agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/github-profile-proof-updater/SKILL.md

github-profile-proof-updater

Skill3 starsChanged 6 months agoMITView on GitHub

Refresh and verify a GitHub profile or public proof layer. Use when the user wants to update GitHub profile visuals, replace README assets while preserving paths, audit profile image references, validate live GitHub rendering, prepare LinkedIn/X proof copy, or document a profile-refresh proof trail.

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. About 0 are common, 17 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈17

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to turn a GitHub profile or proof-layer refresh into a repeatable, public-safe workflow: update visuals, preserve working …

    line 10
  2. Distinctive:

    Do not publish, commit, push, upload, or post externally unless the user explicitly asks for that action.

    line 12
  3. Distinctive:

    Prefer replacing assets under the old filenames.

    line 22
  4. Distinctive:

    Keep known-good hero images unchanged when the user says the hero is already good.

    line 23
  5. Distinctive:

    Never use broad staging until the changed files are understood.

    line 32
  6. Distinctive:

    Prefer staging named files only.

    line 33
  7. Distinctive:

    If the user asks to commit/push, commit with a focused message and push the current branch.

    line 34
  8. Distinctive:

    Verify the live GitHub profile or public repo page after push.

    line 35
  9. Distinctive:

    Check that all updated visuals render.

    line 36
  10. Distinctive:

    Create or update the proof trail:

    line 39
  11. Distinctive:

    commit links or hashes

    line 41
  12. Distinctive:

    Do not include local machine paths, private vault structure, raw prompts, logs, credentials, browser cookies, private repo names, account …

    line 48
  13. Very specific:

    If a public artifact is being prepared, apply the github-safe-publisher rules and run its scanner when available.

    line 51
  14. Distinctive:

    When the user wants LinkedIn or X copy for the refresh:

    line 55
  15. Distinctive:

    Keep LinkedIn reflective and explanatory.

    line 58
  16. Distinctive:

    Keep X shorter, with one idea per post.

    line 59
  17. Distinctive:

    Add alt text for every image.

    line 60
  18. Distinctive:

    Put related X posts into a thread, not scattered comments.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

GitHub Profile Proof Updater

Overview

Use this skill to turn a GitHub profile or proof-layer refresh into a repeatable, public-safe workflow: update visuals, preserve working README paths, verify the live page, and create the social/proof trail that explains the update.

Do not publish, commit, push, upload, or post externally unless the user explicitly asks for that action.

Workflow

  1. Confirm the target repo and the source asset folder.
  2. Inspect the current repo state:
    • git status --short
    • README image references
    • target asset filenames and dimensions
  3. Preserve existing public paths unless the user asks for a rename in README.
    • Prefer replacing assets under the old filenames.
    • Keep known-good hero images unchanged when the user says the hero is already good.
  4. Copy or replace only the intended assets.
  5. Validate the changed media:
    • destination files exist
    • images are readable
    • dimensions/aspect ratios are plausible for the README layout
  6. Re-check README references.
    • Edit README only if an image path is broken, missing, or intentionally changing.
  7. Review the diff and repo status.
    • Never use broad staging until the changed files are understood.
    • Prefer staging named files only.
  8. If the user asks to commit/push, commit with a focused message and push the current branch.
  9. Verify the live GitHub profile or public repo page after push.
    • Check that all updated visuals render.
    • Confirm the unchanged hero remains correct.
    • Capture any broken image, stale cache, or layout issue.
  10. Create or update the proof trail:
  • public GitHub links
  • commit links or hashes
  • asset summary
  • LinkedIn/X post links when available
  • follow-up checklist

Public Safety Rules

  • Do not include local machine paths, private vault structure, raw prompts, logs, credentials, browser cookies, private repo names, account identifiers, or client data in public files.
  • Screenshots must not reveal private tabs, emails, analytics, billing, dashboards, file paths, or account menus.
  • Social copy should describe outcomes and workflow categories, not private implementation details.
  • If a public artifact is being prepared, apply the github-safe-publisher rules and run its scanner when available.

Social Proof Handoff

When the user wants LinkedIn or X copy for the refresh:

  • Lead with the public proof angle.
  • Keep LinkedIn reflective and explanatory.
  • Keep X shorter, with one idea per post.
  • Add alt text for every image.
  • Put related X posts into a thread, not scattered comments.
  • Track published links in a proof trail or engagement tracker.

Output Format

Return:

  1. Verdict: BLOCK, REVIEW, or READY.
  2. Target repo and files changed.
  3. Validation performed.
  4. Live verification result, if applicable.
  5. Proof/social artifacts created or updated.
  6. Next recommended action.

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.