# kangarooking/cangjie-skill

把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills（Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills）

Repository: https://github.com/kangarooking/cangjie-skill
Canonical: https://ross.abutalabs.com/products/cangjie-skill
Language: Python
License: MIT
License Family: permissive
Topics: agent-workflows, ai-skills, automation, book-to-skill, knowledge-distillation, prompt-engineering, skill-generator, templates
Last push: 2026-08-26T05:20:34+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 96, longevity 9
- inputs: {"age_days": 139, "days_push": 7, "days_rel": 24, "gap_med": 0, "n_releases_24m": 2}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9016, forks 1062 (observed 2026-08-28T04:10:26.771017+00:00)

## What it is
Cangjie Skill is a Python-based tool that distills methodologies from high-value content like books, long-form videos, and podcasts into executable, callable AI Agent Skills. It provides templates and a methodology (RIA-TV++) for generating skill packs usable with platforms like Claude Code, OpenClaw, and DeepSeek Harness.

## Use cases
- turn a book into executable agent skills
- distill a podcast episode into a reusable AI skill
- extract methodology from a long YouTube video
- generate skill packs from long-form content
- create callable AI skills from books I've read
- convert expert knowledge into agent workflows

## When to choose
- you want to convert books, videos, or podcasts into reusable AI agent skills
- you use Claude Code, OpenClaw, or DeepSeek Harness and want a skill-generation workflow
- you need templates and a structured methodology for knowledge distillation into skills

## When to avoid
- you need a general-purpose agent framework for running autonomous tasks
- you want a note-taking or summarization tool rather than executable skills
- you don't use any compatible agent platform to invoke the generated skills

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, prompt-engineering, nlp, llm-inference, workflow-automation
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: agent-skills, skill-generator, knowledge-distillation, book-to-skill, claude-code, openclaw, deepseek-harness, templates, content-to-skill, ai-agents, automation

## Member repositories
- kangarooking/cangjie-skill (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:26.771017+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:24:20.583422+00:00, confidence not recorded.
  - readme: https://github.com/kangarooking/cangjie-skill (fetched 2026-08-28T04:10:26.771017+00:00, sha 2299cbc41453)
- Data as of 2026-08-30T08:39:29.467469+00:00.