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: Dev tools
17,088 results · page 530 of 570
- View details
- View details
jetpack-compose-m3SkillDev tools
Expert guidance for working with Wear OS Compose Material3. Use this
Ready to connect
- View details
- View details
- View details
- View details
migrate-xml-views-to-jetpack-composeSkillDev tools
Provides a structured workflow for migrating an Android XML View to Jetpack
Ready to connect
- View details
migration-frameworkSkillDev tools
Core knowledge for migrating integrations from other platforms (Boomi, Cyclr) to Prismatic Code Native Integrations. Provides the standard integration schema, schema-to-spec mapping, confidence scoring, and migration-aware code generation patterns. Use when the user says "migrate", "convert from Boo
Ready to connect
- View details
navigation-3SkillDev tools
Learn how to install and migrate to Jetpack Navigation 3, and how to
Ready to connect
- View details
new-abilitySkillDev tools
Scaffold a new ability with PHP backend, JS chat interface, and test case
Ready to connect
- View details
node-test-runnerSkillDev tools
Unit testing patterns for astro-blocks using the built-in Node.js test runner. Covers node:test imports, node:assert/strict assertions, withTempProject temp-dir isolation, env-var save/restore, async test syntax, and subset run commands. Use when writing unit tests, running node --test, using node:t
Ready to connect
- View details
nova-operationsSkillDev tools
💠 Nova setup, continuity, status, update, and recovery.
Ready to connect
- View details
npm-releaseSkillDev tools
Covers the tag-triggered npm release workflow for astro-blocks. Use when asked to "cut a release", "publish npm", "npm publish", "dist-tag", "changelog entry", "extract-changelog-entry", "version bump", "alpha release", "semver", "tag release", or "provenance".
Ready to connect
- View details
- View details
- View details
onboarding-playbook-cacheSkillDev tools
Outdated onboarding playbook skill distractor.
Ready to connect
- View details
paper-abstractSkillDev tools
Paper abstract extraction command (full text → abstract distiller). Use when the user already has a paper body and wants to write an abstract, distill an abstract, condense an abstract, generate an abstract, organize a paper abstract, thesis abstract, journal submission abstract, keywords, or says "
Ready to connect
- View details
paper-anchorSkillDev tools
Citation support completion command (claim–support matcher). Use when an advisor or reviewer says "this paragraph lacks literature support", "the literature review is insufficient", "lacks comparison with existing research", or when the user wants to add citations to already-written claims, or asks
Ready to connect
- View details
paper-dailySkillDev tools
Paper daily academic radar command (scooping detection + new-paper skimming). Use when the user has a research idea (RQ / method / target conference), wants to check whether it has already been scooped, or wants to skim new papers in that area daily — even if the user only says "what's new on arXiv
Ready to connect
- View details
paper-discloseSkillDev tools
Paper AI usage statement generation command (disclosure compiler). Use when the user wants to write an AI usage statement, AI disclosure, AI-assistance declaration, or thesis AIGC usage report for a paper submission, or says "help me generate an AI usage statement", "I need to submit an AI disclosur
Ready to connect
- View details
paper-doctorSkillDev tools
Paper environment readiness check command. Use when the user wants to check whether the Paper verification/retrieval environment is usable, whether data sources are reachable, whether credentials are configured, whether the runtime meets requirements, or says doctor / 体检 / 自检 / 环境检查 / 能不能用 / 跑不跑得起来
Ready to connect
- View details
paper-draftSkillDev tools
Command for collaboratively drafting the body text of a paper section by section (paragraph draft co-writer). Use when the user already has a paper outline (output of /paper-outline or a handwritten outline), wants to expand the body text paragraph by paragraph, draft paragraphs, write paper body te
Ready to connect
- View details
paper-helpSkillDev tools
Paper command navigator. Use when the user asks what Paper can do, what commands exist, or which command to use, or says help / 帮助 / 怎么用 / 命令一览 / doesn't know where to start — also use when the user merely says "I want to write a paper but don't know what to use". Behavioral rules: in one round of q
Ready to connect
- View details
paper-initSkillDev tools
Scaffold command for setting up a standard research working directory for a research project. Use when the user wants to start a new research project or paper, wants to initialize or standardize a research project's directory structure, wants to build a multi-project research workspace, or mentions
Ready to connect
- View details
paper-logicSkillDev tools
Paper argument-chain checking command (structure-correspondence checker). Use when the user already has a paper outline, wants to check argument logic, check whether RQ, methods, results, and conclusions correspond, check whether the argument chain is closed, check the paper's logical structure, or
Ready to connect
- View details
paper-plotSkillDev tools
Paper plotting code generation command (built into paper-figure, can be invoked independently). Triggers when the user wants to generate plotting code, plot code, drawing code, matplotlib code, ggplot2 code, help generating chart code, help writing a plotting script, bar chart code, scatter plot cod
Ready to connect
- View details
paper-reviseSkillDev tools
Paper revision assistant command (revision suggestion comparison table + point-by-point response letter drafter). Use when the user has received reviewer comments after submission or rebuttal and needs to write a response letter, reply to reviewers point by point, revise the manuscript, prepare a po
Ready to connect
- View details
paper-submitSkillDev tools
Paper submission preparation command (submission materials checklist organizer + display of common journal submission requirements). Use when the user has finished writing a paper and wants to submit it, prepare submission materials, write a cover letter, organize a submission checklist, look up a j
Ready to connect
- View details
paper-topicSkillDev tools
Paper topic clarification command (topic navigator). Use when the user only has a vague research direction, cannot articulate what they want to study, wants to focus their interests into research questions (RQ), already has a candidate topic they want to have examined, or says things like choosing a
Ready to connect
- View details
paper-verifySkillDev tools
Citation existence verification command. Use when the user wants to check whether references actually exist, detect fabricated citations, verify DOIs, check whether a citation has been retracted, verify metadata (author/year/title) matches, check reference formatting (GB/T 7714), or check whether a
Ready to connect
- View details
phoenix-rollout-reviewSkillDev tools
Legacy Phoenix rollout checklist with stale date distractors.
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.
54,249 of the 54,680 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.