How do I enable continuous learning?

Use /learn-on to enable learning; use /learn-off to disable it. The status is read from knowledge/state.json.

How are recent learnings determined?

Recent learnings are the last five entries extracted from the learnings files (patterns, quirks, decisions).

What if there are no knowledge entries yet?

The output will show the empty-state message with guidance to start learning using /learn to extract insights.

knowledge

npx machina-cli add skill aiskillstore/marketplace/knowledge --openclaw

Files (1)

SKILL.md

4.2 KB

Knowledge

Display the current state of the project's knowledge base and recent learnings.

What This Does

Shows:

Learning mode status (on/off)
Knowledge base statistics (entry counts per category)
Recent learnings extracted
Cache statistics

Instructions

Read knowledge/state.json for learning mode status
Read each knowledge file and count entries:
- knowledge/cache/classifications.md
- knowledge/learnings/patterns.md
- knowledge/learnings/quirks.md
- knowledge/learnings/decisions.md
Extract recent entries (last 5) from learnings files
Format and display

Output Format

╔═══════════════════════════════════════════════════╗
║           Project Knowledge Base                   ║
╚═══════════════════════════════════════════════════╝

📚 Learning Status
───────────────────────────────────────────────────
Mode: ON (since 2026-01-08 14:00)
Last Extraction: 5 minutes ago
Extractions This Session: 3

📊 Knowledge Statistics
───────────────────────────────────────────────────
Cache:
  - Classification entries: 23

Learnings:
  - Patterns: 8 entries
  - Quirks: 3 entries
  - Decisions: 5 entries
  - Total: 16 insights

📝 Recent Learnings
───────────────────────────────────────────────────
[Pattern] "Use async/await for API calls in this codebase"
  Discovered: 2026-01-08 | Confidence: high

[Quirk] "Auth module uses non-standard token format"
  Discovered: 2026-01-07 | Confidence: high

[Decision] "Chose Redis over in-memory cache for session storage"
  Made: 2026-01-06 | Confidence: high

💡 Commands
───────────────────────────────────────────────────
/learn      - Extract insights now
/learn-on   - Enable continuous learning
/learn-off  - Disable continuous learning

When Knowledge Base is Empty

╔═══════════════════════════════════════════════════╗
║           Project Knowledge Base                   ║
╚═══════════════════════════════════════════════════╝

📚 Learning Status
───────────────────────────────────────────────────
Mode: OFF
No extractions yet

📊 Knowledge Statistics
───────────────────────────────────────────────────
Knowledge base is empty.

💡 Get Started
───────────────────────────────────────────────────
Use /learn to extract insights from your current session.
Use /learn-on to enable continuous learning.

The knowledge base will grow as you work, capturing:
  - Patterns that work well in this project
  - Quirks and gotchas to remember
  - Decisions and their rationale

Steps

Read knowledge/state.json
Read frontmatter from each knowledge file to get entry counts
Parse recent entries from learnings files (look for ## Pattern:, ## Quirk:, ## Decision: headers)
Format and display the summary
If files are missing or empty, show the "empty" state

Notes

Entry counts come from frontmatter entry_count field or by counting ## headers
Recent learnings are shown most recent first (by discovered/made date)
This is a read-only command - it doesn't modify any files

Source

git clone https://github.com/aiskillstore/marketplace/blob/main/skills/0xrdan/knowledge/SKILL.mdView on GitHub

Overview

The Knowledge skill surfaces the current state of the project’s knowledge base, including learning mode, per-category entry counts, recent learnings, and cache statistics. It reads state and knowledge files to compute counts and extract the latest insights, then presents a concise, formatted summary for quick review.

How This Skill Works

It reads knowledge/state.json to determine the Learning Mode status, counts entries from knowledge/cache/classifications.md and knowledge/learnings/{patterns.md, quirks.md, decisions.md}, extracts the five most recent learnings from those learnings files, and outputs a formatted summary that mirrors the project’s Output Format.

When to Use It

To verify whether learning mode is ON or OFF before running data extractions
To inspect knowledge base entry counts by category (classification, patterns, quirks, decisions)
To review the most recent learnings (last 5) for context before coding or planning
To check cache statistics that impact quick retrieval of knowledge
To assess readiness for a knowledge health check or sprint review

Quick Start

Step 1: Run the knowledge skill to display the current knowledge base status
Step 2: Review Learning Status, Statistics, and Recent Learnings in the output
Step 3: If needed, adjust learning with /learn-on or /learn-off to control continuous extraction

Best Practices

Ensure knowledge/state.json exists and is readable to accurately show Learning Status
Count entries from the specified files (classifications.md and patterns/quirks/decisions) for reliability
Always surface the most recent 5 learnings in descending date order
If data is missing, use the empty-state guidance to inform next steps
Validate new learnings against headers (## Pattern:, ## Quirk:, ## Decision:) when frontmatter is unavailable

Example Use Cases

A teammate runs the knowledge readout after a sprint to confirm new learnings were captured
During a standup, the team checks Learning Status and recent learnings to gauge progress
QA reviews cache statistics to troubleshoot latency in knowledge retrieval
PM compares category counts to identify gaps in knowledge coverage
New joiner uses the output to onboard by understanding patterns, quirks, and decisions

Frequently Asked Questions

Add this skill to your agents