Learn how to get the most out of AI SkillsBank.
To begin using AI SkillsBank, create an account with your email address. You'll receive a verification email — click the link to activate your account, then log in.
Once logged in, you can browse public skills from the community, create your own, and organize them with categories and tags.
There are two ways to create a skill:
Each skill has:
To edit a skill, open it and click Edit. Each edit automatically saves a snapshot of the previous version so you can always go back.
The AI Skill Creator generates a complete, structured skill from a plain-English description. Click ✨ AI Create in the dashboard header to open it.
{{variable}} placeholders for dynamic inputsThe AI creates one skill for one task. If your description covers multiple platforms or formats, it picks the primary one and notes that you can use the Skill Optimizer to convert for other targets later.
| Feature | Free | Premium |
|---|---|---|
| Model | Claude Haiku 4.5 | Haiku 4.5 or Sonnet 4.6 |
| Output token budget | 4,096 tokens | 16,000 tokens |
| Supporting file size | 300–500 tokens each | 500–2,000 tokens each |
The Skill Optimizer converts an existing skill to a specific agent platform or harness format. It's useful when you want to take a skill you've built in AI SkillsBank and deploy it somewhere else without rewriting it from scratch.
Premium feature. Open any skill, click 🔄 Optimize, choose a target format, and click Optimize.
{{variable}} syntaxThe optimizer returns the converted content plus brief notes explaining the key adaptations. Use the Copy button to copy the optimized text to your clipboard.
Use {{variable_name}} placeholders anywhere in your skill content. When you use the skill, you'll be prompted to fill in each variable before copying the final output.
This is useful for reusable instructions where only certain details change — for example, {{project_name}}, {{language}}, or {{tone}}.
You can attach supporting files (reference docs, example scripts, config files) to any skill. These files are bundled with the skill and included when someone forks it, so the full context travels with the instruction.
Every time you edit a skill, the previous version is saved automatically. You can:
Evals turn your skills into tested behaviors. Attach test cases to any skill you own, run them on demand, and see exactly which assertions pass or fail — before an edit slips into production.
Open any skill you own from your dashboard, then click the ✓ Evals button at the bottom of the detail view (next to History). The panel shows a header badge like "3/4 passing", a list of your evals, and an Add eval button. The button is owner-only — collaborators on team-shared skills cannot create evals.
Each eval has three parts:
{{variable}} values to substitute into the skill content. Switch modes with the toggle in the form.| Type | Passes when… |
|---|---|
contains | Output contains the given text (toggle "ignore case" if needed). |
not_contains | Output does not contain the given text. |
matches | Output matches the supplied regex pattern. |
min_length | Output is at least N characters long. |
max_length | Output is at most N characters long. |
judged_pass | An LLM judge (Claude Haiku) decides the output meets your natural-language criterion, e.g. "Response uses a warm but professional tone and addresses the customer by name." |
You can mix and match. judged_pass is the most flexible but slowest — capped at 3 per eval to control cost.
Click the ✎ (edit) icon on any eval row to open the form pre-filled with that eval's name, input, and assertions. Save your changes and the eval is updated — run history is preserved so you can see how the same test behaved before and after the edit.
Once a public skill has at least one eval with a recorded run, a small badge appears on its public page (e.g. "✓ 12/12 evals passing") right alongside the fork count and review stars. This signals to people considering forking your skill that the behavior is tested.
judged_pass max (each judged assertion costs an extra LLM call).contains, matches, min_length) for structural guarantees, and reserve judged_pass for tone, persona, or correctness criteria a regex can't express.Found a public skill you'd like to customize? Click Fork to copy it into your own library. Forked skills are independent — you can edit them freely without affecting the original. The fork count on the original skill shows how many users have built on it.
Toggle visibility at any time from the skill detail view.
Public skills can be rated and reviewed by other users. Leave a 1–5 star rating and optional written feedback. Each user can submit one review per skill — submitting again updates your existing review. Average ratings are shown on skill cards to help surface the best content.
Public skills are automatically scanned for security issues before they're shared with the community. AI SkillsBank uses a three-tier scan pipeline to detect risky content, including malicious patterns, prompt injection attempts, and exposed secrets.
Scan results appear on:
Each scanned skill shows:
You can also manually re-run a scan from the skill detail page.
Important: A passed scan reduces risk, but does not guarantee a skill is safe in every environment. Review public skills before using them with production systems or sensitive data.
Premium users can test their skills before publishing using the ⚡ Test Sandbox button on any skill detail page. There are two modes:
An AI prompt engineer evaluates your skill and returns structured feedback:
You can optionally include a sample test message to also get feedback on how the agent would respond to a specific input.
Your skill content becomes the agent's system prompt verbatim. Send any message and see how an AI following those instructions would actually respond — useful for catching edge cases before going public.
If your skill uses {{variable}} placeholders, the sandbox will show fill-in fields for each one. Values you enter are substituted into the skill before the test runs, so you're testing the final rendered output.
Choose between Claude Haiku 4.5 (fast) or Claude Sonnet 4.6 (deeper analysis) for each test run.
The free tier allows up to 10 skills. AI SkillsBank Premium is $5/month and includes:
Cancellations take effect at the end of your current billing period. Your skills and data are not affected if you cancel.
Create a team to collaborate with others:
Once in a team, you can share private skills with that team so all members can access them.
AI SkillsBank supports the Model Context Protocol (MCP), allowing MCP-compatible tools like Claude Desktop, Claude Code, Cursor, and Windsurf to connect directly to the public skills library.
Once connected, your AI tools can:
search_skillslist_user_skillsget_skilluse_skillProduction endpoint: https://aiskillsbank.com/mcp/
Important: Include the trailing slash (/mcp/, not /mcp).
Every user has a public portfolio page that showcases their public skills. Share your portfolio link to highlight your best AI agent instructions.
Have a question, found a bug, or want to request a feature? Reach out to us at admin@aiskillsbank.com and we'll get back to you as soon as we can.