knowme-careerforge-skill 0.0.1 → 0.0.4

package/README.md

@@ -178,32 +178,29 @@ All visual parameters are concentrated in `:root` variables inside `workspace/re
 knowme search "AI Agent Engineer" --style "two-column-split"
 
 # 2. Analyze a target Job Description
-python3 scripts/analyze-jd.py --jd examples/ai-engineer/jd.md
+python3 scripts/evidence/analyze-jd.py --jd examples/ai-engineer/jd.md
 
 # 3. Instantiate Intermediate Working Canvas
-python3 scripts/instantiate-resume.py --template modern --keywords "Python,LLM,RAG" --output workspace/resume.html
+python3 scripts/template/instantiate-resume.py --template modern --keywords "Python,LLM,RAG" --output workspace/resume.html
 
 # 4. Validate working canvas layout & ATS compliance
 knowme validate
 
-# 5. Render deterministic pixel-perfect PDF via Playwright
-npx ts-node scripts/render-pdf.ts --input workspace/resume.html --output workspace/resume.pdf
+# 5. Render deterministic pixel-perfect PDF
+python3 scripts/rendering/render-pdf.py workspace/resume.html workspace/resume.pdf
 
 # 6. Build & view static HTML Template Gallery
 knowme gallery
-```
 
 ---
 
-## 9. Automated Testing & Verification
+## Automated Test Suite
 
 ```bash
-# Run full automated test suite (21/21 passing in 0.3s)
 npm test
 # Or:
-python3 scripts/run-all-tests.py
+python3 scripts/build/run-all-tests.py
 ```
-
 ---
 
 ## 10. NPM Build, Release & Publishing

package/README.zh-CN.md

@@ -182,32 +182,29 @@ knowme list
 knowme search "AI Agent Engineer" --style "two-column-split"
 
 # 2. 深度解析目标 JD 文本与技能词频
-python3 scripts/analyze-jd.py --jd examples/ai-engineer/jd.md
+python3 scripts/evidence/analyze-jd.py --jd examples/ai-engineer/jd.md
 
 # 3. 实例化 HTML 中间工作区并注入关键词高亮
-python3 scripts/instantiate-resume.py --template modern --keywords "Python,LLM,RAG,FastAPI" --output workspace/resume.html
+python3 scripts/template/instantiate-resume.py --template modern --keywords "Python,LLM,RAG,FastAPI" --output workspace/resume.html
 
 # 4. 运行布局结构、Design Tokens 与文字密度验证
 knowme validate
 
-# 5. 通过 Playwright 确定性导出无损矢量 A4 PDF
-npx ts-node scripts/render-pdf.ts --input workspace/resume.html --output workspace/resume.pdf
+# 5. 确定性导出无损矢量 A4 PDF
+python3 scripts/rendering/render-pdf.py workspace/resume.html workspace/resume.pdf
 
 # 6. 编译生成可视化模板画廊
 knowme gallery
-```
 
 ---
 
-## 9. 自动化测试与质量保障
+## 自动化测试与持续集成
 
 ```bash
-# 运行全链路自动化测试套件 (21/21 项测试 0.3 秒通过)
 npm test
 # 或:
-python3 scripts/run-all-tests.py
+python3 scripts/build/run-all-tests.py
 ```
-
 ---
 
 ## 10. NPM 构建、发布与版本更新

package/SKILL.md

@@ -2,7 +2,7 @@
 name: knowme-careerforge
 displayName: KnowMe CareerForge
 description: An agent-native skill for self-discovery, career positioning, and tailored resume engineering. Analyzes candidate evidence, maps strengths to target JDs, crafts tailored resumes inside an HTML Intermediate Canvas, self-heals layout/ATS, and exports pixel-perfect PDFs.
-version: 0.0.1
+version: 0.0.4
 ---
 
 # KnowMe CareerForge — Agent Reasoning Contract & Execution Specification
@@ -16,7 +16,7 @@ version: 0.0.1
 ## 1. Operating Rules & Core Constraints
 
 When this skill is activated, you are NOT a generic text generator. You act as a coordinated council of 6 specialized personas:
-1. **Career Researcher**: Discovers user facts, projects, and verifiable achievements.
+1. **Career Researcher**: Discovers user facts, codebase architectures, and verifiable achievements.
 2. **Career Strategist**: Analyzes target JDs and formulates career positioning strategy.
 3. **Evidence Analyst**: Strictly enforces L1~L3 evidence classification and eliminates hallucinations.
 4. **Resume Writer**: Crafts high-impact FAB (Feature-Advantage-Benefit) bullet points.
@@ -24,13 +24,61 @@ When this skill is activated, you are NOT a generic text generator. You act as a
 6. **Resume Reviewer**: Executes automated layout, overflow, and ATS Dual-QA tests.
 
 ### Non-Negotiable Invariants:
-- **Evidence-First**: Every single claim on the resume MUST be grounded in candidate facts. Never invent unverified revenue numbers, false company tenures, or fake degrees.
+- **Evidence-First (Anti-Hallucination)**: Every single claim on the resume MUST be grounded in candidate facts. Never invent unverified revenue numbers, false company tenures, or fake degrees.
 - **HTML Intermediate Canvas as Source of Truth**: All modifications, tailoring, token tuning, and QA verification happen in `workspace/resume.html`. Never output raw unformatted text or bypass the HTML canvas.
-- **Deterministic Rendering**: The final PDF (`workspace/resume.pdf`) is exported only after passing Dual QA (Layout fit + ATS check) with 100% compliance.
+- **Deterministic Rendering**: The final PDF (`workspace/resume.pdf`) is exported via multi-strategy auto-discovery renderers only after passing Dual QA with 100% compliance.
+- **Quiet Execution Protocol (Strict Chat Invariant)**:
+  - **DO NOT** print hundreds of lines of raw HTML, full CSS stylesheets, or intermediate scratchpad python scripts to the user chat.
+  - Execute tool scripts silently in the background.
+  - Final response contract: One-line Value Proposition + Top 3 Grounded Evidence Highlights + Direct Output File Paths (`workspace/resume.pdf` and `workspace/resume.html`).
+
+### Reference Manuals (L3 Domain Rules):
+- **Stage 1 (Know Me)**: `references/01-evidence-mining.md`
+- **Stage 2 (Define Goal)**: `references/02-career-goal.md`
+- **Stage 3 (Understand JD)**: `references/03-jd-analysis.md`
+- **Stage 4 (Position & Select)**: `references/04-template-selection.md`
+- **Stage 5 (Forge Canvas)**: `references/05-html-canvas-tokens.md`
+- **Stage 6 (Review & QA)**: `references/06-qa-and-rendering.md`
+
+*See `AGENT.md` for strict editorial standards and `ARCHITECTURE.md` for system architecture.*
 
 ---
 
-## 2. The 6-Stage Deterministic Workflow
+## 2. Input & Content Intelligence Layer (Repo-to-Resume Modes)
+
+Identify the user's input scenario and select the corresponding mode:
+
+```text
+┌─────────────────────────────────────────────────────────────────────────────────┐
+│ Input Modes & Evidence Mining Pipeline                                          │
+├─────────────────────────────────────────────────────────────────────────────────┤
+│ Mode A: Codebase / Repo-to-Resume Mode                                          │
+│   User provides a project directory or Git repo (or runs in current workspace)  │
+│   ➔ Run `python3 scripts/evidence/extract-evidence.py --repo .`                 │
+│   ➔ Extract tech stacks, frameworks, Docker/CI-CD, Git commits, and author info │
+├─────────────────────────────────────────────────────────────────────────────────┤
+│ Mode B: JD-Specific Mode                                                        │
+│   User provides a target Job Description (text or file)                         │
+│   ➔ Run `python3 scripts/evidence/analyze-jd.py --jd "path/to/jd.txt"`          │
+│   ➔ Extract Must-Have skills, Nice-to-Haves, hiring signals, and priority words │
+├─────────────────────────────────────────────────────────────────────────────────┤
+│ Mode C: Target-Role Mode                                                        │
+│   User specifies a direction (e.g. "AI Agent Engineer", "Senior Architect")     │
+│   ➔ Match against `src/knowledge/roles/*.json` knowledge profiles               │
+└─────────────────────────────────────────────────────────────────────────────────┘
+```
+
+### Collecting Candidate Information:
+1. **Basic Info**: Name, Contact (Email, Phone, Location, GitHub). If missing from user prompt, auto-detect from Git / `package.json` / `evidence-master.json` or prompt briefly.
+2. **L1~L3 Evidence Classification**:
+   - **Level 1 (Direct Code/Config Evidence)**: Verified by code files, configuration files (`package.json`, `Dockerfile`, `go.mod`, `Cargo.toml`), API contracts, or Git commits.
+   - **Level 2 (Structural/Dependency Evidence)**: Deduced from directory structure, tech stack dependencies, and architectural patterns.
+   - **Level 3 (Contextual Inference)**: Reasonable contextual deduction (MUST use conservative phrasing, e.g., *"Participated in the design and implementation of..."*).
+   - **Unsupported**: Facts not present in candidate records. **NEVER WRITE INTO RESUME**.
+
+---
+
+## 3. The 6-Stage Deterministic Workflow
 
 You MUST execute the following 6 stages in exact sequence:
 
@@ -47,133 +95,74 @@ You MUST execute the following 6 stages in exact sequence:
 └──────────────┘     └──────────────┘     └──────────────────┘
 ```
 
----
-
-### Stage 1: Know Me (Self-Discovery & Evidence Extraction)
-
-1. **Collect & Structure Facts**:
-   - Extract education, company tenures, project scopes, code repositories, system architectures, and technical competencies.
-2. **Classify Evidence into 3 Strict Levels**:
-   - **Level 1 (Direct Evidence)**: Verified by code files, configuration files (`package.json`, `Dockerfile`), API contracts, Git commits, or published metrics.
-   - **Level 2 (Structural Evidence)**: Deduced from directory structure, tech stack dependencies, and architectural patterns.
-   - **Level 3 (Contextual Inference)**: Reasonable contextual deduction (MUST use conservative phrasing, e.g., *"Participated in the design and implementation of..."*).
-   - **Unsupported**: Facts not present in candidate records. **NEVER WRITE INTO RESUME**. If a core JD skill is missing, prompt the candidate to clarify rather than fabricating.
-
----
-
-### Stage 2: Define (Goal & Career Positioning)
-
-1. **Clarify Career Target**:
-   - **Target Role Title**: e.g., *Senior AI Agent Engineer*, *Staff Frontend Architect*, *Tech Lead*.
-   - **Target Seniority**: Junior / Mid / Senior / Lead / Principal / Executive.
-   - **Industry Domain**: e.g., AI/LLM, Enterprise SaaS, FinTech, E-Commerce.
-2. **Formulate Core Value Proposition (CVP)**:
-   - One concise statement (15~25 words) capturing the candidate's unique intersection of skills and business impact.
-
----
+### Option 1: Fast One-Shot Unified Execution (Recommended)
+You can run the full end-to-end pipeline in a single command:
+```bash
+python3 scripts/pipeline/forge.py --repo . --role "<Target Role>" --jd "<path/to/jd.txt>" --template "<minimal|modern|executive|classic>" --quiet
+```
+Or via CLI:
+```bash
+knowme forge --repo . --role "<Target Role>" --template modern --quiet
+```
 
-### Stage 3: Understand (Job Description & Signal Extraction)
+### Option 2: Step-by-Step Granular Execution
 
-1. Run the JD Analysis script (or execute equivalent extraction logic):
-   ```bash
-   python3 scripts/analyze-jd.py --jd "path/to/jd.txt"
-   ```
-2. **Extract Key Signals**:
-   - **Must-Have Skills**: Absolute prerequisites (e.g., Python, LangChain/LangGraph, RAG, FastAPI).
-   - **Nice-to-Have Skills**: Advantageous boosters (e.g., Kubernetes, VectorDB benchmarking).
-   - **Core Pain Points & Responsibilities**: What business problems is this hire expected to solve?
-   - **Hiring Signals & Cultural Cues**: High-frequency verbs and domain terminology.
+#### Step 1: Extract Evidence (Know Me)
+```bash
+python3 scripts/evidence/extract-evidence.py --repo . --output workspace/evidence-master.json --quiet
+```
 
----
+#### Step 2 & 3: JD & Target Analysis (Understand)
+```bash
+python3 scripts/evidence/analyze-jd.py --jd "path/to/jd.txt"
+```
 
-### Stage 4: Position Myself (Strength Mapping & Resume Strategy)
+#### Step 4: Search & Select Template (Position)
+```bash
+python3 scripts/template/search-template.py "<Target Role>" --style "<minimal|modern|executive|classic>" --target-pages 1
+```
 
-1. **Conduct Gap Analysis**:
-   - Compare Candidate Evidence (Stage 1) against JD Requirements (Stage 3).
-   - Identify **Strong Matches** (L1 evidence), **Potential Matches** (L2/L3), and **Gaps**.
-2. **Define Resume Strategy**:
-   - **Section Priority**: e.g., for AI Engineer: `Skills` ➔ `Projects` ➔ `Experience` ➔ `Education`. For Executive: `Summary` ➔ `Experience` ➔ `Leadership Projects` ➔ `Skills`.
-   - **Keyword Highlight Targets**: 8~12 high-priority terms to emphasize visually.
-   - **Narrative Angle**: Tailor project bullets using the **FAB Formula** (*Feature: What was built; Advantage: How it was built better; Benefit: Measurable business impact*).
+#### Step 5: Instantiate Intermediate HTML Working Canvas (CareerForge)
+```bash
+python3 scripts/template/instantiate-resume.py --template <template_id> --profile workspace/evidence-master.json --keywords "Python,LLM,RAG,FastAPI" --output workspace/resume.html
+```
 
----
+#### Step 6: Review, Dual QA & PDF Export
+```bash
+# 1. Run Layout QA (DOM height & overflow validation)
+python3 scripts/validation/validate-resume.py --html workspace/resume.html --expected-pages 1
+```
+# 2. If overflow occurs, tune CSS tokens in workspace/resume.html:
+#    - Reduce --resume-space-section (e.g., 11pt -> 9.5pt)
+#    - Reduce --resume-font-size-body (e.g., 9.2pt -> 9.0pt)
 
-### Stage 5: CareerForge (Template Selection, Canvas Instantiation & Editing)
-
-1. **Search & Select Best Template**:
-   ```bash
-   python3 scripts/search-template.py "<Target Role>" --style "<minimal|modern|executive|classic>" --target-pages 1
-   ```
-   - `minimal`: Single-column, tech-dense, optimal for Backend/AI/Systems (1 page).
-   - `modern`: Two-column split (32:68), deep navy sidebar, fullstack/AI/global (1~2 pages).
-   - `executive`: Executive dark banner + 33:67 split, leadership & architecture (1~2 pages).
-   - `classic`: Modern structured table grid, formal/gov/corporate (1 page).
-
-2. **Instantiate Intermediate Working Canvas**:
-   ```bash
-   python3 scripts/instantiate-resume.py --template <template_id> --keywords "Python,LLM,RAG,FastAPI" --output workspace/resume.html
-   ```
-
-3. **Edit in Intermediate Canvas (`workspace/resume.html`)**:
-   - Inject candidate details into the semantic HTML structure.
-   - Wrap core matching keywords in `<strong>` or `<span class="tech-tag">`.
-   - Calibrate CSS Variables in `<style>`:
-     - Spacing: `--resume-space-section`, `--resume-space-item`, `--resume-space-bullet`.
-     - Typography: `--resume-font-size-body`, `--resume-line-height-body`.
-     - Accents: `--resume-color-accent`, `--resume-color-primary`.
+```bash
+# 3. Deterministic PDF Export via Multi-Strategy Auto-Discovery:
+python3 scripts/rendering/render-pdf.py workspace/resume.html workspace/resume.pdf --quiet
+```
 
 ---
 
-### Stage 6: Review & Dual QA (Verification, Self-Healing & PDF Export)
-
-1. **Execute Automated Dual QA**:
-   ```bash
-   # QA Test 1: Layout & DOM Height Overflow Check
-   python3 scripts/validate-resume.py --html workspace/resume.html --expected-pages 1
-
-   # QA Test 2: ATS Text Flow & Heading Hierarchy Check
-   npx ts-node scripts/validate-ats.ts --html workspace/resume.html
-   ```
+## 4. Final Response Delivery Contract (Strict Template)
 
-2. **Self-Healing Closed Loop (If QA Fails)**:
-   - **Case A: Page Overflow (e.g. DOM Height 1145px > 1122.5px)**:
-     1. In `workspace/resume.html`, reduce `--resume-space-section` by `1~2pt`.
-     2. Reduce `--resume-font-size-body` by `0.2pt` (minimum `8.8pt`).
-     3. Condense verbose bullet points while preserving evidence verbs and metrics.
-     4. Re-run `validate-resume.py` until 100% single page fit.
-   - **Case B: ATS Structure Warning**:
-     1. Ensure all section titles use standard H2 tags (`工作经历`, `专业技能`, `项目经历`, `教育背景`).
-     2. Ensure contact items are plain text in standard DOM nodes.
+Once `workspace/resume.pdf` is generated, deliver your final response strictly in this clear, professional structure:
 
-3. **Export Deterministic PDF**:
-   ```bash
-   npx ts-node scripts/render-pdf.ts --input workspace/resume.html --output workspace/resume.pdf
-   ```
-
-4. **Deliver to User**:
-   - Provide `workspace/resume.html` and `workspace/resume.pdf`.
-   - Deliver an **Evidence & Strategy Traceability Summary** explaining how real strengths were mapped to the target JD.
+```markdown
+### 🎯 Career Positioning & Value Proposition
+> **[Candidate Name] · [Target Role Title]**
+> *[15~25 words Core Value Proposition highlighting key strengths]*
 
 ---
 
-## 3. Anti-Hallucination & Evidence Rules Summary
-
-| Evidence Level | Permitted Phrasing | Prohibited Phrasing |
-| :--- | :--- | :--- |
-| **L1 (Code/Config Proven)** | "Architected and implemented...", "Reduced latency by 40% (benchmarked in test suite)" | Phrasing that claims scope beyond repository evidence |
-| **L2 (Dependency/Module Proven)** | "Built microservices utilizing FastAPI and PostgreSQL..." | Claiming senior ownership when code only shows minor integration |
-| **L3 (Contextual Inference)** | "Collaborated on the deployment workflow...", "Participated in data pipeline optimization..." | Claiming "Solely designed and led entire enterprise migration" |
-| **Unsupported (No Evidence)** | **DO NOT INCLUDE** | Inventing metrics, tools, or roles |
+### 🛡️ Top Grounded Evidence Highlights (L1/L2)
+1. **[Key Domain / Architecture]**: [Action Verb + Grounded Achievement + Metrics] *(Evidence: [Source])*
+2. **[Core Tech Stack]**: [Engineered feature with exact frameworks] *(Evidence: [Source])*
+3. **[Delivery & Impact]**: [System stability / CI-CD / Performance metric] *(Evidence: [Source])*
 
 ---
 
-## 4. Troubleshooting & Self-Healing Decision Matrix
-
-```text
-QA Failure: Height Overflow (> 1122.5px)
- │
- ├── Step 1: Reduce --resume-space-section (e.g., 11pt -> 9.5pt)
- ├── Step 2: Reduce --resume-space-item (e.g., 7.5pt -> 6pt)
- ├── Step 3: Reduce --resume-font-size-body (e.g., 9.2pt -> 9.0pt)
- └── Step 4: Merge multi-line bullets into concise single-line bullets
+### 📄 Final Verified Deliverables
+- **PDF Resume (Deterministic A4)**: `workspace/resume.pdf` (Passed 100% Dual QA)
+- **HTML Working Canvas**: `workspace/resume.html` (Design Tokens Calibrated)
+- **Master Profile JSON**: `workspace/evidence-master.json` (Traceable Evidence底座)
 ```

package/agents/claude/knowme-careerforge.md

@@ -1,16 +1,18 @@
 ---
 description: An agent-native skill for self-discovery, career positioning, and tailored resume engineering.
-globs: ["workspace/*", "src/**/*"]
+globs: ["workspace/*", "src/**/*", "scripts/**/*", "references/*"]
 ---
 
 # KnowMe CareerForge — Claude Code Skill
 
-Know Yourself. Define Your Direction. Forge Your Opportunity.
+> *"Know Yourself. Define Your Direction. Forge Your Opportunity."*
 
-When activated, follow the 6-stage workflow:
-1. **Know Me**: Extract candidate facts, classify into L1~L3 evidence.
-2. **Define**: Establish target role, seniority, and Core Value Proposition.
-3. **Understand**: Analyze target JD via `python3 scripts/analyze-jd.py`.
-4. **Position**: Perform gap analysis, map evidence, design Resume Strategy.
-5. **CareerForge**: Search template (`python3 scripts/search-template.py`), instantiate `workspace/resume.html`, calibrate CSS tokens.
-6. **Review & Dual QA**: Run `python3 scripts/validate-resume.py`, self-heal overflow, render `workspace/resume.pdf` via `npx ts-node scripts/render-pdf.ts`.
+When activated, follow the 6-Stage Deterministic Workflow and Quiet Execution Protocol (see `AGENT.md` and `ARCHITECTURE.md`):
+
+1. **Evidence Mining (repo-to-resume)**: Extract codebase facts via `python3 scripts/evidence/extract-evidence.py --repo .` or run one-shot `python3 scripts/pipeline/forge.py` (see `references/01-evidence-mining.md`).
+2. **Define Goal & Archetype**: Establish target seniority tier and capability matrix (see `references/02-career-goal.md`).
+3. **Understand Target**: Analyze target JD via `python3 scripts/evidence/analyze-jd.py` (see `references/03-jd-analysis.md`).
+4. **Template Search**: Match template via `python3 scripts/template/search-template.py` (see `references/04-template-selection.md`).
+5. **Intermediate Canvas**: Instantiate `workspace/resume.html` via `python3 scripts/template/instantiate-resume.py` and calibrate CSS design tokens (see `references/05-html-canvas-tokens.md`).
+6. **Review & Dual QA**: Run `python3 scripts/validation/validate-resume.py` and export `workspace/resume.pdf` via `python3 scripts/rendering/render-pdf.py` (see `references/06-qa-and-rendering.md`).
+7. **Quiet Delivery**: Execute silently in background; deliver concise executive summary and final file path (`workspace/resume.pdf`).

package/agents/codex/knowme-careerforge.yaml

@@ -1,15 +1,24 @@
 name: knowme-careerforge
 description: An agent-native skill for self-discovery, career positioning, and tailored resume engineering.
-version: 1.0.0
+version: 0.0.4
 entrypoint: SKILL.md
 tools:
+  - name: forge
+    command: python3 scripts/pipeline/forge.py
+  - name: extract-evidence
+    command: python3 scripts/evidence/extract-evidence.py
   - name: search-template
-    command: python3 scripts/search-template.py
+    command: python3 scripts/template/search-template.py
   - name: analyze-jd
-    command: python3 scripts/analyze-jd.py
+    command: python3 scripts/evidence/analyze-jd.py
   - name: instantiate-resume
-    command: python3 scripts/instantiate-resume.py
+    command: python3 scripts/template/instantiate-resume.py
   - name: validate-resume
-    command: python3 scripts/validate-resume.py
+    command: python3 scripts/validation/validate-resume.py
   - name: render-pdf
-    command: npx ts-node scripts/render-pdf.ts
+    command: python3 scripts/rendering/render-pdf.py
+rules:
+  - "Execute tools silently in background with --quiet (DO NOT print raw HTML, full CSS, or scripts in chat)."
+  - "Use workspace/resume.html as the sole Intermediate Working Canvas."
+  - "Deliver final concise summary and path to workspace/resume.pdf."
+  - "Reference AGENT.md, ARCHITECTURE.md, and references/01~06 for complete specifications."

package/agents/cursor/knowme-careerforge.mdc

@@ -1,12 +1,17 @@
 ---
 description: KnowMe CareerForge — Agent-native career positioning and resume engineering
-globs: ["workspace/*", "src/**/*"]
+globs: ["workspace/*", "src/**/*", "scripts/**/*", "references/*"]
 ---
 
-# KnowMe CareerForge MDC Rules
+# KnowMe CareerForge MDC Rules (Cursor)
 
-1. Enforce Evidence-First discipline: Never hallucinate ungrounded claims (L1~L3 only).
-2. Edit exclusively in `workspace/resume.html` intermediate working canvas.
-3. Use `python3 scripts/search-template.py` to pick the optimal template.
-4. Use `python3 scripts/instantiate-resume.py` to generate the self-contained canvas.
-5. Validate using `python3 scripts/validate-resume.py` before rendering PDF.
+When activated for career positioning, resume tailoring, or repo-to-resume analysis:
+
+1. **Evidence-First Invariant**: Enforce strict L1~L3 evidence classification (see `references/01-evidence-mining.md`). Never hallucinate ungrounded revenue metrics, fake degrees, or false tenures.
+2. **Repo-to-Resume Extraction**: Extract codebase facts using `python3 scripts/evidence/extract-evidence.py --repo .` or execute the one-shot pipeline `python3 scripts/pipeline/forge.py`.
+3. **Target Alignment & JD Parsing**: Analyze target Job Descriptions using `python3 scripts/evidence/analyze-jd.py` (see `references/03-jd-analysis.md`).
+4. **Template Search**: Match template via `python3 scripts/template/search-template.py "<Target Role>"` (see `references/04-template-selection.md`).
+5. **HTML Canvas Editing**: Edit exclusively in `workspace/resume.html` Intermediate Working Canvas (`scripts/template/instantiate-resume.py`). Calibrate CSS variables (`--resume-*`) in `:root` (see `references/05-html-canvas-tokens.md`).
+6. **Dual QA & Deterministic PDF**: Validate layout height ($297\text{mm} \le 1122.5\text{px}$) and ATS via `python3 scripts/validation/validate-resume.py`. Export final vector PDF via `python3 scripts/rendering/render-pdf.py`.
+7. **Quiet Execution Protocol**: Execute all tools silently with `--quiet`. Never output raw HTML/CSS into the chat. Deliver concise value proposition and direct output file paths.
+8. **Authoritative Guide**: Refer to root `AGENT.md` for Vercel-inspired editorial standards and `ARCHITECTURE.md` for system design.

package/agents/opencode/skill.yaml

@@ -1,7 +1,7 @@
 name: knowme-careerforge
 displayName: KnowMe CareerForge
 description: An agent-native skill for self-discovery, career positioning, and tailored resume engineering.
-version: 1.0.0
+version: 0.0.4
 schema: 1.0
 entrypoint: SKILL.md
 tags:

package/agents/windsurf/knowme-careerforge.rules

@@ -1,10 +1,13 @@
 # KnowMe CareerForge — Windsurf Rules
-# Trigger: Career discovery, resume tailoring, JD analysis
+# Trigger: Career discovery, resume tailoring, JD analysis, repo-to-resume
 
-When user requests resume tailoring or career analysis:
-1. Extract candidate facts and tag with Evidence Level (L1~L3).
-2. Analyze target JD requirements using scripts/analyze-jd.py.
-3. Recommend best template using scripts/search-template.py.
-4. Instantiate workspace/resume.html and calibrate CSS variables.
-5. Run scripts/validate-resume.py to check DOM fit and ATS compatibility.
-6. Export final PDF using scripts/render-pdf.ts.
+When user requests resume tailoring, project analysis, or career positioning:
+1. **Evidence Mining**: Extract candidate facts using `python3 scripts/evidence/extract-evidence.py --repo .` or execute one-shot `python3 scripts/pipeline/forge.py`.
+2. **Anti-Hallucination Gate**: Tag all experience items with Evidence Level (L1~L3 only, see `references/01-evidence-mining.md`).
+3. **JD & Signal Analysis**: Analyze target JD requirements using `python3 scripts/evidence/analyze-jd.py` (see `references/03-jd-analysis.md`).
+4. **Template Search**: Recommend best template using `python3 scripts/template/search-template.py` (see `references/04-template-selection.md`).
+5. **Canvas Instantiation**: Instantiate `workspace/resume.html` using `python3 scripts/template/instantiate-resume.py` and calibrate CSS design tokens (see `references/05-html-canvas-tokens.md`).
+6. **Dual QA Verification**: Validate DOM fit ($297\text{mm} \le 1122.5\text{px}$) and ATS compatibility using `python3 scripts/validation/validate-resume.py`.
+7. **Deterministic PDF Export**: Export final vector PDF using `python3 scripts/rendering/render-pdf.py` (see `references/06-qa-and-rendering.md`).
+8. **Quiet Delivery**: Execute silently in background (`--quiet`); deliver concise value proposition and direct output file paths (`workspace/resume.pdf`).
+9. **Authoritative Guide**: Refer to root `AGENT.md` for editorial standards and `ARCHITECTURE.md` for system architecture.

package/dist/cli/src/commands/init.d.ts

@@ -1,6 +1,6 @@
 /**
  * KnowMe CareerForge CLI — Init Command
- * 一键将 Skill 注入并配置至指定 AI Agent 平台环境。
+ * 一键将 Skill 完整工具包注入并配置至指定 AI Agent 平台环境。
  */
 export interface InitOptions {
     platform?: string;

package/dist/cli/src/commands/init.js

@@ -1,7 +1,7 @@
 "use strict";
 /**
  * KnowMe CareerForge CLI — Init Command
- * 一键将 Skill 注入并配置至指定 AI Agent 平台环境。
+ * 一键将 Skill 完整工具包注入并配置至指定 AI Agent 平台环境。
  */
 var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
     if (k2 === undefined) k2 = k;
@@ -52,6 +52,24 @@ function findPackageRoot(startDir) {
     }
     return path.resolve(startDir, '../../..');
 }
+function copyDirRecursive(src, dest) {
+    if (!fs.existsSync(src))
+        return;
+    fs.mkdirSync(dest, { recursive: true });
+    const entries = fs.readdirSync(src, { withFileTypes: true });
+    for (const entry of entries) {
+        const srcPath = path.join(src, entry.name);
+        const destPath = path.join(dest, entry.name);
+        if (entry.isDirectory()) {
+            if (entry.name === 'node_modules' || entry.name === '.git' || entry.name === 'dist')
+                continue;
+            copyDirRecursive(srcPath, destPath);
+        }
+        else {
+            fs.copyFileSync(srcPath, destPath);
+        }
+    }
+}
 function runInit(options) {
     const rootDir = findPackageRoot(__dirname);
     const projectDir = options.projectDir ? path.resolve(options.projectDir) : process.cwd();
@@ -73,17 +91,30 @@ function runInit(options) {
                 case 'claude': {
                     const claudeDir = path.join(homeDir, '.claude', 'skills', 'knowme-careerforge');
                     fs.mkdirSync(claudeDir, { recursive: true });
-                    const skillMd = fs.readFileSync(path.join(rootDir, 'SKILL.md'), 'utf-8');
-                    fs.writeFileSync(path.join(claudeDir, 'SKILL.md'), skillMd, 'utf-8');
-                    console.log(`[✓] Claude Code Skill configured -> ${claudeDir}`);
+                    copyDirRecursive(path.join(rootDir, 'scripts'), path.join(claudeDir, 'scripts'));
+                    copyDirRecursive(path.join(rootDir, 'src'), path.join(claudeDir, 'src'));
+                    copyDirRecursive(path.join(rootDir, 'references'), path.join(claudeDir, 'references'));
+                    fs.copyFileSync(path.join(rootDir, 'SKILL.md'), path.join(claudeDir, 'SKILL.md'));
+                    fs.copyFileSync(path.join(rootDir, 'AGENT.md'), path.join(claudeDir, 'AGENT.md'));
+                    fs.copyFileSync(path.join(rootDir, 'ARCHITECTURE.md'), path.join(claudeDir, 'ARCHITECTURE.md'));
+                    fs.copyFileSync(path.join(rootDir, 'skill.json'), path.join(claudeDir, 'skill.json'));
+                    console.log(`[✓] Claude Code Skill fully bundled -> ${claudeDir}`);
                     break;
                 }
                 case 'codex': {
                     const codexDir = path.join(homeDir, '.codex', 'skills', 'knowme-careerforge');
                     fs.mkdirSync(codexDir, { recursive: true });
-                    const skillMd = fs.readFileSync(path.join(rootDir, 'SKILL.md'), 'utf-8');
-                    fs.writeFileSync(path.join(codexDir, 'SKILL.md'), skillMd, 'utf-8');
-                    console.log(`[✓] Codex Native Skill configured -> ${codexDir}`);
+                    copyDirRecursive(path.join(rootDir, 'scripts'), path.join(codexDir, 'scripts'));
+                    copyDirRecursive(path.join(rootDir, 'src'), path.join(codexDir, 'src'));
+                    copyDirRecursive(path.join(rootDir, 'references'), path.join(codexDir, 'references'));
+                    fs.copyFileSync(path.join(rootDir, 'SKILL.md'), path.join(codexDir, 'SKILL.md'));
+                    fs.copyFileSync(path.join(rootDir, 'AGENT.md'), path.join(codexDir, 'AGENT.md'));
+                    fs.copyFileSync(path.join(rootDir, 'ARCHITECTURE.md'), path.join(codexDir, 'ARCHITECTURE.md'));
+                    fs.copyFileSync(path.join(rootDir, 'skill.json'), path.join(codexDir, 'skill.json'));
+                    if (fs.existsSync(path.join(rootDir, 'agents', 'codex', 'knowme-careerforge.yaml'))) {
+                        fs.copyFileSync(path.join(rootDir, 'agents', 'codex', 'knowme-careerforge.yaml'), path.join(codexDir, 'skill.yaml'));
+                    }
+                    console.log(`[✓] Codex Native Skill fully bundled -> ${codexDir}`);
                     break;
                 }
                 case 'cursor': {
@@ -112,9 +143,14 @@ function runInit(options) {
                 case 'opencode': {
                     const opencodeDir = path.join(projectDir, '.opencode', 'skills', 'knowme-careerforge');
                     fs.mkdirSync(opencodeDir, { recursive: true });
-                    const skillYaml = fs.readFileSync(path.join(rootDir, 'agents', 'opencode', 'skill.yaml'), 'utf-8');
-                    fs.writeFileSync(path.join(opencodeDir, 'skill.yaml'), skillYaml, 'utf-8');
-                    console.log(`[✓] OpenCode Skill configured -> ${opencodeDir}`);
+                    copyDirRecursive(path.join(rootDir, 'scripts'), path.join(opencodeDir, 'scripts'));
+                    copyDirRecursive(path.join(rootDir, 'src'), path.join(opencodeDir, 'src'));
+                    copyDirRecursive(path.join(rootDir, 'references'), path.join(opencodeDir, 'references'));
+                    fs.copyFileSync(path.join(rootDir, 'SKILL.md'), path.join(opencodeDir, 'SKILL.md'));
+                    fs.copyFileSync(path.join(rootDir, 'AGENT.md'), path.join(opencodeDir, 'AGENT.md'));
+                    fs.copyFileSync(path.join(rootDir, 'ARCHITECTURE.md'), path.join(opencodeDir, 'ARCHITECTURE.md'));
+                    fs.copyFileSync(path.join(rootDir, 'skill.json'), path.join(opencodeDir, 'skill.json'));
+                    console.log(`[✓] OpenCode Skill fully bundled -> ${opencodeDir}`);
                     break;
                 }
                 default: