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: Docs & knowledge
4,502 results · page 133 of 151
- View details
checking-source-claimsSkillDocs & knowledge
Checks that the way you cite source families, agencies, standards, or borrowed ideas is honest and does not claim too much. Use when public docs, templates, skills, change records, or rollout copy point to outside sources. Do not use for private notes, or for checking whether code actually works.
Ready to connect
- View details
closedaySkillDocs & knowledge
End-of-day review and summary: based on today's Daily Note and official task sources, outputs today's completions, progress, new ideas, unfinished items, system write-back suggestions, and carry-over items for tomorrow. Triggered when the user asks to end the day / wrap up / do a daily review, says
Ready to connect
- View details
connectSkillDocs & knowledge
Find meaningful connections between two topics across the vault. Use this skill when the user asks to connect, link, or relate two concepts, find relationships between topics, discover how ideas intersect, or explore connections in their knowledge base. This skill searches Knowledge, Projects, and D
Ready to connect
- View details
connect-existing-toolsSkillDocs & knowledge
Connect a site's existing WebMCP tools to AgentLane without rebuilding them. Use when a codebase already registers document.modelContext tools — natively or through any SDK — and the developer wants them visible in AgentLane, migrated onto @nekuda/webmcp-sdk with durable stable keys and verified to
Ready to connect
- View details
coordinate-reasoningSkillDocs & knowledge
AI internal coordination using stigmergic signals — managing information freshness in context and memory, decay rates for assumption staleness, and emergent coherent behavior from simple local protocols. Use during complex tasks where multiple sub-tasks must coordinate, when context has grown long a
Ready to connect
- View details
create-github-releaseSkillDocs & knowledge
Create a GitHub release with proper tagging, release notes, and optional build artifacts. Covers semantic versioning, changelog generation, and GitHub CLI usage. Use when marking a stable version of software for distribution, publishing a new library or application version, creating release notes fo
Ready to connect
- View details
decommission-validated-systemSkillDocs & knowledge
Decommission a validated computerized system at end-of-life. Covers data retention assessment by regulation, data migration validation (mapping, transformation, reconciliation), archival strategy, access revocation, documentation archival, and stakeholder notification. Use when a validated system is
Ready to connect
- View details
doc-maintainerSkillDocs & knowledge
A skill that helps check and fix the health of markdown documentation for AI (SKILL.md, AGENTS.md, .agent/*.md, etc.). Use it when asked to things like "check documentation consistency", "find SSOT violations", "maintain skill definitions", or "update a PR description".
Ready to connect
- View details
doc-standardsSkillDocs & knowledge
Documentation standards workflow for Citum specs, policies, architecture snapshots, guides, and references. Use this skill when creating or updating project documentation and choosing the correct docs directory/template.
Ready to connect
- View details
document-insect-sightingSkillDocs & knowledge
Record insect sightings with location, date, habitat, photography, behavior notes, preliminary identification, and citizen science submission. Covers GPS coordinates, weather conditions, microhabitat description, macro photography techniques, behavioral observations, preliminary identification to or
Ready to connect
- View details
enforce-redaction-gateSkillDocs & knowledge
Statically enforce a privacy/redaction boundary on an artifact tree before publication, the way an AST checker enforces a code contract. Builds a two-tier gate — a shape-based deny-list (regex over identifier shapes) plus a structure-aware tier that parses JSON/HTML/SVG/Markdown/code and asserts sen
Ready to connect
- View details
engine-behavior-reportingSkillDocs & knowledge
Expand or maintain the engine behavior coverage report in citum-core. Use this skill when converting additional citum-engine integration suites into behavior-oriented tests, adding them to the nextest-backed Markdown/HTML report, refining behavior summaries, or updating the published docs report wit
Ready to connect
- View details
escalate-issuesSkillDocs & knowledge
Triage maintenance problems by severity, document findings with context, route to appropriate specialist agent or human, and create actionable issue reports. Use when a maintenance task encounters problems beyond automated cleanup: code that is unsafe to delete, configuration changes requiring domai
Ready to connect
- View details
experiment-reportSkillDocs & knowledge
Create consistent nn_cfd W&B experiment comparison reports from selected run IDs using wandb and wandb_workspaces. Use this whenever the user asks to report experiment results, create a W&B Report, compare CFD training/eval runs, document baseline-vs-variant outcomes, reproduce the project experimen
Ready to connect
- View details
learn-my-tenantSkillDocs & knowledge
Use when the user wants Greybeard to learn the tenant, onboard a new environment, or seed memory with naming conventions, rings, break-glass accounts, and change windows.
Ready to connect
- View details
least-privilege-scopesSkillDocs & knowledge
Use when the user needs minimum Microsoft Graph permissions, scope choices, admin-consent notes, over-permissioning review, or least-privilege access planning.
Ready to connect
- View details
- View details
migration-behavior-reportingSkillDocs & knowledge
Expand or maintain the migration behavior coverage report in citum-core. Use this skill when converting reviewer-facing citum-migrate suites into behavior-oriented tests, adding them to the nextest-backed Markdown/HTML report, refining behavior summaries, or updating the published docs report withou
Ready to connect
- View details
molclaw-skill-template-writerSkillDocs & knowledge
Formats extracted execution patterns into standard MolClaw skill documents. Accepts structured input from the Skill Crystallization Meta-Workflow (L2-12) and outputs a properly formatted L1 or L2 skill document conforming to MolClaw conventions. This skill ensures that auto-generated skills are stru
Ready to connect
- View details
openclaw-brandSkillDocs & knowledge
Apply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials. Use when the task changes brand identity rather than ordinary product UI or public-page composition.
Ready to connect
- View details
openrisk-claim-matrixSkillDocs & knowledge
The "invent nothing" rule and the Marketing Claim Matrix format for OpenRisk. Load before writing, reviewing or approving any README, ROADMAP, documentation, marketing copy or release note.
Ready to connect
- View details
paper-workflowSkillDocs & knowledge
Advances social science empirical research from idea, proposal, data, or existing results to reproducible analysis and a complete paper DOCX. Supports research design, data auditing, estimation, tables and figures, writing and revision, and on-demand preparation of a submission package; progresses s
Ready to connect
- View details
random-thinkingSkillDocs & knowledge
Randomly draws topics from the knowledge base for deep thinking. Triggered when the user says "随机想法", "随机思考", "给我点灵感", "来个有趣的话题", "random thinking", or wants to explore surprises from the knowledge base. The skill randomly selects content across types and topics from knowledge cards and knowledge fi
Ready to connect
- View details
react-ariaSkillDocs & knowledge
Build accessible UI components with React Aria Components. Use when developers mention React Aria, react-aria-components, accessible components, or need unstyled accessible primitives. Provides documentation for building custom accessible UI with hooks and components.
Ready to connect
- View details
reportSkillDocs & knowledge
The OpenRisk weekly report to the owner — velocity, milestone burn-down, defect clusters, competitive note, pending decisions and the recommendation for next week. Run at the end of the week.
Ready to connect
- View details
report-generationSkillDocs & knowledge
Use this skill to produce a structured business report from analysis output and validate it before delivery — turning metrics, findings, and recommendations into a scannable, decision-ready document, then sanity-checking arithmetic, units, claims, and consistency. Industry-agnostic; works for market
Ready to connect
- View details
session-briefSkillDocs & knowledge
Generate a concise working-session brief from this Obsidian vault by reading AGENTS.md, stable context, recent daily notes, current tasks, and active project next actions. Use this skill when starting a new session, resuming work after a break, or needing a quick refresher on current priorities and
Ready to connect
- View details
spaced-reviewSkillDocs & knowledge
Manage active-recall spaced review for Obsidian knowledge cards. Use when the user asks what to review today, wants to enroll a card, or gives an explicit again/hard/good/easy rating for an identified review card.
Ready to connect
- View details
todaySkillDocs & knowledge
Generates a Today's Plan based on the current context: integrates standalone tasks, project tasks, current priorities, and the Daily Note, and outputs the Top 3 priorities with a time schedule. Triggered when the user asks for a today plan / today's schedule / today's focus, "what to do today", need
Ready to connect
- View details
traceSkillDocs & knowledge
Track how a topic has evolved across the vault over time. Use this skill when the user asks to trace, track, or follow the evolution of a concept, see how an idea developed over time, find the history of a topic, or explore when and how a subject emerged in their knowledge base. This skill searches
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.