🎯 KnowMe CareerForge

认识自己，明确方向，锻造属于你的职业机会。
Know Yourself. Define Your Direction. Forge Your Opportunity.

---

1. What is KnowMe CareerForge?

KnowMe CareerForge is an industrial-grade, agent-native resume engineering skill for Claude Code, Cursor, Codex, Windsurf, and Gemini CLI.

Traditional AI resume tools treat resume writing as a superficial text-generation task: feed a prompt to an LLM, get a block of Markdown, and convert it through black-box tools into a fragile, hallucination-prone PDF.

KnowMe CareerForge fundamentally rethinks this paradigm into a structured, dual-engine system:

knowme-careerforge-skill
          │
          ▼
   KnowMe CareerForge
          │
    ┌─────┴─────┐
    ▼           ▼
  KnowMe     CareerForge
    │           │
Self Discovery  Tailored Career Story
& Evidence      & Engineering Delivery

• KnowMe (Self-Discovery & Evidence Engine): Helps candidates discover who they are, organize their supplied career experience and supporting material, and map their true competitive strengths.
• CareerForge (Career Positioning & Resume Engineering): Translates genuine strengths into targeted positioning for specific job opportunities, tailoring high-impact content inside an HTML Intermediate Working Canvas with Design Tokens, and delivering PDFs checked for print layout and text integrity via Playwright.

---

2. Core Philosophy & Guiding Principle

"The goal is not to make the candidate look better than they are. The goal is to make their real strengths visible to the right opportunity."

WRONG DIRECTION (Generic AI Hallucination):
JD ──> Keyword Stuffing ──> AI Guessing ──> Superficial Fluff ──> Inflated Claims (Fragile in Interviews)

RIGHT DIRECTION (KnowMe CareerForge):
Real Experience ──> Grounded Evidence ──> True Strengths ──> Job Match ──> Precise Engineering & Narrative

---

3. Installation

You can install and use KnowMe CareerForge via CLI (Zero Clone) or directly through Agent-Native Manifests:

Option A: Using CLI (Recommended)

Run directly with npx (no clone required):

# Go to your project directory
cd /path/to/your/project

# Install for your preferred AI assistant
npx knowme-careerforge-skill init --ai cursor    # Cursor (.cursor/rules/)
npx knowme-careerforge-skill init --ai claude    # Claude Code (~/.claude/skills/)
npx knowme-careerforge-skill init --ai codex     # Codex CLI (~/.codex/skills/)
npx knowme-careerforge-skill init --ai windsurf  # Windsurf (.windsurfrules)
npx knowme-careerforge-skill init --ai gemini    # Gemini CLI (~/.gemini/skills/)
npx knowme-careerforge-skill init --ai opencode  # OpenCode (.opencode/skills/)
npx knowme-careerforge-skill init --all          # All supported assistants

Or install globally:

npm install -g knowme-careerforge-skill
knowme init --ai cursor
knowme list

---

Platform entrypoints and runtime resources

Platform	Entry location	Configuration command
Claude Code	~/.claude/skills/knowme-careerforge/SKILL.md	knowme init --ai claude
Codex	~/.codex/skills/knowme-careerforge/SKILL.md	knowme init --ai codex
Cursor	.cursor/rules/knowme-careerforge.mdc	knowme init --ai cursor
Windsurf	Managed block in .windsurfrules	knowme init --ai windsurf
Gemini	~/.gemini/skills/knowme-careerforge.json	knowme init --ai gemini
OpenCode	.opencode/skills/knowme-careerforge/SKILL.md	knowme init --ai opencode

Cursor/Windsurf reference a project-local .knowme/skills/knowme-careerforge/ runtime; Gemini configuration points to its sibling runtime directory. Each routes to the same SKILL.md workflow. File installation does not certify host discovery or behavior. Copying a prompt alone is insufficient. Rerun init after relocating an installation to refresh entry paths.

---

4. User input and artifact lifecycle

The host Agent organizes user descriptions, existing resume material and explicitly supplied supporting evidence. Repository-to-resume extraction is not supported. A target role starts intake; a JD is optional. Without candidate material, ask and wait rather than generating an example.

Draft retains incomplete information, Master preserves supplied facts, and Variant records its source Master hash for a target role. Missing values stay omitted/null; sample people, default honors and invented metrics never fill gaps. See the artifact and acceptance contract.

5. Isolated runs and final acceptance

Default generation uses private temporary staging and leaves only resume/resume.html and resume/resume.pdf in the candidate directory. --profile-json - accepts facts on stdin without a permanent input file; --html-input - accepts edited HTML through the same acceptance and paired-publication path. Failure preserves old delivery files; ordinary completion cleans temporary staging. Use --output and --html-output for explicit destinations.

Request --keep-workspace for diagnostic archives; existing explicit --workspace <dir> calls still retain full runs. manifest: null is expected in default clean output, and --summary is not a file-retention switch. Existing user inputs and old workspaces are never swept or deleted.

Checks run in print mode across every page, then parse the final PDF's page dimensions and extracted text. PASS means current checks passed; FAIL means a check failed; UNVERIFIED means inspection could not complete; DRAFT means draft preparation only. Automated checks do not certify factual truth or every ATS.

Prepare dependencies in the installed runtime as instructed by init (npm ci --omit=dev with a lockfile, otherwise npm install --omit=dev), then run node scripts/rendering/browser-engine.js --check-runtime. Python 3.9+, Node.js 22.13+ and Chromium are required. READY is runtime readiness, not resume acceptance. Deliver one current PDF and editable HTML by default; forge.py defaults to concise stdout; full snapshots and diagnostics remain only in explicit archive mode.

---

6. Token Self-Healing & Visual Tuning Cheat Sheet

All visual parameters are concentrated in :root variables inside the current delivery resume/resume.html:

CSS Token	Default	Compact (1-Page Squeeze)	Relaxed (2-Page Flow)	Purpose
--resume-space-section	12pt	9.5pt ~ 10.5pt	14pt ~ 16pt	Section vertical gap (primary self-healing knob)
--resume-space-item	8pt	6.5pt ~ 7pt	9pt ~ 11pt	Item gap between jobs/projects
--resume-font-size-body	9.2pt	8.8pt ~ 9.0pt	9.5pt ~ 10pt	Body text size (safe legibility floor is 8.8pt)
--resume-line-height-body	1.45	1.38	1.50	Line height ratio
--resume-color-accent	#2563eb	Custom Hex	Custom Hex	Primary theme accent color
--resume-sidebar-width	32%	30%	35%	Sidebar width (for modern/executive templates)

---

7. Core Templates Matrix

The four core templates below are a subset of thirteen available layouts. ATS tiers are internal design categories, not external certification. PDF appearance depends on the browser and installed fonts; cross-machine pixel identity is not guaranteed.

Template ID	Style	Category	ATS Tier	Best For	Target Pages
minimal	Single-Column Minimal	Tech / AI	Tier 1 (Optimal)	Backend, Algorithms, AI Research, Systems	1 Page
modern	Two-Column Split (32:68)	Tech / Fullstack	Tier 1 (Optimal)	Fullstack, AI Agent, Frontend, Global Roles	1~2 Pages
executive	Executive Banner + 33:67	Leadership / Product	Tier 1 (Optimal)	Tech Director, Chief Architect, Tech Lead	1~2 Pages
classic	Structured Table Grid	Corporate / Gov	Tier 1 (Optimal)	State Enterprises, Finance, Hardware, Civil	1 Page

Content-led additions: editorial (experience first, section rail), graduate (education and projects first), and project-focus (projects first). Each uses an explicit single A4 page with 9.5pt body text. Select for actual supplied content, not assumed qualifications.

---

8. CLI & Script Reference

# 1. Generate from an existing user-provided facts file
knowme forge --profile-json candidate.json --role "AI Agent Engineer"

# 2. Update the current pair: supply complete edited HTML on stdin
knowme forge --html-input -

# 3. Explicitly requested draft; no PDF
knowme forge --profile-json draft.json --draft

# 4. Optional template search
knowme search --role "AI Agent Engineer" --engine hybrid --summary

# 5. Development gallery, using fictional data
knowme gallery

Use forge for normal generation and updates. Feed stdin through the host command tool; never interpolate candidate text into shell code. Files above are existing inputs, not required new artifacts. Independent knowme validate / knowme render commands are diagnostic tools; they do not publish a verified HTML/PDF pair. knowme extract, npm run extract and the legacy Python entry all reject repository extraction without reading repositories or writing profiles.

---

Automated Test Suite

npm test
# Or:
python3 scripts/build/run-all-tests.py

---

10. NPM Build, Release & Publishing

This package is ready to be built, tested, and published to the NPM Registry:

# 1. Automated release preparation & verification (e.g. patch/minor/major)
npm run release -- <version>

# 2. Publish to public NPM registry
npm publish --access public

See the full NPM Publishing & Update Guide for step-by-step release instructions.

---

11. License

This project is licensed under the MIT License - see the LICENSE file for details.

Development: guidelines · document review and next-stage roadmap.