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 143 of 148
- View details
add-agentSkillDocs & knowledge
Scaffold a new Forge subagent (planner/architect/executor/reviewer/debugger/memory-style).
Ready to connect
- View details
ai-adoption-reportSkillDocs & knowledge
Use this skill to compare flow-metrics JSON outputs and produce a Markdown comparison report -- "how do our flow metrics now compare to pre-AI?", "within Q4 did AI-tagged tickets behave differently from untagged?", "what does Q4 look like across all teams in the program?". Three modes -- baseline (t
Ready to connect
- View details
author-product-docsSkillDocs & knowledge
Create, revise, retrofit, audit, or verify product documentation — pack READMEs, journeys, tutorials, how-to guides, reference pages, and explanations. Use when asked to write, improve, restructure, audit, or verify user-facing documentation, fix a pack README, create a guide for a feature, update a
Ready to connect
- View details
backup-rollbackSkillDocs & knowledge
Snapshot configs, memory, and skills before risky edits, and define a rollback path. Use before bulk refactors, migrations, or skill/config changes.
Ready to connect
- View details
br-openapiSkillDocs & knowledge
Generate or serve better-route 1.1 OpenAPI 3.1 documents from Router/Resource/Woo contracts. Use for OpenApiExporter, OpenApiRouteRegistrar, contracts, contractsFromSources, route args to parameters, explicit parameter overrides, custom responses, OPTIONS 204, strictSchemas, components, securitySche
Ready to connect
- View details
captionSkillDocs & knowledge
Use when you need a social media caption for any platform. Supports brand_context for voice/tone. Model-agnostic. Part of brand-loom; hosted brand-memory version at neoxra.com.
Ready to connect
- View details
component-contractSkillDocs & knowledge
Design a UI component's public interface — props/slots/events, controlled vs. uncontrolled ownership, composition patterns, lifecycle contract, and usage documentation — before writing any implementation. Triggers on "design the public contract for a shared date picker", "define the props, events, a
Ready to connect
- View details
component-docsSkillDocs & knowledge
Generate or update component documentation with usage examples, props tables, and Storybook stories. Use when documenting new components, creating usage examples, or setting up Storybook stories.
Ready to connect
- View details
context-driven-developmentSkillDocs & knowledge
Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a `conductor/` directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the proj
Ready to connect
- View details
ctaSkillDocs & knowledge
Use when you need call-to-action copy for buttons, banners, or closing lines. Generates multiple CTA variants. Model-agnostic. Part of brand-loom; hosted brand-memory version at neoxra.com.
Ready to connect
- View details
devlab-test-expertSkillDocs & knowledge
Testing expert knowledge base. Contains expert-level knowledge such as testing best practices, troubleshooting guides, test strategy design, and performance optimization advice, for reference by other testing skills.
Ready to connect
- View details
diag-container-oomSkillDocs & knowledge
Full-chain troubleshooting for container OOM. Traces from dmesg OOM killer → cgroup memory limits → Docker/Compose memory settings → swap → application memory analysis to locate the root cause and output fix recommendations.
Ready to connect
- View details
diag-k8s-node-pressureSkillDocs & knowledge
K8s node resource pressure troubleshooting. Full-chain diagnosis of CPU/Memory/Disk/PID Pressure: kubectl top → describe node → conditions → eviction events → scheduling analysis, with structured reports and mitigation recommendations.
Ready to connect
- View details
diptrace-datasheet-rulesSkillDocs & knowledge
RAG-backed. Extract auditable schematic, package, footprint, and PCB layout requirements from official component documents into project rules. Use before choosing or placing physical parts, checking a pin map, or resolving component-specific requirements; «требования из даташита». Use when the user
Ready to connect
- View details
docs-writerSkillDocs & knowledge
Keeps documentation in sync with the code: README, usage and related docs when a public API or behavior changes. Leaves no dead or misleading docs behind.
Ready to connect
- View details
documentation-designSkillDocs & knowledge
Use when someone asks how a documentation site, help center, API reference, or guide set should be organized so readers reach first value. Produces content-type, information-architecture, and navigation specifications that scale with the corpus. Use `conversion-design` for marketing surfaces and `in
Ready to connect
- View details
easyeda-lcsc-sourcingSkillDocs & knowledge
Fetch real LCSC/EasyEDA component catalog data over plain HTTPS: resolve an MPN to its LCSC part code, download the combined symbol+footprint JSON from the EasyEDA API, grab the official datasheet PDF, and convert the geometry into a DipTrace .elixml library fragment for schematic/PCB builds. Use wh
Ready to connect
- View details
event-contractSkillDocs & knowledge
Use when authoring an AsyncAPI event contract from requirements, user stories, or domain models. Applies a pluggable event-design standard (Zalando by default) as hard constraints and composes a swappable message envelope (CloudEvents by default) to produce a complete, validated AsyncAPI document fo
Ready to connect
- View details
faqSkillDocs & knowledge
Use when you need FAQ items from a body of text. Generates 3-6 Q&A pairs. Model-agnostic. Part of brand-loom; hosted brand-memory version at neoxra.com.
Ready to connect
- View details
final-delivery-cleanSkillDocs & knowledge
Strip workflow notes, engineering meta text, status remarks, workspace references, and other process-facing language from any final deliverable such as a PPT, DOCX, PDF, report, manuscript, or submission package. Use when preparing a final export, submission-ready artifact, or client-facing handoff.
Ready to connect
- View details
Gardening Skills WikiSkillDocs & knowledge
Maintain skills wiki health - check links, naming, cross-references, and coverage
Ready to connect
- View details
hadsSkillDocs & knowledge
Lets your agent write, convert, and validate technical documentation formatted for both humans and AI models.
Ready to connect
- View details
hashtagsSkillDocs & knowledge
Use when you need hashtags for social media posts. Generates deduped, count-bounded sets. Model-agnostic. Part of brand-loom; hosted brand-memory version at neoxra.com.
Ready to connect
- View details
hookSkillDocs & knowledge
Use when you need scroll-stopping hooks or headlines for a topic. Model-agnostic (OpenAI/Anthropic/Gemini/Ollama). Part of brand-loom; hosted brand-memory version at neoxra.com.
Ready to connect
- View details
iam-best-practicesSkillDocs & knowledge
Least-privilege cloud IAM: policy scope, privilege-escalation paths, permissions boundaries, workload identity over static keys, MFA enforced by policy, cross-account trust, and separating deploy from runtime. Use when generating IAM policies, roles, or trust documents, wiring CI/CD service accounts
Ready to connect
- View details
identify-perspectivesSkillDocs & knowledge
Enumerate the named camps on a contested topic before research begins. Builds the perspective scaffold that `/source-map` and `/compare-hypotheses` consume downstream in the decision pipeline. Grounded in Wikipedia NPOV (neutral point of view — fairly represent significant views) and ACH (competing
Ready to connect
- View details
informational-designSkillDocs & knowledge
Use when someone asks how an article, news page, editorial feature, or other long-form informational surface should support sustained reading. Produces typography, hierarchy, and reading-flow specifications for the surface. Use `documentation-design` for task/reference systems, `conversion-design` f
Ready to connect
- View details
markdown-to-docxSkillDocs & knowledge
Fill a branded Word template from a Markdown artifact — turn this Markdown into a Word doc, produce a report, a memo, a statement of work, or a branded .docx. The deterministic script fills the Jinja fill-points a designer placed in the template (front-matter, headings, lists, tables map onto them),
Ready to connect
- View details
markdown-to-pptxSkillDocs & knowledge
Fill a branded PowerPoint template from a Markdown artifact — turn this into slides, build a slide deck or presentation, produce a branded .pptx. The deterministic script inspects the template's layout placeholders and projects your Markdown (front-matter, headings, lists, tables) onto them, so the
Ready to connect
- View details
math-modeling-finalizerSkillDocs & knowledge
数学建模项目收口与终审 Skill。用于正式结果已基本冻结后的参赛者尺度代码简化与行为回归、最终完整复审、AI 工具使用详情 DOCX、Word/PDF 排版检查、支撑材料 ZIP 与提交前卫生检查。典型请求包括“结果已经定了，把代码改得更像学生项目”“最后完整审一遍”“检查最终 Word/PDF”“生成 AI 使用详情和支撑材料”。若需要重新建模、修改 evaluator 或正式结果，路由回 math-modeling-solver；正文、摘要、引用语义或公式写作问题路由回 math-modeling-paper；提交后的项目复盘/教学交给 math-modeling-growth。
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.