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
4,436 results · page 144 of 148
- View details
math-modeling-paperSkillDocs & knowledge
数学建模竞赛证据约束论文写作 Skill。用于论文结构、正文、摘要、引用语义位置、canonical LaTeX、图表叙事、附录/README 与论文内 AI 披露；正式数字只消费 Solver Result Certificate，不重新计算或改写科学结果。适合“重写摘要”“优化正文”“处理引用/公式/图表”“让论文更像竞赛论文”等任务。若问题会改变模型、evaluator 或正式结果，路由回 math-modeling-solver；已冻结结果后的代码人味化、最终 Word/PDF/ZIP 与独立 AI 使用详情交给 math-modeling-finalizer。
Ready to connect
- View details
math-modeling-solverSkillDocs & knowledge
数学建模竞赛通用协作求解与结果认证 Skill。用于新题理解、Problem Contract、独立建模发散、Web Research 接入、模型/算法选择、formal evaluator、复杂优化搜索空间审计、程序求解、结果验证与 Result Certificate。尤其适用于“怎么建模”“为什么搜不到更好结果”“evaluator 是否正确”“代码是否真正符合题意”等会改变科学结果的问题。论文措辞、引用与 DOCX 版式交给 math-modeling-paper；已冻结结果后的代码人味化与最终交付交给 math-modeling-finalizer。
Ready to connect
- View details
meeting-studioSkillDocs & knowledge
Run the Navin Meeting studio desk - capture notes/transcripts, custom summary templates, speaker labels, calendar-linked meetings, chat-with-meeting Q&A, exports, and local audit-aware reports. Use when the user opens #/meeting or runs /meeting.
Ready to connect
- View details
memory-forensicsSkillDocs & knowledge
Master memory forensics techniques including memory acquisition, process analysis, and artifact extraction using Volatility and related tools. Use when analyzing memory dumps, investigating incidents, or performing malware analysis from RAM captures.
Ready to connect
- View details
memory-safety-patternsSkillDocs & knowledge
Teaches your agent memory-safe coding patterns like RAII, ownership, smart pointers, and resource management.
Ready to connect
- View details
metabolicinputSkillDocs & knowledge
Pass-through process that prepares Seurat object for metabolic landscape analysis. Routes the processed Seurat object to downstream metabolic analysis processes (MetabolicExprImputation, MetabolicPathwayActivity, MetabolicFeatures, MetabolicPathwayHeterogeneity). **Note**: This process requires no d
Ready to connect
- View details
modeling-delivery-gateSkillDocs & knowledge
Final delivery checker for support archives, DOCX/static checks and exact-PDF visual review. Missing exact PDF remains NOT_VERIFIED.
Ready to connect
- View details
on-call-handoff-patternsSkillDocs & knowledge
Gives your agent proven patterns for smooth on-call shift handoffs with continuity and context transfer.
Ready to connect
- View details
ontoindex-cliSkillDocs & knowledge
Use when the user needs to run OntoIndex CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\"
Ready to connect
- View details
openapi-spec-generationSkillDocs & knowledge
Lets your agent create and check OpenAPI specification files from your code for API docs and contracts.
Ready to connect
- View details
patent-reviewSkillDocs & knowledge
Multi-round cyclic rigorous review of Chinese patent technical disclosure documents. Supports multi-dimension review (data flow closure, terminology consistency, state transition, formula completeness, error code routing, text-diagram consistency), round-by-round convergence, and optional auto-fix (
Ready to connect
- View details
patent-specification-writerSkillDocs & knowledge
Draft Chinese patent specification sections for invention, utility model, or design submissions, especially background technology and technical solution writeups, with intake guidance, prior-art-oriented analysis, terminology consistency, and document-ready output. Excludes claims drafting. Use when
Ready to connect
- View details
pcb-project-intakeSkillDocs & knowledge
RAG-backed. Inventory a bounded DipTrace project, its document identity, models, rules, connectivity, unknowns, and evidence before planning changes. Use when the user says “Inventory this DipTrace project before we plan work.”
Ready to connect
- View details
pdf-ocr-extractorSkillDocs & knowledge
Extract tables, forms, and text from PDFs and scans (OCR when needed), including multilingual docs. Use for contracts, invoices, and document intake.
Ready to connect
- View details
performance-auditorSkillDocs & knowledge
Profile and optimize applications - hot paths, N+1 queries, blocking I/O, caching, bundle size, memory, startup time. Use for /turbo, "why is it slow?", or pre-launch performance passes.
Ready to connect
- View details
plan-to-beadsSkillDocs & knowledge
Translate a polished markdown plan into self-contained beads in .beads/beads.jsonl. Every bead must be executable without reopening the plan. Use after the plan has converged.
Ready to connect
- View details
playcanvas-editor-api-realtimeSkillDocs & knowledge
Use when working with the PlayCanvas Editor API, realtime sync protocols, WebSocket endpoints, ShareDB, Operational Transformation (OT), or document collections.
Ready to connect
- View details
playcanvas-editor-version-controlSkillDocs & knowledge
Use when working with the PlayCanvas Editor version control system (VCS), managing checkpoints, handling branches, merging histories, or resolving document conflicts.
Ready to connect
- View details
postmortem-writingSkillDocs & knowledge
Guides your agent through writing blameless incident postmortems that help teams learn and prevent repeat incidents.
Ready to connect
- View details
pptproSkillDocs & knowledge
Create visually polished, editable PPT/PPTX presentations in a clean PPTPRO style. Use when the user asks for a beautiful, designed, non-generic PowerPoint deck, especially course presentations, reading applications, source-backed slides, scripts matched to slide pages, or requests to avoid AI-looki
Ready to connect
- View details
presentation-designerSkillDocs & knowledge
Design the story, structure, and slide-by-slide plan of presentations - pitch decks, client presentations, reports. Use before generating any deck.
Ready to connect
- View details
professional-writerSkillDocs & knowledge
Write business letters, reports, memos, meeting notes, and formal documents in French, English, or Arabic. Use for any professional document that must be polished and correctly toned.
Ready to connect
- View details
protocol-reverse-engineeringSkillDocs & knowledge
Guides your agent through capturing and analyzing unknown network protocols for security research and debugging.
Ready to connect
- View details
public-git-workflow-expert-baseSkillDocs & knowledge
Git workflow knowledge base. Extends netresearch/git-workflow-skill with upstream general Git knowledge, adding team commit conventions, branching strategy, Gitea workflow, and mirror sync experience. Intended for downstream skills such as devlab-git-workflow-expert to inherit via extends.
Ready to connect
- View details
public-kafka-expert-baseSkillDocs & knowledge
Kafka knowledge base. Covers Topics/Partitions, Consumer Groups, Producer/Consumer Config, Serialization, Exactly-Once, and Rebalancing. Intended for devlab-middleware-expert to inherit via extends.
Ready to connect
- View details
public-rabbitmq-expert-baseSkillDocs & knowledge
RabbitMQ knowledge base. Covers Exchange Types, Queue & Routing, Durability, Dead Letter, Confirmations. Intended for devlab-rabbitmq-usage to inherit via extends.
Ready to connect
- View details
rag-knowledge-builderSkillDocs & knowledge
Build and evaluate RAG corpora - ingest, chunk, embed, index, and spot-check retrieval quality. Use when creating knowledge bases for agents.
Ready to connect
- View details
readme-writerSkillDocs & knowledge
Use this skill to write or revise a README.md for a Shipfox workspace package (libs/*, tools/*). It applies the shared package README standard and repository prose policy. Trigger on write a README, draft README, rewrite README, document this package, or improve the README.
Ready to connect
- View details
reasoning-doctrineSkillDocs & knowledge
The working method for every nontrivial task: frame the objective, ground load-bearing facts, converge on a route, execute without drift, and verify before delivery. Use for analysis, planning, implementation, debugging, document work, reviews, and multi-stage tasks.
Ready to connect
- View details
relinkSkillDocs & knowledge
Scan notes and suggest missing backlinks between related topics
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.
53,462 of the 53,895 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.