codekb-extract

Extract structured knowledge from source code, git history, and OpenSpec changes.

1|Updated Jun 27, 2026
One-click install
npx skills add https://github.com/TE-QuanBZhang/skills-pool --skill codekb-extract-te-quanbzhang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: codekb-extract
Source: https://github.com/TE-QuanBZhang/skills-pool/tree/main/codekb/skills/codekb-extract
Command: npx skills add https://github.com/TE-QuanBZhang/skills-pool --skill codekb-extract-te-quanbzhang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Valuable engineering knowledge—design decisions, business rules, coding conventions, and bug patterns—stays buried in code and commit history, forcing teams to rediscover it repeatedly. ## Core Features & Use Cases - Five LLM-Powered Extractors: pattern (architecture), decision (lightweight ADRs), rule (business rules), convention (coding standards), and bug-pattern (defect patterns from fix commits). - OpenSpec Integration: Run extraction from an archived OpenSpec change with --from-change to close the knowledge feedback loop. - Quality Guardrails: Content-hash caching avoids redundant LLM calls, low-confidence entries (< 0.7) are flagged for review, and supersede links keep knowledge current. - Use Case: After archiving an OpenSpec change like add-refund-fee, run extraction to automatically capture the new business rules and design decisions into the knowledge base. ## Quick Start Ask the AI to run codekb extract on the current project to generate structured knowledge entries from the codebase and git history.

Frequently Asked Questions about codekb-extract

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract knowledge from code and git history?▼

Run `codekb extract` to execute all configured extractors against your project. Use `--scope` to limit directories, `--extractors` to select specific types like decision or rule, and `--from-change` to extract from an archived OpenSpec change.

What knowledge extractors does CodeKB support?▼

CodeKB provides five extractors: pattern for architecture patterns, decision for lightweight ADRs from commits and code comments, rule for business rules, convention for coding standards, and bug-pattern for defect patterns from fix commits.

Does codekb extract require an LLM API key?▼

An LLM API key is optional. CodeKB falls back to heuristic extraction when no key is configured, so basic knowledge extraction still works without LLM access.

How do I extract knowledge from an OpenSpec change?▼

Run `codekb extract --from-change <change-name>` after archiving the change. This sets the source_change field on generated entries for traceability back to the originating OpenSpec change.

Why are some extracted knowledge entries flagged for review?▼

Entries with confidence below 0.7 are flagged as pending review and excluded from automatic association in /opsx:propose. Review and confirm these entries before they participate in downstream workflows.

When should I not run codekb extract?▼

Do not run extraction on a hotfix branch, since the skill operates in read-only mode there. Also avoid re-running full extraction unnecessarily; use --stale to refresh only entries marked potentially stale.