Download
cangjie-skill is a workflow for converting books and other long-form knowledge into executable AI skill packs. Its goal is structured reuse rather than producing another summary or set of reading notes. The seven-stage RIA-TV++ pipeline analyzes the full source, extracts candidate frameworks, verifies them, constructs skill modules, links related ideas, pressure-tests behavior, and prepares delivery files. Each accepted skill records supporting material, a reconstructed explanation, examples, trigger situations, executable steps, and limitations. Strict verification rejects generic or weak ideas that lack independent evidence, predictive value, or meaningful uniqueness. The generated package can include an overview, glossary, reference graph, long-form digest, individual skill files, and test prompts. Completed skills can be installed for compatible coding agents such as Claude Code and Cursor.
Features
- Whole-source structural and applicability analysis
- Parallel extraction of frameworks, principles, and examples
- Triple verification of candidate knowledge units
- Executable RIA++ skill module construction
- Relationship mapping through Zettelkasten-style linking
- Pressure testing with trigger and confusion prompts
Project Samples
