in sync after edits.
Ready to connect★ 142
- View details
htmxSkillProductivity
Implements HTMX interactions, configures swap behaviors, debugs hx-* requests, and builds hypermedia-driven UI components. Use when tasks involve hx-* attributes, HTMX AJAX requests, swap strategies, server-sent events, WebSockets, or hypermedia-driven UIs.
Ready to connect★ 194
- View details
agent-deckSkillProductivity
Manage AI agent sessions via the agent-deck CLI. Triggers (RU): "запусти агента", "запусти саб-агента", "создай сессию", "проверь сессию", "проверь статус", "покажи вывод агента", "что агент ответил". Triggers (EN): "launch sub-agent", "create sub-agent", "start session", "check session", "show
Ready to connect★ 192
- View details
commit-and-doneSkillProductivity
Commit changes, mark the current task as done, and close its tab
Ready to connect★ 192
- View details
slay-auto-titleSkillProductivity
Automatically title tasks based on conversation context
Ready to connect★ 192
- View details
slay-orchestrateSkillProductivity
Supervise a set of slay tasks through planning, execution, and verification
Ready to connect★ 192
- View details
slay-tasksSkillProductivity
Manage tasks, subtasks, tags, and templates via the slay CLI
Ready to connect★ 192
- View details
chenggu-analysisSkillProductivity
Structured Chinese Chenggu (“bone weight”) fortune analysis for 称骨算命 / 袁天罡称骨 tasks. Use when the user wants a deterministic lookup + structured output pipeline from birth datetime or normalized lunar components.
Ready to connect★ 191
- View details
source-command-opsx-applySkillProductivity
Implement tasks from an OpenSpec change (Experimental)
Ready to connect★ 190
- View details
ab-create-roadmapSkillProductivity
Turn a larger idea into a dependency-ordered roadmap of tasks — the layer above create-task. Use when the work is several distinct tasks with real ordering between them (schema before API before UI), and you want the whole task graph drawn before implementing. Producer only; ab-start-roadmap execute
Ready to connect★ 190
- View details
ab-create-taskSkillProductivity
Create a focused task and break it into test-driven missions. Use when the user wants to start a new feature, fix a bug, or begin implementation work.
Ready to connect★ 190
- View details
ab-create-task-from-handoffSkillProductivity
Resume a handoff (a side-topic spun off mid-grill) and turn it into a test-driven task. Use when the user wants to continue grilling on a deferred topic captured under docs/handoffs/.
Ready to connect★ 190
- View details
ab-extend-taskSkillProductivity
Append new missions to an existing task. Use when requirements changed or scope grew on a task already underway.
Ready to connect★ 190
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.
53,586 of the 54,018 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.