feat: retroactive bootstrap analyzer for Claude Code history#3
Merged
feat: retroactive bootstrap analyzer for Claude Code history#3
Conversation
Implements `skill-issue analyze` command that scans Claude Code session history (JSONL files) to infer initial mastery scores based on conversation patterns: - User questions about a concept → weakness signal (-0.15) - User assertions/code with a concept → strength signal (+0.20) - Claude-only mentions → neutral/slight positive (+0.05) - Final scores clamped to [0.0, 0.8] Integration: - New `skill-issue analyze` CLI command with --all, --dry-run, --max-sessions - Opt-in prompt during `skill-issue init` to bootstrap from history - Detects concepts via node names, IDs, and aliases from knowledge graphs This addresses the cold-start problem: new users can start with knowledge state calibrated to their actual demonstrated understanding rather than a blank slate. Co-Authored-By: Claude Opus 4.5 <[email protected]>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
skill-issue analyzecommand to bootstrap knowledge state from Claude Code conversation historyskill-issue initwith opt-in prompt for automatic bootstrappingHow it works
The analyzer scans Claude Code session JSONL files and infers mastery scores:
Final scores clamped to [0.0, 0.8] (max 0.8 since we can't be sure of full mastery from history alone).
Commands
Test plan
python3 -m pytest tests/ -v)skill-issue analyze --helpshows correct optionsskill-issue analyze --dry-run --allproduces sensible output🤖 Generated with Claude Code