Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Knowledge Extractor Skill — measured AI agent skill | DecimalAI

a5c-ai/knowledge-extractor

SkillScore86Maintained

Extract tribal knowledge from code, documentation, and commit history to preserve institutional memory

by a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Knowledge Management pack

decimalai skills pull a5c-ai-knowledge-extractor

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-knowledge-extractor/SKILL.md

Raw file: /s/a5c-ai-knowledge-extractor/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-knowledge-extractor.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9d ago

Yes — +64% lift · at higher cost+26% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	27%	0%
case-02	✗→✓	▲ Improved	-3%	0%
case-03	✗→✓	▲ Improved	35%	0%
case-04	✗→✓	▲ Improved	37%	0%
case-05	✗→✓	▲ Improved	3%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/specializations/code-migration-modernization/skills/knowledge-extractor/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

Knowledge Extractor Skill

Extracts tribal knowledge from code comments, commit messages, documentation, and other sources to preserve institutional memory during migration.

Purpose

Enable knowledge preservation for:

Comment analysis and extraction
Commit message mining
Documentation parsing
Pattern recognition
Business rule discovery

Capabilities

1. Comment Analysis

Extract TODO/FIXME comments
Parse documentation comments
Identify explanatory notes
Find warning comments

2. Commit Message Mining

Extract rationale from commits
Identify bug fix context
Find feature explanations
Track decision history

3. Documentation Parsing

Parse markdown documentation
Extract from wikis
Process README files
Catalog API docs

4. Pattern Recognition

Identify coding patterns
Recognize idioms
Detect conventions
Map architectural patterns

5. Business Rule Extraction

Find business logic comments
Extract validation rules
Identify calculation explanations
Document edge cases

6. Glossary Generation

Build domain vocabulary
Define abbreviations
Map term usage
Create terminology guide

Tool Integrations

| Tool | Purpose | Integration Method | |------|---------|-------------------| | Sourcegraph | Code search | API | | GitHub API | Commit history | API | | grep/ripgrep | Pattern search | CLI | | Custom NLP | Text analysis | Library | | Confluence API | Wiki extraction | API |

Output Schema

json
{
  "extractionId": "string",
  "timestamp": "ISO8601",
  "knowledge": {
    "comments": [
      {
        "type": "todo|fixme|note|warning|explanation",
        "file": "string",
        "line": "number",
        "content": "string",
        "context": "string"
      }
    ],
    "commits": [
      {
        "hash": "string",
        "message": "string",
        "author": "string",
        "context": "string",
        "relatedFiles": []
      }
    ],
    "documentation": [],
    "businessRules": [],
    "glossary": {}
  }
}

Integration with Migration Processes

legacy-codebase-assessment: Knowledge discovery
documentation-migration: Source material

Related Skills

legacy-code-interpreter: Code understanding
documentation-generator: Doc creation

Related Agents

legacy-system-archaeologist: Uses for excavation
documentation-migration-agent: Uses for doc creation

Want to see if a5c-ai/knowledge-extractor would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.