agentleFS
sametbrrsametbrr/github-manager/skills/profile-bio/SKILL.md

profile-bio

Skill0 starsChanged 12 days agoMITView on GitHub

Fills in GitHub account profile fields (name, bio, company, location, blog, social accounts) through the GitHub API, asking for every missing value instead of inventing one and confirming before any write. Use when the user wants to complete or update their GitHub profile details.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run only when the user explicitly asks.

    line 14
  2. Very specific:

    If not logged in or the scope is missing, ask the user to run gh auth refresh -s user (or gh auth login -s user) and wait.

    line 24
  3. Very specific:

    Never guess any value, including company and location.

    line 43
  4. Distinctive:

    Never invent values; a skipped field stays empty.

    line 63
  5. Distinctive:

    Every write needs explicit approval.

    line 64
  6. Distinctive:

    Never delete existing social accounts unless the user asks.

    line 65

≈ “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

profile-bio

Fills in GitHub account fields (PATCH /user and social accounts) interactively. Never invents a value; asks for what is missing. Writes only after approval.

Run only when the user explicitly asks.

0. Preflight

The user scope is required for writes.

gh auth status 2>&1 | grep -i "token scopes"   # must list 'user'

If not logged in or the scope is missing, ask the user to run gh auth refresh -s user (or gh auth login -s user) and wait.

1. Read the current state

gh api user --jq '{login,name,bio,company,location,blog,twitter_username,hireable}'
gh api /user/social_accounts --jq '[.[]|{provider,url}]'

2. Evaluate

Standard: references/profile-bio.md. List empty and weak fields (recommended: name, bio ≤ 160, blog, ≥ 1 social account; optional: location, company).

3. Ask for missing values

  • Recommended field empty → ask the user and wait for an explicit answer.
  • Optional field empty → ask once whether they want to fill it; empty is fine.
  • Never guess any value, including company and location.
  • Fields the API can't set (pronouns, PRO badge, local time, pins, avatar) → list them as manual steps; don't touch them.

4. Diff and approval

Show current → new for every field that changes. Don't write before an explicit yes.

5. Apply

Send only the changed fields. Pass values as separate -f arguments.

gh api -X PATCH /user -f name="$name" -f bio="$bio" -f blog="$blog"
gh api -X POST /user/social_accounts -f "account_urls[]=$url"
gh api -X DELETE /user/social_accounts -f "account_urls[]=$url"   # only when the user asks

Rules

  • Never invent values; a skipped field stays empty.
  • Every write needs explicit approval; never send unchanged fields.
  • Never delete existing social accounts unless the user asks.

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.