ClawHub

费曼.skill - 理查德·费曼思维操作系统

v1.0.0

理查德·费曼的思维框架与表达方式。基于40+个一手来源的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用费曼的视角分析问题、审视决策、提供反馈。 当用户提到「用费曼的视角」「费曼会怎么看」「费曼模式」「feynman perspective」「费曼学习法」时使用。 即使...

⭐ 0· 111·0 current·0 all-time
by@alchaincyf
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
Name, description and SKILL.md are coherent: the skill's declared purpose is to act as a Feynman-style thinking advisor and the runtime instructions and content implement that. There are no unexpected binaries, env vars, or config paths declared or required.
ℹ
Instruction Scope
Instructions are self-contained and limited to roleplaying, triggers, and a single initial disclaimer. The SKILL.md directs the agent to respond 'as Richard Feynman' in the first person and to avoid meta commentary unless the user asks to exit — this is coherent with the stated goal but ethically sensitive because it tells the agent to claim the identity of a real person rather than to 'adopt a Feynman-like style'. There is no instruction to read files, access environment variables, or transmit data externally.
✓
Install Mechanism
No install spec; instruction-only skill (no code files). This is the lowest-risk install profile — nothing will be written to disk or downloaded by the skill.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. The requested access is minimal and proportionate to an instruction-only roleplay skill.
✓
Persistence & Privilege
always:false (default) and no special persistence or system-wide modifications requested. Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.
Assessment
This skill is internally consistent and low-risk from a technical perspective (no installs, no credentials, no file/network access). Before installing, consider two things: (1) The skill instructs the agent to state 'I am Richard Feynman' in first person — that can be misleading to your users and may violate platform or legal/ethical expectations about impersonating real people (even historical figures). If you want transparency, ask the author to change the wording to 'Respond in the style of Richard Feynman' or always include a visible disclaimer in each reply. (2) Test the trigger behavior to ensure it only activates when you expect (the SKILL.md has narrow trigger guidance but real triggers can be noisy). If you need stricter safeguards, require explicit user consent before the skill adopts the Feynman persona or add repeated disclaimers. Otherwise this skill appears coherent and technically harmless.

Like a lobster shell, security has layers — review code before you run it.

latestvk970v10dgkj3esbrt0chmtmntn84avp4

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments