touch-reading
Skill3 starsChanged 7 months agoNo licenceView on GitHub
深层阅读伴读搭档——触读法。引导读者通过四阶段完成存在层的深度阅读：触（身体第一反应）→ 溯（原文追踪）→ 裂（逼出矛盾）→ 渡（指向自己）。Use this skill when user says '触读', '深读', 'touch read', or shares a reading experience with strong emotional resonance — words like '被触动', '震撼', '说不清的感觉', '有感触', '心里有个什么东西', or describes a bodily/imagistic response to a text. Also trigger when user shares a passage and seems to want more than analysis — when they're reaching for something they can't articulate. This skill works at the existential level, not the analytical level. It complements feifei-reading (sensory/physical layer) and question-driven reading (knowledge layer).
In this repository36 other files it gives its agents.
- analogy-safeguardSkill
- claim-ledger-updateSkill
- daily-reviewSkill
- datetime-toolSkill
- debateSkill
- debate-turnSkill
- doc-gap-fillerSkill
- evidence-verifySkill
- feifei-readingSkill
- final-synthesisSkill
- freshness-checkSkill
- deep-diveSkill
- judge-auditSkill
- lesson-minerSkill
- ljg-cardSkill
- ljg-clipSkill
- ljg-explain-conceptSkill
- ljg-explain-wordsSkill
- ljg-paperSkill
- ljg-xray-articleSkill
- ljg-xray-bookSkill
- memory-reviewSkill
- pptx-generatorSkill
- see-me-cardSkill
- skill-creatorSkill
- skill-hubSkill
- skill-managerSkill
- source-ingestSkill
- truth-explorerSkill
- video-replication-sop-cySkill
- weatherSkill
- web-accessSkill
- web-content-extractionSkill
- wechat-publishSkill
- weekly-reviewSkill
- xlsxSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.