← Back to Skills Marketplace
F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架)
by
KeDouPi(珂抖屁)
· GitHub ↗
· v1.0.2
· MIT-0
187
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install mental-model-forge
Description
F.A.C.E.T. cognitive framework for extracting mental models from classic books and theories. Use when (1) user asks for "reading notes", "extract models", or...
Usage Guidance
This skill appears internally consistent and low-risk: it only reads an optional USER.md to tailor the [T] Transfer and outputs a F.A.C.E.T. analysis plus a fenced metadata block. Before installing, (1) inspect USER.md and remove any secrets or sensitive personal data you would not want the agent to read, (2) confirm how the caller (or host agent) will store the KB metadata — the skill itself does not perform storage but outputs a block that may be saved elsewhere, and (3) ensure you trust the agent/caller that will invoke this skill (it could read USER.md whenever invoked). If you see unexpected network or filesystem behavior at runtime (e.g., data sent to external endpoints or writes to other files), revoke the skill and investigate — that would change the assessment.
Capability Analysis
Type: OpenClaw Skill
Name: mental-model-forge
Version: 1.0.2
The 'mental-model-forge' skill is a prompt-based framework (F.A.C.E.T.) designed to help an AI agent extract and structure mental models from books and theories. It requests read access to 'USER.md' solely to personalize its analysis based on the user's background, and its instructions in SKILL.md are focused entirely on text processing, logical analysis, and Markdown/YAML formatting without any signs of malicious execution, data exfiltration, or unauthorized system access.
Capability Assessment
Purpose & Capability
Name and description (F.A.C.E.T. mental-model extraction) match the declared behavior: no binaries, no credentials, no installs, and only an optional USER.md read for personalization. All required capabilities are proportional to the stated purpose.
Instruction Scope
SKILL.md instructs the agent to read USER.md (explicitly declared in the skill header) to personalize [T] Transfer. Apart from that, the runtime instructions are narrowly scoped to producing the F.A.C.E.T. analysis and the structured KB metadata block. Note: reading USER.md is appropriate for personalization but could expose whatever the user put in that file (see guidance).
Install Mechanism
No install spec and no code files — purely instruction-only. This minimizes risk because nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requests no environment variables, no credentials, and no config paths beyond an optional USER.md. The only I/O is reading USER.md for personalization and producing a Markdown + YAML metadata block — proportionate for the described task.
Persistence & Privilege
always:false and default autonomous invocation are present. The skill does not request persistent presence or elevated privileges and does not modify other skills or system configs. It emits a metadata block intended for the caller to store, which is normal behavior for a content-generation skill.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mental-model-forge - After installation, invoke the skill by name or use
/mental-model-forge - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
**Changelog for mental-model-forge v1.0.2**
- Added structured knowledge base metadata output (YAML block) for each analysis, enabling better storage and retrieval.
- Updated interface contract: outputs now include both a user-facing F.A.C.E.T. analysis and a separate metadata section.
- Introduced new input parameter `exclude_models` to support depth-mode deduplication.
- Defined stricter metadata field rules (unique model id, category list, required tags/scenarios/related_models).
- Clarified output format examples and required sections.
- No code changes; documentation and output specification improvements only.
v1.0.1
**Changelog for version 1.0.1**
- Added an explicit interface contract specifying required/optional input fields (book_title, author, topic).
- Clarified that the skill performs a single model extraction per invocation; multi-model depth handled externally.
- Updated [F] Framework dimension to include a word/character limit (50 words English, 80 characters Chinese).
- Described fallback behavior for missing USER.md—now generates generic transfer suggestions without blocking.
- Updated versioning and last updated date.
v1.0.0
- Initial release of mental-model-forge: a specialized tool for extracting core mental models from classic books and theories using the F.A.C.E.T. cognitive framework.
- Provides concise, multidisciplinary analyses anchored by real-world cases and ruthless focus on actionable insights.
- Dynamically adapts output to user context via optional USER.md integration for personalized cross-domain application ([T] Transfer).
- Clear output format focused on: Framework, Anchor Case, Contradiction, Edge, and Transfer, plus a sharp strategic question.
- Not for summaries or reviews—delivers concrete, user-relevant mental models for strategic thinking.
Metadata
Frequently Asked Questions
What is F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架)?
F.A.C.E.T. cognitive framework for extracting mental models from classic books and theories. Use when (1) user asks for "reading notes", "extract models", or... It is an AI Agent Skill for Claude Code / OpenClaw, with 187 downloads so far.
How do I install F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架)?
Run "/install mental-model-forge" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架) free?
Yes, F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架) is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架) support?
F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架)?
It is built and maintained by KeDouPi(珂抖屁) (@kedoupi); the current version is v1.0.2.
More Skills