agentleFS
Sign inStart free
milad-ahmdmilad-ahmd/agent-skills/skills/roast-my-github/SKILL.md

roast-my-github

Skill5 starsChanged 15 days agoMITView on GitHub

Roasts a GitHub profile with humor, then gives genuinely useful advice. It analyzes public repos, stars, languages, missing descriptions and licenses, abandoned projects, lazy commit messages, and activity with a data script, and produces a shareable scorecard and a glow-up plan. Use when the user asks to roast, rate, review, or improve a GitHub profile, or asks "what does my GitHub say about me".

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user wants pinned repos or the profile README reviewed, ask them to paste them, because the REST API doesn't expose pins.

    line 18
  2. Distinctive:

    Every joke must point at a fact from the data: "47 repos, 41 without a description.

    line 22
  3. Distinctive:

    When roasting someone else's profile, keep it friendly and suggest roasting only yourself or friends who agreed to it.

    line 53
  4. Distinctive:

    Don't make up stats. If the API returns nothing, say so.

    line 54

≈ “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

Roast My GitHub 🔥

Funny enough to screenshot, useful enough to fix.

1. Get the facts (never roast from imagination)

python3 scripts/github_profile.py <username>          # human-readable facts
python3 scripts/github_profile.py <username> --json   # structured output

Set GITHUB_TOKEN (or GH_TOKEN) to avoid the 60 requests/hour anonymous rate limit. The script only uses public data. If the user wants pinned repos or the profile README reviewed, ask them to paste them, because the REST API doesn't expose pins.

2. The roast (5–8 lines)

  • Every joke must point at a fact from the data: "47 repos, 41 without a description. Your projects are in witness protection."
  • Roast the code and the habits, never the person: no jokes about appearance, identity, nationality, age or employment.
  • Make it playful, not cruel. End on something genuinely good you found.

3. Scorecard (/10 each, then an overall score)

AreaBased on
Profilebio, name, blog/site, profile README repo (<user>/<user>)
Repo hygienedescriptions, licenses, topics, READMEs on top repos
Activityrecent pushes, stale repos, account age vs output
Impactstars, forks, followers
Focuslanguage spread, clear theme vs scattered experiments
Commit craftlazy commit messages ratio (if events available)

4. Glow-up plan (top 5 fixes, highest impact first)

Concrete actions, e.g. "Add descriptions and topics to these 6 repos: …", "Archive these 9 stale repos", "Create a profile README (draft below)", "Pin these 4 repos". Offer to draft a profile README, and offer to run readme-glow-up on the weakest README.

5. Share card

🔥 My GitHub just got roasted: 6.4/10
"<best roast line>"
Roast yours → github.com/milad-ahmd/roast-my-github

Rules

  • Public data only. Never dig for personal information.
  • When roasting someone else's profile, keep it friendly and suggest roasting only yourself or friends who agreed to it.
  • Don't make up stats. If the API returns nothing, say so.

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.

Check your setup, free