derep
Skill2 starsChanged 8 months agoNo licenceView on GitHub
文案去重（改写）：把 md/txt 素材改写为"表述不同、观点一致"的全新文案，并通过 n-gram 重复度检测循环修复直至达标，输出 `_derep` 文件。Use when 用户要求文案去重、洗稿、改写、换一种说法、避免与素材重复、生成表述不同但观点一致的文案，或需要处理素材文件时。
In this repository48 other files it gives its agents.
- abcd-modelSkill
- advantage-compounding-in-networksSkill
- adversity-to-opportunity-frameworkSkill
- ancestor-wisdom-inheritanceSkill
- anti-fragility-gene-cultivationSkill
- apical-dominance-positioningSkill
- bidirectional-mentorship-modelSkill
- burden-shifting-identificationSkill
- concise-communication-principleSkill
- constraint-inertiaSkill
- contextual-insight-extrapolationSkill
- cultivate-professional-aweSkill
- distinguish-productive-playSkill
- dual-perspective-decision-filterSkill
- dual-role-mindset-integrationSkill
- embodied-cognition-learningSkill
- emomemSkill
- external-leverage-amplificationSkill
- find-space-through-external-perspectiveSkill
- foundational-skill-isolationSkill
- human-machine-collaboration-mindsetSkill
- idea-integration-before-creationSkill
- identify-singularity-trendSkill
- identity-leverage-frameworkSkill
- information-network-as-acceleratorSkill
- information-source-classification-frameworkSkill
- interest-first-communicationSkill
- late-mover-advantage-strategySkill
- llm-wikiSkill
- minimal-resistance-pathSkill
- narrative-to-roadmap-translationSkill
- on-demand-skill-managementSkill
- optimal-return-focus-strategySkill
- personal-pe-valuationSkill
- premise-identification-for-effective-actionSkill
- priority-invisible-layer-problem-solvingSkill
- process-over-inspirationSkill
- product-scene-transformationSkill
- quantity-over-initial-qualitySkill
- raw-information-extractionSkill
- risk-hedging-by-counterbalanceSkill
- role-adaptation-through-artistic-observationSkill
- self-evaluation-via-reversed-criteriaSkill
- strategic-mindset-principlesSkill
- superconductor-thinkingSkill
- thick-and-flexible-evaluationSkill
- threshold-crossing-strategySkill
- write-code-anlsSkill
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.