HeisenbergUwUHeisenbergUwU/resume-builder-skill/AGENTS.md

resume-builder-skill

AGENTS.md6 starsChanged 7 months agoMITView on GitHub

A Hermes/OpenClaw agent skill, not a conventional software project. No build system, no tests, no CI. Everything is pure Python scripts + HTML/CSS templates. Create assets/styles/<name>/ with 3 files: - resume-css.css — the styles - resume-html.html — English HTML skeleton - resume-html-cn.html — Chinese HTML skeleton Use the same CSS class names as existing styles (.header, .job-card, .skills-grid, .edu-table, etc.) so avatar embedding and data injection work.

Installs packages

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repositoryOne other file it gives its agents.
- resume-builderSkill

The file

We split this AGENTS.md into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Footer: Must be empty or removed. Never write "Generated from..." or any attribution.
line 30
Distinctive:
No fabrication: Never invent metrics, companies, or leadership roles.
line 31
Distinctive:
Deep-dive: Always expand the most recent 2 entries (employers for pros, projects for students) using the elevate framework.
line 32
Very specific:
Deliverables: Always produce 3 files: .html (single-file, inline CSS, Base64 avatar), .md, and .pdf.
line 33
Very specific:
Create assets/styles/<name>/ with 3 files:
line 37
Very specific:
Use the same CSS class names as existing styles (.header, .job-card, .skills-grid, .edu-table, etc.) so avatar embedding and data injection …
line 42

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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

AGENTS.md

AGENTS.md — Resume Builder Skill

What This Is

A Hermes/OpenClaw agent skill, not a conventional software project. No build system, no tests, no CI. Everything is pure Python scripts + HTML/CSS templates.

Where Everything Lives

Path	Purpose
`SKILL.md`	The single source of truth. Complete workflow, rules, and conventions. Read it first.
`scripts/`	6 scripts (4 standalone + 1 renderer + 1 orchestrator)
`assets/styles/<name>/`	Per-style CSS + EN/CN HTML templates
`references/<career>/`	Per-career resume writing guides (EN + CN)

Scripts

Script	What it does	Key deps
`scripts/pipeline.py`	Orchestrator. Runs all scripts in sequence. All paths configurable via CLI args (`--dir`, `--output-dir`, `--resume`, `--style`).	none
`scripts/extract_sources.py`	Categorizes files from zip/dir into avatars, reports, docs. Auto-picks best avatar. Writes `extracted_manifest.json`.	none (stdlib)
`scripts/extract_text.py`	Extracts plain text from .eml/.msg/.html/.txt/.md. JSON output with `--json`. Skips binary files (zip, images, etc).	`msgreader` (optional, for .msg)
`scripts/render_resume.py`	Auto-render. Parses `个人简历.md` → structured JSON, fills HTML template, extracts keywords from weekly reports. No LLM needed.	none (stdlib)
`scripts/embed_avatar.py`	Center-crops avatar, Base64-embeds into HTML.	`Pillow` (optional; falls back to raw embed)
`scripts/html_to_pdf.py`	HTML → PDF via weasyprint > wkhtmltopdf > chromium.	`weasyprint` (recommended)

Critical Rules from SKILL.md (Easy to Miss)

Language matching: User's language dictates guide file (*-guide.md vs *-guide-cn.md), HTML template (resume-html.html vs resume-html-cn.html), and all generated content. Default to English.
Footer: Must be empty or removed. Never write "Generated from..." or any attribution.
No fabrication: Never invent metrics, companies, or leadership roles. Use "约" / "approximately" for estimates.
Deep-dive: Always expand the most recent 2 entries (employers for pros, projects for students) using the elevate framework. Other entries stay concise.
Deliverables: Always produce 3 files: .html (single-file, inline CSS, Base64 avatar), .md, and .pdf.

Adding a New Style

Create assets/styles/<name>/ with 3 files:

resume-css.css — the styles
resume-html.html — English HTML skeleton
resume-html-cn.html — Chinese HTML skeleton

Use the same CSS class names as existing styles (.header, .job-card, .skills-grid, .edu-table, etc.) so avatar embedding and data injection work.

Prerequisites

pip install Pillow          # avatar cropping (optional but recommended)
pip install weasyprint      # PDF generation (recommended)
pip install msgreader       # .msg support (optional)

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