collab-proof

Generates session documentation and HTML proof of AI collaboration from git history and conversation analysis.

25.3k|3.6k|Updated Oct 19, 2025
One-click install
npx skills add https://github.com/alirezarezvani/claude-skills --skill collab-proof
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: collab-proof
Source: https://github.com/alirezarezvani/claude-skills/tree/main/engineering/collab-proof/skills/collab-proof
Command: npx skills add https://github.com/alirezarezvani/claude-skills --skill collab-proof

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI-assisted coding sessions leave no trace of who contributed what or why decisions were made. This Skill analyzes your Claude Code session and git history to produce calibrated evidence of AI versus developer contributions, decisions, and reasoning.

Core Features & Use Cases

  • Signal Detection: Classifies sessions as HIGH, MEDIUM, or LOW signal using git diff stats and conversation analysis, so routine sessions produce no noise.
  • Four-Frame Intent Classification: Scores technical complexity, uncertainty, decision forks, and AI contribution to classify sessions as FEATURE_BUILDING, BUG_FIXING, REFACTORING, and more.
  • Calibrated Evidence Artifacts: Generates DECISIONS.md entries, session-history markdown, WORKLOG lines, and a self-contained HTML proof file with token usage stats.
  • Use Case: After a debugging session where Claude identified a root cause, run the skill to append a structured bug-fix record to DECISIONS.md and generate a shareable HTML proof for your portfolio.

Quick Start

Ask Claude to run /collab-proof at the end of your coding session to analyze what was built and generate the collaboration evidence artifacts.

Frequently Asked Questions about collab-proof

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

FAQPage Schema
How do I document what Claude contributed in a coding session?

Run /collab-proof at session end. It analyzes git log, git diff, and conversation context, scores four reasoning frames, then writes DECISIONS.md entries, a session-history markdown file, and an HTML proof summarizing AI versus developer contributions.

What is AI collaboration evidence for developer portfolios?

AI collaboration evidence shows what you decided versus what the AI suggested or identified. collab-proof generates a self-contained HTML file with decision records, frame scores, and token usage that you can attach to portfolios, PRs, or job applications.

Does collab-proof record every coding session?

No. It uses a three-level signal filter: HIGH sessions get full artifacts, MEDIUM sessions get a single WORKLOG line, and LOW sessions like typo fixes or routine changes record nothing. This keeps documented sessions meaningful.

How does collab-proof handle context compaction during long sessions?

A PreCompact hook writes lightweight JSON snapshots to session-history/.tmp-*.json before context is lost. At session end, snapshots are merged by taking max frame scores and combining key moments, then deleted.

Can the HTML proof be tampered with or backdated?

The HTML footer embeds the last git commit hash, linking the artifact to a verifiable code state. The references describe optionally attaching a SHA-256 hash of the file via git notes for tamper-evident verification.