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: AI & models
9,028 results · page 301 of 301
- View details
rseng-pair-programmingSkillAI & models
Covers the agent as an effective pair programmer and pull-request review buddy for research software: driver-navigator collaboration with think-aloud reasoning, ping-pong test-driven pairing, keeping the human in charge of scientific decisions, pre-review of pull requests before human reviewers see
Ready to connect
- View details
rseng-performance-profilingSkillAI & models
Covers making research code faster with evidence: profiling before optimizing (py-spy and language-native profilers), interpreting hotspots, choosing optimizations by measured payoff, benchmark regression tracking with airspeed velocity (asv), and scaling measurements. Use when the user says their c
Ready to connect
- View details
rseng-project-kickoffSkillAI & models
Covers starting a new research software project with a short kickoff interview: asking the user the few questions whose answers actually change decisions (goal, software tier, stack, data sensitivity, openness, collaboration, compute, deadlines, and how much the agent may decide alone), then derivin
Ready to connect
- View details
rseng-project-scaffoldingSkillAI & models
Covers starting research software projects from maintained templates and keeping them in sync: choosing a generator (Copier, cookiecutter), scaffolding a Python package, retrofitting template structure, pulling template upgrades into generated projects, and picking a pyproject build backend. Use whe
Ready to connect
- View details
rseng-quality-frameworkSkillAI & models
The entry point and router for this pack: explains the research software quality framework - community-standard quality dimensions, measurable indicators and the three-tier model (analysis code, prototype tools, infrastructure) - and routes to the right companion rseng-* skill. Use PROACTIVELY at th
Ready to connect
- View details
rseng-regulatory-complianceSkillAI & models
Covers checking research code and data against data-protection and AI regulation: GDPR obligations in code (personal data discovery, minimization, pseudonymization vs anonymization, retention, data-subject rights, DPIA triggers), the EU AI Act (risk tiers, research carve-out, transparency duties), a
Ready to connect
- View details
rseng-reproducibilitySkillAI & models
Covers end-to-end computational reproducibility: making a project's results regenerable with one command, determinism and seed discipline, research compendium structure, replication packages for papers, Binder-launchable repositories, artifact evaluation and reproducibility badges. Use PROACTIVELY w
Ready to connect
- View details
rseng-reproducible-environmentsSkillAI & models
Covers making research software environments reproducible: pinning a language version and its dependencies in a per-project virtual environment, choosing a package/environment manager, and packaging code and its full stack into a container. Use when the user asks how to set up venv/conda/poetry/uv/r
Ready to connect
- View details
rseng-research-integritySkillAI & models
Covers integrity checks on research outputs before submission or release: statcheck/GRIM-style consistency of reported statistics, agreement between manuscript numbers and pipeline outputs, retraction screening of cited work, sanity checks on tables and figures against the data, and an auditable pre
Ready to connect
- View details
rseng-science-communicationSkillAI & models
Covers communicating research software outward to research audiences: supporting the user's software papers (JOSS/SoftwareX-style) with outlines, gathered material and structure - never writing a submission-ready manuscript - plus release announcements, lay summaries of what the software does, talk
Ready to connect
- View details
rseng-software-peer-reviewSkillAI & models
Covers community peer review of research software: preparing a package for JOSS, pyOpenSci or rOpenSci submission, self-checking against their review criteria before submitting, writing the paper or statement of need, responding to reviews, and acting as a reviewer or CODECHECK-style codechecker who
Ready to connect
- View details
rseng-software-publishingSkillAI & models
Covers publishing research software through its distribution channels: packaging for and releasing on package indexes (PyPI, conda-forge, CRAN and ecosystem equivalents), registering in research software registries, submitting to software journals (JOSS-style), and choosing the channel mix for a pro
Ready to connect
- View details
rseng-software-reuseSkillAI & models
Covers discovering and reusing existing research software instead of rebuilding it, using Research Software Directory (RSD) instances such as research-software-directory.org and helmholtz.software. Use PROACTIVELY when a research project is about to implement functionality that likely already exists
Ready to connect
- View details
rseng-storytellingSkillAI & models
Covers telling the story of research data, software and projects to broad audiences: narrative structure for data stories, turning milestones into human-centered stories, and citizen-science engagement - recruiting contributors, closing the feedback loop with data stories, honest narrative that neve
Ready to connect
- View details
rseng-testingSkillAI & models
Covers how to test research software: choosing test types and levels (unit, integration, system, regression, property-based, golden-master), test frameworks and coverage, TDD, validating analysis code against reference cases, and taming CI testing matrices across compilers, platforms and dependency
Ready to connect
- View details
rseng-trainerSkillAI & models
Covers teaching research software skills while working: turning everyday coding moments into short, learner-centered lessons using Carpentries/CodeRefinery-style pedagogy (objective-led episodes, formative checks, error normalization), and routing learners to canonical training materials. Use when a
Ready to connect
- View details
rseng-version-control-reviewSkillAI & models
Covers using version control effectively for research software and the PR-time review process: choosing a VCS, branching and commit practice, authorship and signatures in commit metadata (author/committer identity, Co-authored-by trailers, signed commits and tags, .mailmap), collaboration on GitHub/
Ready to connect
- View details
sensitive-disclosureSkillAI & models
Detects PII, credentials, and secrets passed to LLM APIs or embedded in system
Ready to connect
- View details
skill-benchmarkingSkillAI & models
Skill and prompt benchmarking expertise for measuring latency, accuracy, token cost, and token-budget compliance across variants
Ready to connect
- View details
suicide-risk-assessment-protocolSkillAI & models
Suicide risk assessment using the Columbia Protocol (C-SSRS) and SAFE-T framework — auto-prompts when warning indicators appear
Ready to connect
- View details
swift-focusengine-proSkillAI & models
Reviews, writes, and fixes focus management code for all Apple platforms (tvOS, iOS/iPadOS, watchOS, visionOS, macOS), covering SwiftUI, UIKit, AppKit, and RealityKit. Use when reading, writing, or reviewing apps that handle focus, hover, key view loops, or Digital Crown navigation.
Ready to connect
- View details
text-summarizerSkillAI & models
Lets your agent summarize text on your machine without sending it anywhere.
Ready to connect
- View details
tiny-vue-skillSkillAI & models
When developing with the TinyVue component library (@opentiny/vue) or configuring TinyVue projects for internationalization, theme configuration, form validation guidelines, automatic component imports, etc., be sure to read this skill. It provides strict API documentation and examples, as well as l
Ready to connect
- View details
token-smugglingSkillAI & models
Detects user input passed to LLMs without Unicode normalization, allowing RTL
Ready to connect
- View details
update-provider-modelsSkillAI & models
Add new or remove obsolete model IDs for existing AI SDK providers. Use when adding a model to a provider, removing an obsolete model, or processing a list of model changes from an issue. Triggers on "add model", "remove model", "new model ID", "obsolete model", "update model IDs".
Ready to connect
- View details
weather-forecastSkillAI & models
Fetch 7-day weather forecasts from Open-Meteo API. ALWAYS use get_coordinates.py first when given city names to look up coordinates, then use get_forecast.py with those coordinates. Use for weather forecasts, weather data, or temperature trends.
Ready to connect
- View details
webmcp-cli-skillSkillAI & models
Installation and execution guide for third-party AI Agents: how to use webmcp-cli to interact with browser pages. Includes domain-specific tool descriptions for pages with injected WebMCP tools.
Ready to connect
- View details
webmcp-sdk-skillSkillAI & models
指导如何使用 WebMCP SDK库去开发WebAgent的技能包，将前端应用快速智能化。它包含 TinyRemoter，WebMcpServer，WebMcpClient，createRemoter， AI-Extension插件开发的文档及指南。
Ready to connect
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
55,483 of the 55,914 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.