AI Self-Evolution Engine( AI 自我进化引擎）
v1.0.4Dual-value learning system - extracts reusable mental models from books, writes individual pattern files (patterns/{id}.md) with YAML frontmatter for buildin...
⭐ 0· 118·0 current·0 all-time
byKeDouPi(珂抖屁)@kedoupi
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description (building a library of mental models) matches the runtime instructions: selecting books, running F.A.C.E.T. analyses, deduplicating, and writing per-model markdown files under memory/knowledge-base. Declared dependencies (book-scout and mental-model-forge) are consistent with the task.
Instruction Scope
Instructions read USER.md and memory/reading-history.json and write patterns and concept files—these are appropriate for personalization and deduplication. However the README and SKILL.md recommend optional startup behavior (edit AGENTS.md to load SOUL.md, USER.md, and recent memory files each session). That optional guidance expands what the agent will read (potentially sensitive session memory) and should be applied only intentionally.
Install Mechanism
This is an instruction-only skill with no install spec and no code files—lowest disk/write risk. Dependencies are other skills (book-scout, mental-model-forge) that must be installed separately; verify their provenance before installing.
Credentials
The skill references optional external integration tokens (FEISHU_APP_TOKEN, FEISHU_TABLE_ID, NOTION_API_KEY, NOTION_DATABASE_ID) for posting analysis to external tracking systems. Requesting those optional credentials is proportionate to the described optional feature (external tracking), but you should not provide them unless you want the skill to send data to Feishu/Notion.
Persistence & Privilege
The skill writes persistent files under memory/knowledge-base and reading-history.json as intended for a knowledge-base. It does not set always:true and does not request system-wide privileges. The only persistence concern is the README's suggestion to add auto-loading of many memory files at session startup; enabling that increases the skill's effective access surface and should be done consciously.
Assessment
This skill is coherent with its stated purpose: it reads a small set of workspace files, calls two other skills to find and analyze books, and writes markdown model files to a knowledge-base. Before installing or enabling automatic runs: 1) Review and trust the two dependencies (book-scout, mental-model-forge) because they will be invoked and may perform web requests. 2) Only provide FEISHU/NOTION tokens if you want the optional external posting feature; treat those as sensitive credentials. 3) Be cautious about applying the README’s optional AGENTS.md edits — auto-loading SOUL.md or recent memory files each session will make more of your workspace readable to the agent. 4) Backup memory/reading-history.json and check its contents for any sensitive data you don’t want the skill to read. 5) If you need higher assurance, inspect (or request) the implementations of book-scout and mental-model-forge and run the skill in a restricted workspace first. These steps will reduce privacy/supply-chain exposure while keeping the skill’s useful behavior.Like a lobster shell, security has layers — review code before you run it.
AI-evolutionvk97andf7654q4v1f1bnmjnyhv183jz2rFACETvk97andf7654q4v1f1bnmjnyhv183jz2rbooksvk97andf7654q4v1f1bnmjnyhv183jz2rcognitive-upgradevk97andf7654q4v1f1bnmjnyhv183jz2rdecision-frameworksvk97andf7654q4v1f1bnmjnyhv183jz2rknowledge-basevk97andf7654q4v1f1bnmjnyhv183jz2rlatestvk970672dv9g4ah19dh32g451t183p9g7learningvk97andf7654q4v1f1bnmjnyhv183jz2rmental-modelsvk97andf7654q4v1f1bnmjnyhv183jz2rpermanent-upgradevk97andf7654q4v1f1bnmjnyhv183jz2rself-improvementvk97andf7654q4v1f1bnmjnyhv183jz2rstrategic-thinkingvk97andf7654q4v1f1bnmjnyhv183jz2rthinking-patternsvk97andf7654q4v1f1bnmjnyhv183jz2r
License
MIT-0
Free to use, modify, and redistribute. No attribution required.