Works with the AI Agents you already use
My Style
Generate a personalized AI agent skill that matches your voice, code, and standards.
Free
My Style
Example session with this skill installed
Use my-style-gen considering my projects in ~/dev/web-apps and my specs in ~/Documents/specs. I'm a Senior Frontend Engineer.
- Read your context and instructions
- Compiled the my style
I have analyzed your TypeScript repositories and project specifications. The analysis identified a consistent preference for functional composition, specific documentation headers, and a terse, technical communication style.
I have generated and installed the dev-style skill to ~/.claude/skills/dev-style. I also updated the .gitignore files in your development directories to ensure this personal profile remains local.
Generated Personal Style Rules
| Category | Finding | Confidence |
|---|---|---|
| Code Idiom | Prefers const arrow functions over function declarations; uses early returns to minimize nesting. | High (Seen in 4 repos) |
| Documentation | Always includes a 'Side Effects' section in JSDoc for hooks; uses kebab-case for component folders. | High (Corroborated) |
| Communication | Uses "BLUF" (Bottom Line Up Front) for status updates; omits formal greetings in internal slack drafts. | Medium (Specs only) |
| Vocabulary | Consistently uses "component-local" instead of "private state"; refers to endpoints as "contracts". | High (Cross-source) |
Next steps
- Run the A/B test script:
~/.claude/skills/dev-style/ab-test/ab-test.sh --compareto see the style in action. - Review the generated
SKILL.mdin thedev-stylefolder to manually tweak any hedged rules. - Try asking your agent to "Draft a brief for the new auth module" and observe the idiom shift.
Connects securely to your tools. The creator never sees your data.
About this skill
Your agent writes well. It just doesn't write like you.
So the code it writes, the deck it drafts, the spec it fills in... all in a stranger's idiom: slower to read, deaf to the shorthand you actually use, and not quite yours by the time it ships. This fixes all three, once.

Point it at work you already produced: git repositories, specs, decks, spreadsheets,
contracts, notes. It reads each source, works out how you work and how you write, and
installs a skill called my-style that every future agent session follows.
- Faster review — the work and the prose explaining it read the way you write, and need fewer corrections
- Shared language — your vocabulary and shorthand travel with the skill, so a terse request is decoded the way a long-time colleague would decode it
- Personal touch — what you make with an agent still reads like your work
Works for any line of work, not just engineering (an engineer's sources are repositories, a product manager's are specs and decks, a lawyer's are filings — same method, same output). And it adopts the style, not the weakness: a modern model already writes a cleaner first draft than most of us, so each analysis agent filters as it reads. The goal is legibility, not forgery.
Requires author-identifiable material. Does not work on third-party code or documents where your contribution cannot be isolated via git logs or metadata.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Permissions
File Scopes