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
2,715 results · page 80 of 91
- 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
linear-implementSkillProductivity
Work a Linear ticket end-to-end — read it, mark In Progress, do the work, summarize, proactively suggest follow-up tickets, and mark Done.
Ready to connect
- View details
manage-linearSkillProductivity
Manage Linear issues, projects, cycles, initiatives, and teams via the `linear` CLI (schpet/linear-cli)
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
- View details
project-workerSkillProductivity
Workflow, commands (/work, /start-session, etc.), and coding conventions guide for executing Evolution CMS JP Edition development tasks. Use when starting development work.
Ready to connect
- View details
- View details
review2SkillProductivity
Review your code with 2 adversarial review subagents. This is an expensive task, only run if user asks for it.
Ready to connect
- View details
roadmap-managerSkillProductivity
Skill for managing the roadmap (`.agent/roadmap.md`). Consistently handles adding, changing, and deleting tasks, starting the next task, and syncing completions. For tasks without an ExecPlan, it creates a plan before starting work.
Ready to connect
- View details
roadmap-next-taskSkillProductivity
Skill that starts the next incomplete task based on dependency order from the roadmap (`.agent/roadmap.md`). Consistently handles reflecting checkmarks upon completion, creating a plan first for tasks without an ExecPlan, and beginning implementation.
Ready to connect
- View details
staying-on-missionSkillProductivity
Tests the current work against a written, lasting mission anchor and forces one choice, re-anchor, escalate, or stop. Use when an agent keeps finishing tasks but the work drifts from the goal, scope creeps, the same action repeats in a loop, or standards slip one small step at a time. Do not use for
Ready to connect
- View details
test-coverageSkillProductivity
Domain knowledge for test coverage in citum-core. Use this skill whenever you're implementing a feature, fixing a bug, writing tests, or claiming something is "tested" in citum-core. Trigger on any task involving: adding fixture data, writing Rust tests, running the oracle, validating style behavior
Ready to connect
- View details
- View details
tool-workflowsSkillProductivity
Multi-tool recipes for common building energy modeling tasks. Use when chaining tools together for operations like adding windows, changing insulation, setting up HVAC, or running simulations.
Ready to connect
- View details
- View details
- View details
editorial-calendar-plannerSkillProductivity
Generate a structured editorial calendar: content mapping across weeks or months, production stage tracking, external event alignment, and workload distribution — for publications planning their coverage pipeline.
Ready to connect
- View details
get-contextSkillProductivity
Pull everything the agent needs to know about a topic (person, company, project, decision) before doing the work. Resolves the target, fetches the entity snapshot, the observation history, linked tasks, recent communication, and walks one hop of the relationship graph. Synthesizes a brief rather tha
Ready to connect
- View details
story-pitch-writerSkillProductivity
Drafts a concise, editor-ready story pitch that captures the angle, news hook, key sources, and proposed format so you can walk into an editorial meeting with a compelling one-page proposal.
Ready to connect
- View details
verified-delegationSkillProductivity
Structures multi-agent delegation so trust comes from executed checks, not agent self-reports: an orchestrator writes specs and reviews, cheaper workers implement, and every task passes or fails by running the work. Use when delegating to subagents or swarms, routing work across model price tiers, o
Ready to connect
- View details
whereSkillProductivity
Present-tense orientation — where everything stands right now, answered from what is already in context plus one scoped read of this session's Neotoma tasks, so work that aged out of the window is still reported. What is running, what just landed, what is waiting on the operator and why it is theirs
Ready to connect
- View details
bitrix-cms-basicsSkillProductivity
Covers CMS fundamentals — sites, site templates, menus, page templates, includes, breadcrumbs, styles/CSS handling (styles.css vs template_styles.css, Asset::addCss, SetAdditionalCSS), user groups, user fields, admin panel. Applied for site structure and content management tasks. Key terms — CSite,
Ready to connect
- View details
bitrix-datetimeSkillProductivity
Covers date and time in Bitrix — Bitrix\Main\Type\Date and DateTime, parsing and formatting by kernel masks, date arithmetic, time zones via toUserTime/disableUserTime/enableUserTime, Context::getCulture() and locale formats, conversion to timestamp. Applied when building schedules, converting time
Ready to connect
- View details
comment-jira-issueSkillProductivity
Use this skill only when the user explicitly invokes /comment-jira-issue to add, list, edit, or delete comments on a Jira issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Subcommands: add (post a new comment), list (fetch all co
Ready to connect
- View details
deepen-planSkillProductivity
Enhance an existing marketing plan with parallel research. Use when the agent has a draft plan (brand strategy, campaign brief, content calendar, launch plan) that needs strengthening with real data. Triggers on 'deepen this plan', 'strengthen this strategy', 'research gaps in my plan', 'make this p
Ready to connect
- View details
edictum-ossSkillProductivity
Implement features in the Edictum OSS core (src/edictum/). Use when the task touches pipeline, adapters, YAML engine, CLI, audit, envelope, or session. Core NEVER imports from ee/.
Ready to connect
- View details
embedded-timing-libsSkillProductivity
Use when integrating, porting, configuring, or debugging embedded software timer libraries such as MultiTimer, timeout schedulers, or tick-based callback timers
Ready to connect
- View details
engineeringSkillProductivity
Development agent for implementing features, fixing bugs, refactoring, and all engineering work. Context-aware — knows the project structure, docs, architecture, and conventions. Use for any development task.
Ready to connect
- View details
eo-change-reviewSkillProductivity
On-demand plan review: when risk signals are hit or the user names it, performs a plan-level review of change.md (AC quality, TODO↔AC mapping, premise validity) and produces a brief change-review.md. Triggers: 审查 change / change 审查 / 审方案 / /eo-change-review. NOT FOR: code review (/eo-review); defaul
Ready to connect
- View details
eo-implementSkillProductivity
Implement code in batches according to the TODOs in change.md, self-verifying against the corresponding ACs at the end of each batch. Triggers: 实现 / 写代码 / implement / /eo-implement. NOT FOR: bug and feedback fixes (bugs reported verbally and feedback within the test/review/acceptance loop must go th
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.
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.