LEARN() turns vague learning intent into a validated, actionable learning path with goals, stages, practice tasks, and verification.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install zayn-learn
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 zayn-learn 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() Learning Plan?
LEARN() is an Openclaw Skills workflow for converting ambiguous learning requests into a structured, executable learning plan. It forces a disciplined intake process: define the goal, learning reason, current baseline, target level, evidence, constraints, and validation method before any full plan is produced.
This Openclaw Skills entry is designed to prevent over-planning, guesswork, and unsupported recommendations. Instead of generating a generic checklist, it produces a parameter state table, assesses executability, identifies missing inputs, and only then outputs stage-by-stage tasks, practice items, and verifiable next steps.
LEARN() Learning Plan Use Cases
- When a user has a fuzzy learning goal and needs it translated into a concrete plan.
- When the current skill level, timeline, or evidence is incomplete and must be clarified first.
- When you need an AI-generated learning path that is constrained by real inputs rather than assumptions.
- When a request should result in practice tasks and verification, not just a resource list.
- When learning objectives must be audited for feasibility before execution.
- When you want Openclaw Skills to structure a personal productivity or upskilling workflow.
How LEARN() Learning Plan Works
- Parse the user’s input and map it into a parameter state table.
- Check the required fields: learning goal, learning reason, current foundation, and target level.
- Collect optional fields such as time budget, deadline, practice project, verification method, learning style, resources, and constraints.
- Validate evidence priority and ensure at least one reliable source is available.
- Evaluate whether the learning goal is specific, executable, and within the skill’s responsibility boundary.
- If key parameters are missing, request clarification instead of inventing details.
- If minimum operating conditions are met, generate a structured learning path with stages, tasks, practice, verification, and next steps.
- Preserve ambiguity boundaries: do not convert predictions or guesses into facts, and do not expand scope beyond the original request.
LEARN() Learning Plan Setup
- Add the Openclaw Skills package or sync the skill definition into your skill registry.
- Register the skill identifier and display name in your agent configuration.
- Ensure the agent can prompt for missing inputs before attempting a full plan.
- Use the skill with requests that include at least the minimum required parameters.
- Keep the skill scoped to learning-plan generation only; route unrelated tasks to the appropriate WorkFn skill.
# Example: place the skill in your local skills directory
mkdir -p ~/.openclaw/skills
cp SKILL.md ~/.openclaw/skills/zayn-learn/SKILL.md
# Example: verify the file is available to your agent runtime
ls -la ~/.openclaw/skills/zayn-learn
# Example: configure the agent to load the skill
export OPENCLAW_SKILLS_PATH="$HOME/.openclaw/skills"
# Example: validate the skill metadata
cat ~/.openclaw/skills/zayn-learn/SKILL.md
LEARN() Learning Plan Data Schema & Taxonomy
Core metadata
| Field | Value |
|---|---|
| Skill ID | zayn-learn |
| Display Name | LEARN() |
| Chinese Name | 学习计划 |
| Project | WorkFn |
| Author Prefix | zayn |
| Category | Personal Productivity |
| Version | 0.1.0 |
| Status | Draft for testing |
Input parameter model
The skill requires a parameter state table before formal analysis. Parameters are grouped as follows:
Required parameters
- Learning goal
- Learning reason
- Current foundation
- Target level
Optional parameters
- Time budget
- Deadline
- Practice project
- Verification method
- Target object
- Output outcome
- Learning style
- Learning resources
- Learning constraints
Internal state taxonomy
| State | Meaning |
|---|---|
| 已命中 | Parameter is present and usable |
| 部分命中 | Parameter is partially present |
| 缺失 | Parameter is missing |
| 冲突 | Parameters conflict or contradict |
| 待验证 | Information exists but is not yet confirmed |
Output structure
- Parameter completeness conclusion
- Parameter state table
- Learning executability assessment
- Missing parameters
- Learning path
- Stage tasks
- Practice project
- Verification method
- Next step
Validation and control rules
- Do not auto-fill missing parameters.
- Do not turn fuzzy goals into complete plans without clarification.
- Do not write unverified information as fact.
- Do not resolve conflicts without preserving source and requesting validation.
- Do not skip practice; every plan must include an executable verification path.
LEARN() Learning Plan Advanced Features
- Parameter-first intake flow that forces explicit state mapping before planning.
- Evidence-priority validation that prevents unsupported assumptions from entering Openclaw Skills outputs.
- Missing-parameter interception: the skill asks for clarification instead of hallucinating a full plan.
- Conflict-aware handling that preserves source context and flags inconsistencies for review.
- Verification-driven planning that ties every learning path to an executable check or outcome.
- Strict scope boundaries to avoid over-expanding a vague request into unrelated WorkFn tasks.
- Human judgment gate that keeps manual approval central for ambiguous or high-risk learning plans.
SKILL.md
Loading
Related Openclaw Skills
PLAN() Planning Decomposition Skill
PLAN() is an Openclaw Skills planning agent that transforms vague goals into structured, executable task plans with dependencies, timing, resources, and completion criteria.
PRACTICE()
PRACTICE() is an Openclaw Skills workflow that converts ideas, articles, or methods into minimal, verifiable, low-cost experiments with clear stop conditions.
READ() - Reading to Action Transformation
READ() transforms reading materials into structured insight and action, turning content into reasons, questions, evidence, next steps, and review points.
Image to 3D Part STL Builder
Openclaw Skills converts dimensioned images into confirmation-ready SVG blueprints and accurate STL models for fabrication.
REQUEST() Internal Request Skill
REQUEST() turns vague internal asks into structured, evidence-backed requests with clear scope, deadlines, and decision-ready context.
Tulimoa Gateway
Tulimoa Gateway gives AI agents one MCP endpoint for federated SaaS access plus persistent memory that survives compaction and new sessions.
Featured*
