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
4,501 results · page 87 of 151
- View details
ddmemoSkillDocs & knowledge
Generate comprehensive investment memos for cyber•Fund investment committee decisions. Use when creating DD memos or investment analysis documents.
Ready to connect★ 105
- View details
optimizeSkillDocs & knowledge
Lets your agent get recommendations for improving AI model performance.
Ready to connect★ 105
- View details
summarizeSkillDocs & knowledge
Summarize various content types (therapy sessions, meetings, documents) into structured notes. Use when processing transcripts or long-form content.
Ready to connect★ 105
- View details
hybrid-memorySkillDocs & knowledge
Hybrid memory strategy combining OpenClaw's built-in QMD vector memory with Graphiti temporal knowledge graph. Use for all memory recall requests.
Ready to connect★ 104
- View details
japanese-style-ppt-skillSkillDocs & knowledge
Create or redesign PowerPoint/PPTX decks in the user's Japanese editorial styles: (1) "Washi Paper & Soft Glow" with washi texture, indigo restraint, and warm minimalism; or (2) high-end Japanese lifestyle magazine style with stark white background, burnt orange accent, charcoal gray, structured gri
Ready to connect★ 104
- View details
soft-3d-clay-ppt-skillSkillDocs & knowledge
Create or redesign PowerPoint/PPTX decks in a "Soft 3D / Claymorphism" style: minimalist professional presentation design with soft matte 3D geometric shapes, pastel beige/sage/warm-pink palette, airy clean layouts, soft shadows, high-end illustration feel, and sophisticated UI design. Use when the
Ready to connect★ 104
- View details
codex-memory-trimSkillDocs & knowledge
Manage Codex's native global memory (~/.codex/memories) with three sub-procedures - trim (audit + dedupe + three-layer cleanup), compress (rewrite verbose memories into concise form), and add-global (add a custom global rule/preference). Use when the user asks to 精简/清理/整理/压缩 Codex 记忆, 去重, 简化冗长记忆, 添加
Ready to connect★ 103
- View details
paper-writing-pipelineSkillDocs & knowledge
Full paper writing pipeline. Orchestrates paper-plan → paper-figure-generate → paper-draft → paper-review-loop → paper-covert to go from upstream research artifacts to a polished, submission-ready manuscript package (Markdown → LaTeX → PDF + DOCX). Use when user says \"write paper pipeline\", \"pape
Ready to connect★ 103
- View details
cutting-releasesSkillDocs & knowledge
Cuts Iris GitHub releases through the version-bump PR, merge commit, tag-driven build workflow, attestations, installer tests, and generated release notes. Use when preparing, publishing, verifying, or backfilling notes for a purescript-iris release.
Ready to connect★ 102
- View details
fix-self-checkSkillDocs & knowledge
M-1.6 envelope self-check — independence guarantee against self-deception (5 blocking_checks). Automatically triggered by the CLI ./tw fix complete --self-check-mode fork (fork is the default), without going through the Skill tool; the fix main session reads this document directly before producing F
Ready to connect★ 102
- View details
memory-and-disposalSkillDocs & knowledge
This skill should be used when managing WASM handle lifetimes or hunting memory leaks in brepjs — when a task mentions "createHandle() without using keyword risks WASM memory leak", "require-using-for-handles", "Shape handle has been disposed", "kernel handle has been disposed", "memory grows / heap
Ready to connect★ 102
- View details
writing-code-commentarySkillDocs & knowledge
Writes and reviews Iris compiler comments, algorithm traces, and documentation examples. Use when documenting non-obvious compiler transformations, revising inline commentary, or applying documentation-focused review nits.
Ready to connect★ 102
- View details
bump-versionsSkillDocs & knowledge
Apply the yash-rs versioning rules: bump affected crate versions, sync the root Cargo.toml, and add Unreleased changelog headings. Use proactively, before committing, for every code change to any yash-* crate in this workspace — not just when the user asks about versioning. Documentation updates are
Ready to connect★ 101
- View details
paper-reading-zhSkillDocs & knowledge
In-depth Chinese paper reading, summaries/TL;DR, engineering breakdowns, implementing/reproducing papers, comparisons, and evidence audits. Use when the user provides a paper PDF, link, title, abstract, body text, or figures, or explicitly asks to read a paper. If there is only a paper reference wit
Ready to connect★ 101
- View details
syncSkillDocs & knowledge
Mid-session checkpoint. Saves to memory, flags Command Center or To-Do drift, rotates session context.
Ready to connect★ 101
- View details
academic-writerSkillDocs & knowledge
Lets your agent draft research papers, grant proposals, and abstracts in proper academic style.
Ready to connect★ 99
- View details
code-refactoringSkillDocs & knowledge
Expert code refactoring and optimization with analysis, improvements, and documentation. Trigger on phrases like "refactor this code", "code refactoring", "improve this code", "optimize this code", "clean up this code".
Ready to connect★ 99
- View details
content-creation-and-marketingSkillDocs & knowledge
Cross-channel content production from an approved idea, brief, notes, transcript, or existing asset. Use when the user wants a ready-to-review draft or a small set of adaptations saved into the bootstrap content workspace. For content strategy use content-strategy-and-planning; for specialist Linked
Ready to connect★ 100
- View details
document-converter-suiteSkillDocs & knowledge
Convert PDFs, Office docs, markdown, HTML, and tables between editable formats. Use for best-effort document conversion, PDF utilities, form filling, and table extraction.
Ready to connect★ 100
- View details
hk-autonomy-auditSkillDocs & knowledge
Audit whether an AI agent can autonomously close the loop on problems in a given area — from discovering a symptom to verifying a fix — without human intervention. Evaluates documentation, diagnostic tools, commands, logs, and flows for completeness and actionability. Generates a gap-focused report
Ready to connect★ 100
- View details
hk-breadcrumb-creatorSkillDocs & knowledge
Traces a workflow end-to-end through the harness-kit monorepo and creates a breadcrumb analysis doc in docs/breadcrumb_analysis/. Use this skill whenever the user wants to document a flow, trace a workflow, understand how a feature works across layers (frontend → backend → worker → CLI), or create d
Ready to connect★ 100
- View details
hk-compoundSkillDocs & knowledge
Compound a learning into a reusable pattern. Use after solving a non-trivial problem, discovering a principle worth reusing, or hitting a gotcha that would bite someone else. Triggers on: 'document this', 'capture this learning', 'that was tricky', 'let's compound this', 'compound this', or /hk-comp
Ready to connect★ 100
- View details
hk-rcaSkillDocs & knowledge
Interactive Root Cause Analysis enforcer. Guides you through the 7-step RCA protocol: Reproduce, Locate, Hypothesis, Failing Test, Fix, Verify Live, Document. Use when debugging a bug, investigating a failure, or when something unexpected happened. This skill gates each step — it won't let you skip
Ready to connect★ 100
- View details
ocr-document-processorSkillDocs & knowledge
Extract text and structure from scans, images, and scanned PDFs. Use for OCR, searchable PDFs, table extraction, receipt parsing, and business card parsing.
Ready to connect★ 100
- View details
org-mode-workflow-specialistSkillDocs & knowledge
Leverage Org-mode for productivity, task management, note-taking, and project management. Trigger on phrases like "org-mode workflow", "org-mode help", "org-mode setup", "org-mode configuration", "org-agenda", "org-capture".
Ready to connect★ 99
- View details
ph-content-recyclingSkillDocs & knowledge
Repurpose Product Hunt launch content across channels. Use this skill to maximize the value of your launch assets by adapting them for blog posts, documentation, social media, and more.
Ready to connect★ 100
- View details
pitch-deck-creationSkillDocs & knowledge
Create professional investor pitch decks with structured content and visual design. Use when users need help with pitch deck, investor deck, fundraising deck, startup pitch, deck design, slide design, pitch presentation, pitch deck visuals, investor presentation, Series A deck, seed deck, or VC deck
Ready to connect★ 100
- View details
preserveSkillDocs & knowledge
Single write point for the vault. Centralizes entity detection, textual matching, entity creation/update, and bidirectional linking. Accepts structured input (list of entities), free-form input (text, meeting notes, session context), or graphify output (graph.json + obsidian markdown from /graphify
Ready to connect★ 100
- View details
release-notes-specialistSkillDocs & knowledge
Communicate software changes effectively with categorized release notes. Trigger on phrases like "release notes", "changelog", "write release notes", "version announcement", "software changelog".
Ready to connect★ 99
- View details
slide-outlineSkillDocs & knowledge
Use this skill whenever a user wants to create a presentation outline, slide deck structure, storyboard slides, or plan a deck for any context (talk, boardroom, email report). Also use when the user mentions "help me structure my presentation", "slide outline", "storyboard my deck", "presentation fl
Ready to connect★ 100
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.
53,585 of the 54,017 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.