github-glowup
Skill5 starsChanged 7 days agoMITView on GitHub
Audit and upgrade a candidate's GitHub profile the way recruiters and interviewers see it, covering profile README, pinned repos, repo READMEs, descriptions, topics, commit history and red flags, then draft the fixes (profile README, repo READMEs, descriptions) and apply them only with permission. Use when the user wants to improve their GitHub profile, make GitHub recruiter-ready, write a profile README, choose pinned repos, or get feedback on their GitHub.
- Reads credentials
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- website/AGENTS.mdAGENTS.md
- company-intelSkill
- cracked-profileSkill
- setup-crackedSkill
- core-vivaSkill
- defend-my-projectSkill
- hr-roundSkill
- mock-interviewSkill
- oa-simSkill
- pattern-coachSkill
- system-design-mockSkill
- jd-matchSkill
- make-it-hireableSkill
- referral-dmSkill
- resume-blueprintSkill
- roast-my-resumeSkill
- offer-decodeSkill
- prep-planSkill
- rejection-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 12
Call the Skill tool with "cracked-profile" for the GitHub username.
- Very specific: line 62
Call the Skill tool with "cracked-profile" and log a scorecard titled github.com/<u>.
≈ “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.
Files
GitHub glow-up
A recruiter clicks the GitHub link on a resume and decides in about 10 seconds whether this person builds things. Make those 10 seconds count.
0. Setup
- Call the Skill tool with "cracked-profile" for the GitHub username. Otherwise ask, or use
gh api user --jq .login. - Gather data. Prefer
gh(works unauthenticated for public data, with lower rate limits); fall back tocurl https://api.github.com/...:- Profile:
gh api users/<u>(name, bio, company, location, blog, followers, public_repos) - Repos:
gh api "users/<u>/repos?per_page=100&sort=updated"(name, description, language, stars, fork, topics, homepage, pushed_at, archived) - Pinned:
gh api graphql -f query='{ user(login:"<u>") { pinnedItems(first:6, types:REPOSITORY) { nodes { ... on Repository { name description stargazerCount primaryLanguage { name } } } } } }' - Profile README:
gh api repos/<u>/<u>/readme --jq .content | base64 -d(it may not exist) - For the top 6 candidate repos, read each README and glance at the tree (
gh api repos/<u>/<repo>/contents). - Contribution activity:
gh api graphql -f query='{ user(login:"<u>") { contributionsCollection { contributionCalendar { totalContributions } } } }'
- Profile:
1. The 10-second view
Describe exactly what a recruiter sees, top to bottom: avatar/name/bio, profile README, pinned repos, and the contribution graph. Then give the verdict: "Does this look like someone who builds things? Yes / Kind of / No."
2. Audit
Score and comment on each area:
| Area | What good looks like |
| Bio and identity | Real name, a one-line role bio (example: "Backend dev · Go & Postgres · <grad year> grad"), location, links |
| Profile README | Short: who you are, what you're building now, 3 best projects with one line each, how to reach you. No stat-widget overload, no giant GIFs |
| Pinned repos | 4–6 of your best original work, matching your target role. No forks, no tutorial clones, no college assignments unless they're impressive |
| Repo READMEs | For each pinned repo: what it is, a screenshot/GIF/demo link, the stack, how to run it, key technical decisions |
| Repo hygiene | Descriptions, topics, a homepage link if deployed, a license, no committed node_modules/.env/secrets |
| Activity | Consistent, real commits. Never suggest fake-commit generators: interviewers spot them and it's dishonest |
Check for leaked secrets in the top repos: search for patterns like API_KEY=, sk-, AKIA, or a committed .env, using code search or the file tree. If you find any, this is the #1 priority: tell them to rotate the key immediately and purge it from history.
3. Draft the fixes
Produce, in the conversation:
- New bio (3 options).
- Profile README: a complete Markdown file in a modern style. Read README-STYLES.md and the curated references in examples/, recommend one style (A: ASCII terminal, B: clean recruiter-first, C: minimal, D: story-led, E: neofetch portrait, where their photo becomes braille ASCII via
scripts/image-to-ascii.py) based on their role and personality, and offer to render a second style for comparison. Use only real projects and facts. Never describe a project's features, numbers or organisation that you haven't read in its code or README, or been told. Write[what it does]and ask instead. Hedging ("tell me if this is wrong") doesn't make an invented detail acceptable. Generate any ASCII banner with a tool, and check that it's ≤ 80 columns. - Pin plan: which 4–6 repos to pin and in what order, with what to unpin and why.
- README rewrites for the 2–3 most important repos, from their actual code (read it), using this template: title + one-line pitch → demo/screenshot → features → tech stack → architecture (a short note, or a diagram if useful) → run locally → what I learned / technical challenges.
- Descriptions and topics for each pinned repo.
Fact check before you show any draft. Go through every bio, README and description line and ask, for each factual claim (a feature, number, habit, organisation, tech, achievement): did I read this in their repo or profile, or did they tell me? If not, replace it with a [placeholder] or delete it. That includes flattering filler like "solving DSA daily" or "organised by pattern". Then add one line under the drafts: Fact-checked: every claim is from your repos or what you told me; [placeholders] need your input.
4. Apply (only with explicit permission)
Changes are public. Ask per item: "Want me to apply this?" Then:
- Bio:
gh api -X PATCH user -f bio="…"(needsgh authwith the user scope). - Profile README: create or update the
<u>/<u>repo's README via a clone, commit and push, or via the contents API. - Repo description/topics:
gh repo edit <u>/<repo> --description "…" --add-topic …. - Repo READMEs: clone, edit, commit, push (or open a PR if they prefer).
- Pinning has no API, so give them the exact click path.
5. Scorecard
Call the Skill tool with "cracked-profile" and log a scorecard titled github.com/<u>. Dimensions: First Impression, Pinned Work, READMEs, Hygiene & Security, Activity.
Skill calls: if your agent has no Skill tool, open the named skill's SKILL.md in the cracked skills folder (core/, interview/, profile/, strategy/) and follow it instead.
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
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.

