# Cangjie-Skill Distillation Output Structure: A Complete Directory Guide > Explore the Cangjie-skill distillation output structure. Discover how to generate agent-ready skill packs with markdown files JSON tests and organized sub-folders for AI integration. - Repository: [kangarooking/cangjie-skill](https://github.com/kangarooking/cangjie-skill) - Tags: architecture - Published: 2026-08-11 --- **Cangjie-skill distillation produces a structured directory of agent-ready skill packs containing markdown files, JSON test assets, and organized sub-folders for seamless integration into AI agent systems.** The Cangjie-skill framework transforms entire books into reusable, executable knowledge units through a multi-stage pipeline. According to the kangarooking/cangjie-skill source code, the final output follows a rigorous directory hierarchy designed for immediate deployment in darwin-skill compatible environments. Understanding this structure enables developers to navigate, validate, and integrate distilled book knowledge efficiently. ## Root-Level Output Files After the distillation pipeline completes Stage 5 (delivery), the `books//` directory contains four mandatory markdown documents that provide top-level context and navigation. ### BOOK_OVERVIEW.md **[`BOOK_OVERVIEW.md`](https://github.com/kangarooking/cangjie-skill/blob/main/BOOK_OVERVIEW.md)** sits at the repository root and delivers a high-level synthesis of the source material. This file captures the book's structural architecture, main argumentative threads, and critical evaluation notes generated during the distillation process. The overview serves as the entry point for human reviewers before they deep-dive into specific skills. It references the methodology pipeline documented in [[`methodology/00-overview.md`](https://github.com/kangarooking/cangjie-skill/blob/main/methodology/00-overview.md)](https://github.com/kangarooking/cangjie-skill/blob/main/methodology/00-overview.md). ### DIGEST.md **[`DIGEST.md`](https://github.com/kangarooking/cangjie-skill/blob/main/DIGEST.md)** contains a long-form "essence" article that stitches together vetted skills with contextual commentary. Unlike individual skill files that isolate specific capabilities, the digest presents interconnected knowledge as a cohesive narrative. The digest follows the template defined in [`templates/DIGEST.md.template`](https://github.com/kangarooking/cangjie-skill/blob/main/templates/DIGEST.md.template), ensuring consistent formatting across different book distillations. ### INDEX.md **[`INDEX.md`](https://github.com/kangarooking/cangjie-skill/blob/main/INDEX.md)** provides a navigable directory of all extracted skills, organized thematically with dependency graph visualizations. This file transforms the flat directory structure into a semantic map of the book's actionable knowledge. The index template at [`templates/INDEX.md.template`](https://github.com/kangarooking/cangjie-skill/blob/main/templates/INDEX.md.template) includes an "安装使用" (installation and usage) section that specifies how to copy the distillation output into a host agent's `skills/` folder. ### GLOSSARY.md **[`GLOSSARY.md`](https://github.com/kangarooking/cangjie-skill/blob/main/GLOSSARY.md)** contains an alphabetized terminology dictionary extracted by a dedicated glossary extractor during the pipeline. This ensures consistent vocabulary usage across all skills derived from the source book. ## Skill Package Directories The core output of Cangjie-skill distillation resides in individual `/` folders—each representing a discrete, agent-executable capability unit. ### SKILL.md Structure Every skill directory contains a **[`SKILL.md`](https://github.com/kangarooking/cangjie-skill/blob/main/SKILL.md)** file implementing the **RIA-TV++ structure** (Reading, Interpretation, Application-1, Application-2, Trigger, Execution, Boundary). This format originates from the template at [`templates/SKILL.md.template`](https://github.com/kangarooking/cangjie-skill/blob/main/templates/SKILL.md.template). The SKILL.md embeds critical audit metadata including: - **Validation status** — whether the skill passed triple-verification - **Test-prompt coverage** — which scenarios have been pressure-tested - **Reading** — source context and prerequisites - **Interpretation** — conceptual analysis of the knowledge - **Application** — two-tier implementation guidance (theory and practice) - **Trigger** — activation conditions for the agent - **Execution** — concrete, step-by-step procedures - **Boundary** — limitations and contraindications ### test-prompts.json Each skill directory includes **[`test-prompts.json`](https://github.com/kangarooking/cangjie-skill/blob/main/test-prompts.json)**, a darwin-skill compatible test-prompt set for automated pressure-testing and evolutionary refinement. These JSON assets enable continuous validation against edge cases and adversarial inputs. ## Processing Directories The output structure preserves visibility into the distillation pipeline's intermediate states through dedicated folders. ### candidates/ The **`candidates/`** directory stores the raw extraction pool produced during Stage 1 (parallel extractors). This folder contains unvetted knowledge units before they undergo the triple-verification process described in Stage 1.5. ### rejected/ The **`rejected/`** directory holds units that failed verification or were manually flagged as unsuitable. Preserving rejected candidates supports audit trails, iterative improvement, and potential re-evaluation with refined extraction parameters. ## Static Assets The **`assets/`** folder contains supporting resources referenced by markdown files throughout the output structure. This includes: - Diagrams and visualizations - Font files for consistent rendering - Extracted images from the source book - Pipeline-generated graphics ## Consolidated Test Infrastructure The root-level **[`test-prompts.json`](https://github.com/kangarooking/cangjie-skill/blob/main/test-prompts.json)** (generated per book) aggregates all individual skill test prompts into a single collection. This consolidation enables: - Batch validation across the entire skill set - darwin-skill integration for automatic evolution - Regression testing when source books are re-distilled ## Complete Directory Hierarchy ```text books// ├─ BOOK_OVERVIEW.md # High-level book synthesis ├─ DIGEST.md # Long-form essence article ├─ INDEX.md # Navigable skill directory ├─ GLOSSARY.md # Terminology dictionary ├─ test-prompts.json # Consolidated test collection ├─ candidates/ # Raw extraction pool (Stage 1) ├─ rejected/ # Failed verification units (Stage 1.5) ├─ / # Individual skill package │ ├─ SKILL.md # RIA-TV++ structured skill │ └─ test-prompts.json # darwin-skill compatible tests ├─ / # Additional skill packages... │ ├─ SKILL.md │ └─ test-prompts.json └─ assets/ # Static resources ``` ## Loading and Deploying Distilled Output ### Agent Integration (Python) ```python import yaml # Assume distilled book at ./books/lean-startup/ skill_dir = "./books/lean-startup/lean-startup-mvp" with open(f"{skill_dir}/SKILL.md") as f: skill_yaml = yaml.safe_load(f) # Access structured skill components description = skill_yaml["description"] execution_steps = skill_yaml["E — 可执行步骤"] trigger_conditions = skill_yaml["T — 触发条件"] ``` ### Full Deployment (Bash) ```bash # From cangjie-skill repository root cp -r books/lean-startup/* ~/.claude/skills/ # Verify darwin-skill compatibility darwin-skill validate ~/.claude/skills/lean-startup/ ``` ## Source File References The output structure implementation spans these key repository files: - **[`methodology/00-overview.md`](https://github.com/kangarooking/cangjie-skill/blob/main/methodology/00-overview.md)** — Visual pipeline and stage definitions - **`templates/SKILL.md.template`** — Canonical skill file structure - **`templates/DIGEST.md.template`** — Long-form digest layout - **`templates/INDEX.md.template`** — Thematic index with dependency graphs ## Summary - **Cangjie-skill distillation** produces a `books//` directory containing four root markdown files, processing folders, and individual skill packages - **SKILL.md** files implement the RIA-TV++ structure with embedded validation metadata and audit fields - **[`test-prompts.json`](https://github.com/kangarooking/cangjie-skill/blob/main/test-prompts.json)** assets provide darwin-skill compatible automated testing at both skill and book levels - **`candidates/`** and **`rejected/`** folders preserve pipeline transparency for quality assurance and iteration - The complete output can be copied directly to `~/.claude/skills/` for immediate agent deployment according to the installation instructions in INDEX.md.template ## Frequently Asked Questions ### What does the RIA-TV++ structure in SKILL.md contain? The RIA-TV++ structure organizes executable knowledge into six sections: **R**eading (source context), **I**nterpretation (conceptual analysis), **A**pplication (two-tier theory/practice guidance), **T**rigger (activation conditions), **E**xecution (step-by-step procedures), and **B**oundary (limitations). This format ensures agents receive complete contextual grounding before executing actions, with explicit constraints preventing inappropriate application. ### How does Cangjie-skill handle extraction units that fail verification? Failed units move to the **`rejected/`** subdirectory after Stage 1.5 triple-verification. This preserves auditability and enables potential reprocessing with refined parameters, rather than permanent deletion. The rejection reasons and original extraction metadata remain accessible for pipeline improvement analysis. ### What makes the output compatible with darwin-skill? Each skill's **[`test-prompts.json`](https://github.com/kangarooking/cangjie-skill/blob/main/test-prompts.json)** follows darwin-skill's schema for automated pressure-testing and evolutionary refinement. The root-level consolidated **[`test-prompts.json`](https://github.com/kangarooking/cangjie-skill/blob/main/test-prompts.json)** enables batch validation, while the structured markdown format allows darwin-skill parsers to ingest RIA-TV++ sections directly for agent runtime execution. ### Where do I install the distillation output for Claude-style agents? Copy the entire `books//` contents to your agent's skills directory—typically `~/.claude/skills/` as documented in the "安装使用" section of [`templates/INDEX.md.template`](https://github.com/kangarooking/cangjie-skill/blob/main/templates/INDEX.md.template). The INDEX.md file within the output provides specific integration instructions for your target agent platform.