agentleFS
26zl26zl/universal-agent-skills/skills/no-ai-traces/SKILL.md

no-ai-traces

Skill2 starsChanged 40 days agoMITView on GitHub

Keep delivered work free of AI self-reference, with no Co-Authored-By trailers or generated-with footers in commits and pull requests, and no comments, documentation, or changelog entries that narrate AI involvement, prompts, or the editing session. Use when writing commits, merge or squash messages, pull requests, release notes, changelogs, code comments, or documentation; do not use to bypass a policy that explicitly requires AI disclosure.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never add a Co-Authored-By, Signed-off-by, or similar trailer naming an AI assistant, agent, model, or tool.

    line 13
  2. Distinctive:

    Never append generated-with footers, robot signatures, tool names, or promotional links to commit messages, merge or squash messages, pull …

    line 14
  3. Distinctive:

    Never write code comments, docstrings, documentation, or ticket updates that narrate prompts, AI involvement, the editing session …

    line 15
  4. Distinctive:

    Never change the configured Git author or committer identity.

    line 16
  5. Distinctive:

    Do not introduce new attribution or narration while amending, rebasing, squashing, or rewording existing content.

    line 18
  6. Distinctive:

    Keep AI mentions that are part of the product itself, its documented subject matter, or required third-party notices.

    line 19
  7. Distinctive:

    Never remove attribution or sign-off lines that a policy, license, or developer certificate of origin requires.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

No AI Traces

Delivered work records the accountable human author and describes the change, never the tool or session that produced it.

Rules

  • Never add a Co-Authored-By, Signed-off-by, or similar trailer naming an AI assistant, agent, model, or tool.
  • Never append generated-with footers, robot signatures, tool names, or promotional links to commit messages, merge or squash messages, pull request titles or bodies, changelogs, or release notes.
  • Never write code comments, docstrings, documentation, or ticket updates that narrate prompts, AI involvement, the editing session (including before/after or fix-history narration such as "previously… now…"), or a conversation with an assistant.
  • Never change the configured Git author or committer identity.
  • Preserve trailers and attribution that credit humans; only machine self-reference is removed or withheld.
  • Do not introduce new attribution or narration while amending, rebasing, squashing, or rewording existing content.
  • Keep AI mentions that are part of the product itself, its documented subject matter, or required third-party notices.

Boundaries

  • An explicit user, repository, or organizational requirement to disclose AI use wins; disclose in the mandated form instead of applying this skill.
  • Never remove attribution or sign-off lines that a policy, license, or developer certificate of origin requires.
  • This skill governs text about tooling only; it never hides which changes were made or misrepresents review status.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.