An analytical decision-making skill designed to evaluate whether a user should learn a new topic, defer it, or acquire only the absolute minimum required to solve an immediate problem.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install learn-occam
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install learn-occam using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is learn-occam?
The learn-occam skill functions as a cognitive brake system for developers and learners who suffer from wide-scope exploration or excessively long interest queues. Operating on the core principle that time is a developer's most valuable asset, this Openclaw Skills component challenges the impulse to accumulate depreciating knowledge. It shifts the learning focus from a "nice-to-know" mentality to a strictly problem-driven, high-ROI workflow.
By evaluating factors like technical depreciation cycles, existing knowledge crossover, and immediate problem-solving utility, learn-occam helps users avoid intellectual hoarding. It guides users away from technologies that expire quickly or tasks that can be fully offloaded to AI, redirecting focus to high-value foundational skills or immediate context execution.
learn-occam Use Cases
- When deciding whether to learn a brand-new framework, tool, or language.
- When struggling to determine how deep to dive into a specific technical topic.
- When faced with limited time and energy, requiring prioritization across competing backlogs.
- When balancing exploration of cutting-edge tech versus applying tried-and-true solutions.
How learn-occam Works
- Identify the Target Problem: The skill forces clarity by questioning the exact, practical problem the user is trying to solve. If no immediate problem exists, the topic is automatically deferred.
- Audit Existing Competencies: It assesses the user's current knowledge base to check if existing skills can already solve the problem without learning something new.
- Evaluate Depreciation & ROI: It analyzes how quickly the target knowledge will depreciate (e.g., fast-changing toolchains) and whether the time investment justifies the return, or if it can be offloaded to an AI tool.
- Balance Explore vs. Exploit: It weighs the cost of exploration against immediate application benefits, prompting a deep dive only when goals are challenging and existing knowledge is insufficient.
- Deliver Definitive Verdict: The workflow outputs one of three clear actions: Learn, Do Not Learn (defer to queue), or Learn the Absolute Minimum (defining exactly what snippet or sub-module is required).
learn-occam Setup
To integrate learn-occam into your Openclaw Skills workflow environment, configure the skill block within your agent profile definitions:
# Initialize and add learn-occam to your active agent workspace
openclaw skills add learn-occam
Ensure that related cognitive skills are accessible within the same environment to allow for execution fallback hooks.
learn-occam Data Schema & Taxonomy
The learn-occam skill manages decision metrics, evaluation states, and pipeline transitions. The structured breakdown of its data evaluation model and taxonomy includes:
| Attribute / Field | Type | Purpose | Validation Rules |
|---|---|---|---|
target_topic |
String | The technical skill or concept under evaluation. | Required |
defined_problem |
String | The explicit task or bottleneck to resolve. | Must be concrete; no vague entries. |
existing_competency |
Array | Validated existing skills owned by the user. | Strict rule: Only include explicitly confirmed knowledge. |
depreciation_horizon |
String | Estimated lifespan of the tech stack (e.g., 6-12 months). | Quantifiable temporal value. |
verdict |
Enum | Final output directive. | Must resolve to: LEARN, DEFER, or MINIMUM_VIABLE. |
Related Taxonomy
- Sibling Openclaw Skills:
learn-crossover(mapping existing knowledge foundations),learn-graph(systematic path generation for deep dives),learn-prototype(hands-on iterative building), andlearn-feynman(self-assessment validation loop).
learn-occam Advanced Features
- Strict Knowledge Validation Guardrail: Features a strict iron-clad rule that prevents the agent from assuming user knowledge based on current text materials, author profiles, or third-party conversational contexts. The agent must explicitly confirm past experience.
- Dynamic Fallback Pipeline: Integrates native handoffs to
learn-crossoverwhen existing knowledge coverage is uncertain, or escalates tolearn-graphto build dependency maps if a deep-diveLEARNverdict is reached. - AI Offload Assessment: Automatically evaluates if the subject matter can be dynamically generated or queried via AI on-demand, lowering the learning priority to "know-of-existence" rather than operational mastery.
SKILL.md
Loading
Related Openclaw Skills
Skill Router
The Skill Router serves as the master gateway and dispatcher, automatically matching user prompts to the exact subset of capabilities needed for execution.
MaxHub Instagram Data Assistant
A powerful data analytics and search skill designed to pull comprehensive user profiles, posts, reels, and hashtag data from Instagram using the MaxHub API.
MaxHub Bilibili Data Assistant
An advanced AI coding agent skill designed to query and analyze Bilibili videos, creators, comments, and live stream data via the MaxHub API.
MaxHub Lemon8 Data Assistant
A read-only analytical assistant designed to query, track, and analyze Lemon8 post, user, and trend data via the MaxHub API.
speak-69378f
An AI-driven operational workflow skill that leverages learned insights from evaluation videos to execute step-by-step automation sequences.
AI Governance & Safety Intelligence
An advanced governance engine providing comprehensive intelligence on global AI regulations, incident tracking, standards, and frontier model safety evaluation frameworks.
Featured*
