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 138 of 151
- View details
memory-systemsSkillDocs & knowledge
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
Ready to connect
- View details
mermaid-diagramSkillDocs & knowledge
Generate beautiful Mermaid diagrams — flowcharts, sequence, ER, class, state, pie, gantt, mindmap, timeline, gitgraph, C4, kanban, block, quadrant, sankey, XY charts. Renders to PNG locally and Markdown for GitHub. Use when the user asks for diagrams, visualizations, schemas, flowcharts, architectur
Ready to connect
- View details
midi-cleanupSkillDocs & knowledge
Use when the user asks to humanize a MIDI part, fix voice leading, quantize notes, clean up timing, fix stuck/duplicate notes, or generally polish a MIDI clip they recorded or wrote. Examples - "humanize this hat", "voice these chords better", "the timing is too stiff", "fix the voice leading on the
Ready to connect
- View details
paper-importSkillDocs & knowledge
Paper reference import command (reference organizer + reference-draft consistency checker). Use when the user has references exported from CNKI/Zotero/EndNote to organize in batch, organize bibliographies, import references, check reference-draft citation consistency, find which draft citations have
Ready to connect
- View details
paper-outlineSkillDocs & knowledge
Paper outline command (structure draft co-writer). Use when the user already has a research question (RQ) and literature notes and wants to build the paper's skeleton, draft chapter outlines, write the paper structure, organize a writing framework, or says things like "help me list my paper outline"
Ready to connect
- View details
paper-proposalSkillDocs & knowledge
Command for assembling a paper proposal report (multi-source aggregation assembler). Use when the user wants to write a proposal report, assemble thesis proposal materials, organize project initiation documents according to Chinese thesis proposal system milestones, or says things like "帮我组装开题报告", "
Ready to connect
- View details
perfetto-trace-analysisSkillDocs & knowledge
Analyzes Perfetto traces to find the root cause of latency, memory, or
Ready to connect
- View details
product-deep-researchSkillDocs & knowledge
Runs a reproducible, evidence-traceable deep research workflow for AI products or companies, delivering shareable Markdown reports and an auditable research package. Suitable for product research, company research, competitive analysis, growth breakdowns, business models, founding teams, and user fe
Ready to connect
- View details
prune-memorySkillDocs & knowledge
Audit project memory (.agents/MEMORY.md and ~/.claude/.../memory/MEMORY.md) against current code and remove stale claims to prevent bad signals in future sessions
Ready to connect
- View details
researching-with-deepwikiSkillDocs & knowledge
Research GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. Use when exploring unfamiliar codebases, understanding project architecture, or asking questions about how a specific open-source project works. Provides AI-powered repo analysis and RAG-based Q&A about source code. NOT f
Ready to connect
- View details
session-recapSkillDocs & knowledge
Generate structured session recap and auto-extract high-confidence learnings into project memory
Ready to connect
- View details
swmm-experiment-auditSkillDocs & knowledge
Consolidate Agentic SWMM run artifacts into auditable provenance, comparison records, and local Obsidian audit notes. Use after any SWMM build/run/QA attempt, successful or failed, when an agent or CLI workflow needs a traceable record of inputs, commands, artifacts, metrics, QA checks, run-to-run d
Ready to connect
- View details
swmm-modeling-memorySkillDocs & knowledge
Read historical Agentic SWMM experiment audit artifacts and summarize repeated assumptions, QA issues, failures, missing evidence, run-to-run differences, lessons learned, and controlled skill update proposals. Use downstream of swmm-experiment-audit when multiple audited runs exist or when a user a
Ready to connect
- View details
swmm-plotSkillDocs & knowledge
Nature-spec figures from a SWMM run: paired rainfall (inverted) + node/link flow hydrograph (plot_run), network layout map (map_run), study-area map. 89/183 mm columns, 5-7 pt sans-serif, ticks out, no gridlines, Wong colour-blind-safe palette, vector PDF + 450 dpi PNG twin, SI units, no title; opti
Ready to connect
- View details
swmm-rag-memorySkillDocs & knowledge
Retrieve relevant Agentic SWMM modeling memory from audited runs, modeling-memory summaries, and Obsidian-compatible notes at query time. Use when a user asks for RAG, similar past runs, evidence-linked memory retrieval, historical QA/failure patterns, or memory-grounded answers.
Ready to connect
- View details
swmm-reportSkillDocs & knowledge
Generate a client-deliverable Word (.docx) report from an audited SWMM run directory. Reads manifest.json, experiment_provenance.json, model_diagnostics.json, comparison.json, and any PNG figures — SWMM is never re-run. Supports custom YAML/JSON section templates.
Ready to connect
- View details
tectonic-pdfSkillDocs & knowledge
Generate PDFs from LaTeX (.tex) or Markdown (.md) using Tectonic, a self-contained TeX engine. Use whenever the user wants a PDF, whether converting markdown, compiling existing LaTeX, writing a document from scratch (reports, resumes, letters, CVs), or live-rebuilding while the user edits. Trigger
Ready to connect
- View details
update-api-referenceSkillDocs & knowledge
Regenerate the OpenAPI reference documentation after adding, modifying, or removing API endpoints in sandbox-api. Run this whenever handler signatures, route paths, or swag annotations change.
Ready to connect
- View details
working-with-documentsSkillDocs & knowledge
Creates and edits Office documents: Word (.docx), PDF, and PowerPoint (.pptx). Use when working with document creation, PDF manipulation, presentation generation, tracked changes, or converting between formats.
Ready to connect
- View details
xhs-image-text-generatorSkillDocs & knowledge
Turns HTML, Markdown, articles, interview transcripts, product material, or topics into publish-ready 6-10 page Xiaohongshu/RedNote image-text carousels, handling content distillation, pagination, visual design, image generation, failure retries, and delivery verification. Suitable for requests like
Ready to connect
- View details
youtube-podcast-to-mdSkillDocs & knowledge
Extracts YouTube podcast, interview, or long-video subtitles and organizes them into Chinese Markdown. Supports core summaries with high-fidelity dialogue restoration, subtitle fallback strategies, speaker handling, and timestamp-based source tracing. Prioritize when the user provides a YouTube link
Ready to connect
- View details
agent-shared-memorySkillDocs & knowledge
Use when a user asks to inspect coordination memory, propose a durable decision or resolution, review pending memory proposals, or apply an explicitly approved proposal as a new append-only event.
Ready to connect
- View details
agent-task-splitterSkillDocs & knowledge
Use when a goal needs multiple bounded agent roles, parallel or dependent task packets, explicit scope partitions, and a provider-neutral DAG. Not for research-domain routing that owns .research, .paper, Zotero, Obsidian, or NotebookLM workflows; use research-hub-multi-ai for those.
Ready to connect
- View details
annotator-input-parity-checkSkillDocs & knowledge
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-c
Ready to connect
- View details
architecture-decision-recordsSkillDocs & knowledge
Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.
Ready to connect
- View details
backup-rollbackSkillDocs & knowledge
Snapshot configs, memory, and skills before risky edits, and define a rollback path. Use before bulk refactors, migrations, or skill/config changes.
Ready to connect
- View details
brainstormSkillDocs & knowledge
Iterative brainstorming skill for turning fuzzy ideas into approved tree documents. Diverges into branches, deepens and prunes them over many rounds, saves a tree doc. Run breakdown on the tree to distill it into a spec via guided questions.
Ready to connect
- View details
branded-deck-builderSkillDocs & knowledge
Builds PowerPoint decks on the user's own company template and checks every slide against written brand rules (colours with hex codes, fonts, logo placement, banned visuals). Use when the user asks for a branded, on-brand, CI-compliant or corporate-template presentation, or wants a deck that follows
Ready to connect
- View details
cbo-reviewerSkillDocs & knowledge
Reviews a proposal, business case, deck or plan in character as a Chief Business Officer archetype, covering commercial model, partnerships, deal structure, market positioning, strategic fit and opportunity cost. Produces a DRAFT review document with a verdict, findings that cite the artifact, risks
Ready to connect
- View details
cdo-reviewerSkillDocs & knowledge
Reviews a proposal, business case, deck or plan in character as a Chief Data Officer archetype, then saves a structured review document with a verdict, findings that cite the artifact, data and AI governance risks and five interrogation questions. Use when the user asks for a CDO review, a data or A
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.