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
4,535 results · page 23 of 152
- View details
editSkillDocs & knowledge
Add or remove raw sources, or update wiki content, per user request
Ready to connect★ 2k
- View details
exp-pilot-runSkillDocs & knowledge
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Ready to connect★ 2k
- View details
ideateSkillDocs & knowledge
Multi-phase research idea generation pipeline: landscape scan → dual-model brainstorm → filter & validation → write to wiki → pilot
Ready to connect★ 2k
- View details
ingestSkillDocs & knowledge
Ingest a paper into the wiki — creates pages (papers + concepts + methods + people) and builds all cross-references and graph edges. Trigger whenever the user says "ingest", "add this paper", drops a `.pdf` / `.tex` / arXiv URL, or asks to fold a paper into the knowledge base.
Ready to connect★ 2k
- View details
initSkillDocs & knowledge
Bootstrap ΩmegaWiki from user sources plus optional discovery, then ingest the final paper set in parallel
Ready to connect★ 2k
- View details
noveltySkillDocs & knowledge
Multi-source novelty verification — WebSearch + Semantic Scholar + wiki + Review LLM cross-verify — outputs novelty score and recommendations. Optionally writes the score back to an idea page with --write.
Ready to connect★ 2k
- View details
paper-draftSkillDocs & knowledge
Draft a LaTeX paper from PAPER_PLAN — write each section from wiki sources + generate figures/tables + BibTeX verification + de-AI polish
Ready to connect★ 2k
- View details
prefillSkillDocs & knowledge
Seed wiki/foundations/ with domain background knowledge so subsequent /ingest does not create duplicate concept pages for textbook material
Ready to connect★ 2k
- View details
rebuttalSkillDocs & knowledge
Parse review comments → atomize concerns (Rvx-Cy) → map to wiki ideas/methods → check evidence → Review LLM stress-test → generate rebuttal
Ready to connect★ 2k
- View details
refineSkillDocs & knowledge
General-purpose multi-round iterative improvement — repeatedly calls /review on any research artifact, parses feedback, applies fixes, updates wiki, until the target score is reached
Ready to connect★ 2k
- View details
resetSkillDocs & knowledge
Reset wiki state to a clean scaffold by scope (wiki / raw / log / checkpoints / all). Useful during development or carefree restarts after a botched setup.
Ready to connect★ 2k
- View details
reviewSkillDocs & knowledge
General-purpose cross-model review — Review LLM independently reviews any research artifact, outputs structured scores, wiki entity mapping, and improvement suggestions
Ready to connect★ 2k
- View details
surveySkillDocs & knowledge
Generate a Related Work section for a paper from wiki knowledge — thematic grouping → narrative structure → LaTeX output, following citation-verification and academic-writing
Ready to connect★ 2k
- View details
visualizeSkillDocs & knowledge
Generate and update visualization artifacts — Obsidian graph config and Canvas knowledge maps. The interactive web graph view lives in the SPA at app/modules/graph.js (served by tools/serve.py).
Ready to connect★ 2k
- View details
mps-dsl-memorySkillDocs & knowledge
Create or refresh project-local DSL skills under `.agents/skills/<dsl-name>-dsl/` for one or more MPS languages after discovering concepts, sandbox examples, JSON blueprints, references, or gotchas.
Ready to connect★ 2k
- View details
mps-lang-core-xmlSkillDocs & knowledge
Use when authoring XML documents as MPS root nodes or building XML-generating generator templates with jetbrains.mps.core.xml — covers XmlFile, XmlDocument, prolog (XML declaration, DOCTYPE, processing instructions, comments), elements, attributes, CDATA, entity references, and macro attachment via
Ready to connect★ 2k
- View details
documenting-rust-codeSkillDocs & knowledge
Rust documentation practices for HASH codebase. Use when writing doc comments, documenting functions/types/traits/modules, creating error sections, using intra-doc links, or following rustdoc conventions.
Ready to connect★ 2k
- View details
exploring-rust-cratesSkillDocs & knowledge
Generate Rust documentation to understand crate APIs, structure, and usage. Use when exploring Rust code, understanding crate organization, finding functions/types/traits, or needing context about a Rust package in the HASH workspace.
Ready to connect★ 2k
- View details
gherkin-specificationSkillDocs & knowledge
Elicit or revise software behavior, maintain a recoverable behavior workpiece, and author or review honest Gherkin feature documents. Use for a behavior-specification interview, Gherkin document, executable-specification draft, or review of any of them.
Ready to connect★ 2k
- View details
hivemindSkillDocs & knowledge
Lets your agent delegate coding and research subtasks to free opencode workers it runs and supervises.
Ready to connect★ 2k
- View details
hivemind-graphSkillDocs & knowledge
Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what is the architecture / which subsystems exist?". The graph
Ready to connect★ 2k
- View details
hivemind-memorySkillDocs & knowledge
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
Ready to connect★ 2k
- View details
abmahnung-reagierenSkillDocs & knowledge
For responding to a cease-and-desist letter (Abmahnung): maps the norm, burden of proof, and counterarguments; result: an assessment document with risk and next step.
Ready to connect★ 2k
- View details
agb-entwurf-kaltstartSkillDocs & knowledge
For AGB Entwurf Kaltstart: routes role, deadline, documents and the professional step; result: a review product with risk and next step.
Ready to connect★ 2k
- View details
agb-pruefung-kaltstartSkillDocs & knowledge
For AGB review cold start: routes role, deadline, documents and procedural step; result: facts matrix or claims matrix.
Ready to connect★ 2k
- View details
dbt_ingestSkillDocs & knowledge
Map dbt `schema.yml` / `properties.yml` models and sources into ktx semantic-layer overlays and column notes. Covers `sources:` vs `models:`, column `data_tests` (not_null, unique, accepted_values, relationships), and how bundle-time writes complement manifest backfill from git sync. Load when the W
Ready to connect★ 2k
- View details
sigma_ingestSkillDocs & knowledge
Extract durable ktx wiki knowledge from staged Sigma data model specs and workbook summaries. Load for WorkUnits with unitKey sigma-data-models or sigma-workbooks.
Ready to connect★ 2k
- View details
sl_captureSkillDocs & knowledge
How to capture new reusable patterns into ktx's semantic layer - when a measure, segment, or join belongs in the catalog and how to write it generically so it stays small and useful over time. Loaded by the post-turn memory-agent only. The research agent does not write to the SL.
Ready to connect★ 2k
- View details
wiki_captureSkillDocs & knowledge
ktx's knowledge base - wiki pages for durable, reusable business knowledge. Covers capture workflow for user preferences, metric definitions, organizational conventions, and cross-references between wiki pages and semantic-layer sources. Loaded by the post-turn memory-agent only. The research agent
Ready to connect★ 2k
- View details
coauthor-briefSkillDocs & knowledge
Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact (manuscript, analysis, slides), open questions, how to reproduce locally, and any restricted-data access steps.
Ready to connect★ 2k
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.