01
Find skills you didn’t know to look for
Start with the task, even when you don’t know the name of a skill. Your agent can search for relevant guidance.
Skills for the work in front of you
Make your AI agent do more.
Describe your task. 9octopus helps your agent discover and use relevant skills—even ones you didn’t know existed.
Connect once through MCP. No separate installation for each skill.
Requires Streamable HTTP and OAuth sign-in.
Task searches use OpenAI for semantic matching. Do not include secrets or repository contents.
Examples of MCP clients
ChatGPTClaude Desktop
Claude Code
Codex
Cursor
GitHub Copilot in VS Code
Gemini CLI
Cline
OpenCode
Kilo Code
Choose your agent for setup instructions. Availability depends on your client, plan, and workspace settings.
Start with an example task
From the public library
1,731 public skills
- a11y-auditUse for any accessibility audit or a11y fix (WCAG 2.2 A/AA, color contrast, compliance report, CI check) in React, Next.js, Vue, Angular, Svelte or HTML. Scans with a11y_scanner.py and checks contrast with contrast_checker.py, then fixes and re-verifies.
- ab-test-setupUse before planning or launching any A/B, split or multivariate test, or when asked if a result is significant. Sizes the test with sample_size_calculator.py and writes the hypothesis, metric and stop rule first, so it is not called early on noise.
- academy-guideStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
- access-lifecycleUse when preparing or running a user access review, checking that leavers lost their access, finding orphaned or ownerless service accounts, answering an auditor's access-control request for SOC 2, ISO 27001, PCI DSS, HIPAA or NIST 800-53, or checking whether a finished review campaign will hold up. Diffs the HR roster against account exports, tests the campaign for coverage, self-review, unremoved revokes and rubber-stamping, and maps every exception to the controls it breaks.
- accessibilityWCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。
- accessibilityAudit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible". Do NOT use for SEO (use seo), performance (use core-web-vitals), or comprehensive site audits covering multiple areas (use web-quality-audit).
- accessibility使用 WCAG 2.2 Level AA 标准设计、实施和审计包容性数字产品。运用此技能为 Web 生成语义 ARIA，并为 Web 和原生平台（iOS/Android）生成无障碍特性。
- accessibilityDesign, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels, accessibility traits and hints, focus management, contrast, target size, and screen-reader support. Use when building or auditing UI for accessibility compliance, keyboard navigation, or screen-reader support.
- ad-creativeUse for any ad copy request (RSA headlines, Meta, LinkedIn or TikTok ads, bulk variations), before writing. Checks every line against platform character limits and policy with ad_copy_validator.py. Campaign strategy and budgets: paid-ads.
- adversarial-reviewerTough, critical review of a diff or PR before merge, through hostile reviewer personas that catch shared blind spots. Use whenever the user wants a change torn apart, a harsh second opinion, or a self-review felt too agreeable.
- aeoUse when content should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization), before rewriting it. Scores E-E-A-T and structure with aeo_audit.py, rewrites with aeo_optimizer.py and logs citations with citation_tracker.py.
- agent-architecture-auditFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.
A task, in practice
Two small fixes.
A form you can use.
Follow a browser check from a vague “review this form” request to a labeled email field and a button you can reach with your keyboard.
Worked example · sample form01 / 03
You bring the task
“Check a signup form for accessible labels and keyboard operation.”
The sample form has visible email text that is not connected to its input, and a clickable Subscribe control that Tab skips.
Inspect the original sample →A real skill, loaded through 9octopus
Inspect the form in a browser.
We loaded the Playwright skill and used its snapshot → interact → check workflow.
- Accessible field names
- Keyboard navigation
- Submission feedback
The browser exposed an unnamed textbox and a generic Subscribe element. The agent still needed terminal access and an installed browser to perform the check.
The result, checked
A labeled field. A reachable button.
We added an associated label and a native button. Tab now reaches Subscribe; Enter completes the demo. Try it below. No data is sent or saved.
This verifies two behaviors in a sample form, not full accessibility conformance.
Read the input, changes, and checks →Find skills for this task
Task searches use OpenAI for semantic matching. Do not include secrets or repository contents.
From a request to a result
See what you can put to work.
Real skill releases, sample inputs, and outputs you can inspect.
Website owners and developers
Check a signup form with your AI agent
Find a missing label and an unreachable control in a sample signup flow, then verify the corrected form in a real browser.
Read the worked example Marketers and foundersTurn a product brief into an X launch post
Use a brand skill to turn product facts into a short announcement with a clear benefit and one next step.
Read the worked example Engineering teams and technical writersTurn rough notes into an architecture decision record
Capture a decision’s context, alternatives, and trade-offs so teammates can understand the reasoning later.
Read the worked exampleFrom task to capability
Connect once.
Use skills as you work.
Start with an agent that supports remote MCP over Streamable HTTP with OAuth sign-in. Connect it to 9octopus, then ask it to find a skill for the task in front of you.
- 01Connect via MCP
Add the 9octopus MCP server to your agent’s MCP client configuration and approve the connection.
- 02Describe the task
Ask your connected agent to find a relevant skill for the work you want to do.
- 03Load and use it
Your agent retrieves the skill instructions and supporting files it needs, then uses them to carry out the task.
Built around your work
Less searching.
More useful guidance.
02
One registry across clients
Use the same skill library across agents that support remote MCP connections. Connect each agent to 9octopus and keep your capabilities in one place.
03
No repeated manual installs
Once your client is connected, your agent can retrieve skill instructions and supporting files as needed. No copying each skill into each project.
Control stays with you.
- Exact versions
- Load a pinned release with instructions that stay consistent.
- Private libraries
- Keep your skills available to the agents you authorize.
- Your approval
- Choose which exact releases become public.
Put a skill to work