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
4,561 results · page 118 of 153
- View details
documentation-agentSkillDocs & knowledge
Generates standards-based repository documentation for GitHub or any project. Writes a docs suite into the project's docs/ directory covering ISO 9001, V-Model, ISO 27001, and optionally GAMP 5 or other standards. Use when the user asks for repo documentation, compliance docs, quality docs, or to cr
Ready to connect★ 54
- View details
douyin-interactSkillDocs & knowledge
Like, favorite, or comment on a clearly specified public Douyin video or note, or return its share link. Use when the user asks to like, favorite, comment, cancel any of these statuses, or get the link to a Douyin work.
Ready to connect★ 54
- View details
execute-oneSkillDocs & knowledge
Reactant router — read a document, interpret its annotations in context, and execute only the first actionable <@skill> tag. Use when the user wants to step through Reactant tags one at a time.
Ready to connect★ 54
- View details
figureSkillDocs & knowledge
Generates publication-quality econometric figures like event study and coefficient plots styled for top economics journals.
Ready to connect★ 54
- View details
gke-ai-troubleshooting-tpu-vbar-oomSkillDocs & knowledge
Diagnoses and prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbar_control_agent crashes, memory cgroup OOM
Ready to connect★ 54
- View details
gke-cost-optimizationSkillDocs & knowledge
Optimizes GKE costs, rightsizes workloads, and configures Spot VMs, CUDs, cost allocation, and resource quotas. Use when optimizing GKE cluster or workload costs, configuring GKE cost allocation or quotas, rightsizing CPU/memory requests, or selecting Spot VMs and machine types. Don't use for genera
Ready to connect★ 54
- View details
gke-manifest-generationSkillDocs & knowledge
Generates and updates secure, production-ready Kubernetes YAML manifests optimized for GKE Autopilot and GKE Standard clusters. Use when creating or modifying GKE deployment manifests, configuring container security contexts, setting CPU/memory resource limits, defining readiness/liveness/startup pr
Ready to connect★ 54
- View details
gke-tpu-metrics-monitoringSkillDocs & knowledge
Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL. Use when monitoring TensorCore duty cycle, TPU memory, node readiness, multi-host TPU node pool availability, host maintenance or preemption interruptions, and calculating MTTR or MTBI metrics fo
Ready to connect★ 54
- View details
gongwenSkillDocs & knowledge
Formatting for official Chinese government documents. Standardizes body text fonts, heading levels, page layout, signatures, attachments, and other formatting elements according to Party and government document formatting standards.
Ready to connect★ 54
- View details
infographic-imageSkillDocs & knowledge
Stably converts any topic, long article, report, meeting notes, or explanatory text into a Chinese visual image-generation prompt, then calls the DashScope Qwen image model to generate the image directly. Suitable for scenarios such as "turn this content into an infographic", "make it into a story c
Ready to connect★ 54
- View details
liteparseSkillDocs & knowledge
Local PDF parsing via liteparse — text with bounding boxes, page screenshots, visual element detection.
Ready to connect★ 54
- View details
office-document-operationsSkillDocs & knowledge
Choose the right extraction or editing path for office documents such as PDF and DOCX without losing review context.
Ready to connect★ 54
- View details
ontology-zhSkillDocs & knowledge
Typed knowledge graph for structured agent memory and composable skills. Supports creating/querying entities (people, projects, tasks, events, documents), relation objects, constraint checking, planning multi-step operations as graph transformations, and cross-skill state sharing. Trigger words: "记住
Ready to connect★ 54
- View details
pdf-parsingSkillDocs & knowledge
Choose between docling, liteparse and pdfplumber for PDF extraction — tables, layout, fonts, screenshots, vector graphics.
Ready to connect★ 54
- View details
pdf-to-deckSkillDocs & knowledge
Convert a PDF input into a deck artifact, choosing between summary distillation and visual reconstruction with explicit traceability and QC.
Ready to connect★ 54
- View details
persona-commandsSkillDocs & knowledge
Runtime chat commands for the AI persona operating system. Routes 11 commands to their operations — status dashboard (with health metrics), show persona (displays SOUL.md identity), show memory (displays MEMORY.md contents), health check (runs diagnostic script), security audit (runs security valida
Ready to connect★ 54
- View details
persona-heartbeatSkillDocs & knowledge
Ambient monitoring and health heartbeat for AI persona OS sessions. Monitors context window usage, provides proactive suggestions when advisor mode is enabled, detects session startup to resume previous work, performs silent memory maintenance (cleaning old entries, archiving logs), and presents hea
Ready to connect★ 54
- View details
persona-learningSkillDocs & knowledge
Captures, reviews, and promotes learnings, errors, and feature requests in the AI persona operating system. Records structured entries to ~/workspace/.learnings/ (LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md), scans for weekly patterns, promotes repeated learnings (3+ occurrences) to MEMORY.md, and
Ready to connect★ 54
- View details
phSkillDocs & knowledge
Reactant tag-only placeholder. Use only when execute or execute-one dispatches an exact <@ph> tag from a document; never activate from ordinary chat or another skill.
Ready to connect★ 54
- View details
plotSkillDocs & knowledge
Reactant tag-only data visualization. Use only when execute or execute-one dispatches an exact <@plot> tag from a document; never activate from ordinary chat or another skill.
Ready to connect★ 54
- View details
proofreadSkillDocs & knowledge
Reactant tag-only proofreading. Use only when execute or execute-one dispatches an exact <@proofread> tag from a document; never activate from ordinary chat or another skill.
Ready to connect★ 54
- View details
release-automationSkillDocs & knowledge
Enforce and automate releases in CI so a promotion to main can never silently ship without a version bump. Documents and governs the release gate (block a main promotion that did not bump VERSION past the last vX.Y.Z tag) plus, on the same VERSION<->tag primitive, the auto-release lanes that already
Ready to connect★ 54
- View details
review-docs-driftSkillDocs & knowledge
Reviews a pull request for documentation drift — finds which docs the change should have updated, verifies doc claims against source, and checks the docs map and AGENTS.md themselves for staleness.
Ready to connect★ 54
- View details
Self-Improving + Proactive AgentSkillDocs & knowledge
Self-reflection + self-critique + self-learning + self-organized memory. The agent evaluates its own work, catches errors, and improves permanently. Use in these scenarios: (1) when a command, tool, API, or operation fails; (2) when the user corrects you or rejects your work; (3) when you find your
Ready to connect★ 54
- View details
using-bookSkillDocs & knowledge
Use to import, prepare, read, or synthesize a complete supported book in verified source order. Skip ordinary document lookup.
Ready to connect★ 54
- View details
using-planSkillDocs & knowledge
Use when an Agent needs to create, resume, advance, block, revise, complete, or abandon a durable current execution plan in LWC.
Ready to connect★ 54
- View details
using-practiceSkillDocs & knowledge
Use when creating or recovering a durable paper, attempt, grade, flashcard, scheduled review, mistake history, or goal-evidence record. Skip Tutor comprehension checks, lightweight diagnostics, and disposable questions.
Ready to connect★ 54
- View details
using-syncSkillDocs & knowledge
Use when an Agent needs to synchronize LWC Wiki stores across SSH hosts, resume or abort an interrupted Sync session, or resolve semantic Sync conflicts safely.
Ready to connect★ 54
- View details
using-todoSkillDocs & knowledge
Use when an Agent needs to capture, find, update, finish, cancel, or reopen durable deferred work in LWC.
Ready to connect★ 54
- View details
using-tutorSkillDocs & knowledge
Use when starting or changing teacher-led learning, or recovering Tutor after context loss or a state error. Skip bound steady-state replies and ordinary factual questions.
Ready to connect★ 54
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.
55,111 of the 55,543 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.