extract

Original：🇺🇸 English

Translated

Extract decisions and learnings from Claude session transcripts. Triggers: "extract learnings", "process pending", SessionStart hook.

2installs

Sourceboshu2/agentops

Added on2026-02-07

NPX Install

npx skill4agent add boshu2/agentops extract

SKILL.md Content

View Translation Comparison →

Extract Skill

Typically runs automatically via SessionStart hook.

Process pending learning extractions from previous sessions.

How It Works

The SessionStart hook runs:

bash

ao extract

This checks for queued extractions and outputs prompts for Claude to process.

Manual Execution

Given

/extract

:

Step 1: Check for Pending Extractions

bash

ao extract 2>/dev/null

Or check the pending queue:

bash

cat .agents/ao/pending.jsonl 2>/dev/null | head -5

Step 2: Process Each Pending Item

For each queued session:

Read the session summary
Extract actionable learnings
Write to
```
.agents/learnings/
```

Step 3: Write Learnings

Write to:

.agents/learnings/YYYY-MM-DD-<session-id>.md

markdown

# Learning: <Short Title>

**ID**: L1
**Category**: <debugging|architecture|process|testing|security>
**Confidence**: <high|medium|low>

## What We Learned

<1-2 sentences describing the insight>

## Why It Matters

<1 sentence on impact/value>

## Source

Session: <session-id>

Step 3.5: Validate Learnings

After writing learning files, validate each has required fields:

Scan newly written files:

bash

ls -t .agents/learnings/YYYY-MM-DD-*.md 2>/dev/null | head -5

For each file, check required fields:
- Heading: File must start with
```
# Learning: <title>
```
  (non-empty title)
- Category: Must contain
```
**Category**: <value>
```
  where value is one of:
```
debugging
```
  ,
```
architecture
```
  ,
```
process
```
  ,
```
testing
```
  ,
```
security
```
- Confidence: Must contain
```
**Confidence**: <value>
```
  where value is one of:
```
high
```
  ,
```
medium
```
  ,
```
low
```
- Content: Must contain a
```
## What We Learned
```
  section with at least one non-empty line after the heading
Report validation results:
- For each valid learning: "✓ <filename>: valid"
- For each invalid learning: "⚠ <filename>: missing <field>" (list each missing field)
Do NOT delete or retry invalid learnings. Log the warning and proceed. Invalid learnings are still better than no learnings — the warning helps identify extraction quality issues over time.

Step 4: Clear the Queue

bash

ao extract --clear 2>/dev/null

Step 5: Report Completion

Tell the user:

Number of learnings extracted
Key insights
Location of learning files

The Knowledge Loop

Session N ends:
  → ao forge --last-session --queue
  → Session queued in pending.jsonl

Session N+1 starts:
  → ao extract (this skill)
  → Claude processes the queue
  → Writes to .agents/learnings/
  → Validates required fields
  → Loop closed

Key Rules

Runs automatically - usually via hook
Process the queue - don't leave extractions pending
Be specific - actionable learnings, not vague observations
Close the loop - extraction completes the knowledge cycle

extract

NPX Install

Tags

SKILL.md Content

Extract Skill

How It Works

Manual Execution

Step 1: Check for Pending Extractions

Step 2: Process Each Pending Item

Step 3: Write Learnings

Step 3.5: Validate Learnings

Step 4: Clear the Queue

Step 5: Report Completion

The Knowledge Loop

Key Rules