Imprint skill
A skill records how you work with an agent, keeps it in a short text profile next to your code and carries it between AI tools.
- 104 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The skill writes a profile file into the project and decides when to act without confirmation.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/imprintDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill writes a profile file into the project and decides when to act without confirmation.
This is third-party code. Review the repository files before installing.
What it does
Imprint is a single skill that on first run talks to the user not about the project but about themselves: how they debug, plan, write commits and what they prefer. The answers become a portable profile under 500 tokens, stored as a plain text file next to the code. In later sessions the agent applies the profile to code style, reviews, plans and git habits. The skill also decides when to act at once, when to ask first and when to stop at a line the user drew. The profile can be read, edited and kept in git.
Who it is for. Developers who work with several AI agents and are tired of re-explaining their style and code standards to each one.
Good fit when
- You are moving from Claude Code to Cursor or Codex and want to keep your working habits.
- A new session starts with the same explanations about commits and reviews.
- A team wants a shared profile a colleague can pull from git.
- The agent asks for confirmation too often or, the other way round, acts without asking.
Not a fit when
- The task is one-off and a profile will not be reused.
- A ready review regulation with strict rules is wanted rather than adaptation to a personal style.
- The project forbids storing personal-preference files next to the code.
Example request
Run Imprint and ask me how I debug and write commits, then save the profile next to the project.Limitations
It is one skill, and the areas the README lists, such as review, debugging and SEO, are covered briefly and do not replace dedicated specialist skills. The profile appears after the conversation and updates as you work, so the first sessions give little benefit. For other agents the `SKILL.md` file is copied into their skills directory by hand, and each path differs. The VS Code extension installs copies of the skill into several directories at once. The latest commit in the repository dates from September 2026.
How to disable. Delete the `imprint` folder from the agent's skills directory, for example `~/.claude/skills/imprint`. Remove the profile file next to the code separately or keep it in git.
FAQ
Where is the profile stored?
In a plain text file next to the code. It can be read and edited, kept in git and shared with colleagues.
Which agents are supported?
The README lists Claude Code, Cursor, Codex CLI, Copilot, Gemini CLI, Windsurf, Cline, Roo, Trae and Hermes. Most need `SKILL.md` copied by hand.
How do I install it in Hermes?
With `hermes skills install ilang-ai/Imprint`.
How large is the profile?
The core stays under 500 tokens. Project and progress layers can grow.
Is there a VS Code extension?
Yes. The extension installs `SKILL.md` into 14 agent directories on the machine at once.
Discussion
No questions or reviews yet.
Related
SkillsA skill that distills chats, documents and public sources into a reusable person profile for AI agents and compatible bots
A skill that distills a person's digital twin from chat logs and documents into a ready Agent Skill package
Skill setting up Markdown file memory for Codex via AGENTS.md: profile, rules, lessons, errors and capability requests.
Self-learning
self-learning-skills
A meta-skill that saves a hard-won working procedure as a new skill or rule, so the next session starts already knowing it
A CLI skill manager for AI agents: install from repositories, translate between agent formats and deploy into their configs
Open infrastructure for agents that learn from experience: session traces, a knowledge base and skill packs via CLI, MCP and API
README in short
The profile uses a `.dna.md` format with layers: core, facts, projects, lessons, progress and runtime. Tentative genes expire under the DECAY rules.