[FEATURE] CLAUDE.md export — generate from ZeroDB memories - #29
Merged
Merged
Conversation
…ZeroDB memories - Add skills/claudemd-export/SKILL.md: full generation logic including project detection, broad semantic retrieval (up to 200 memories, 6 queries), grouping by type, deduplication, and structured CLAUDE.md output - Update skills/memory/SKILL.md: delegate claudemd format to the new skill, document --dry-run and merge mode in the export subcommand section - Add TestCLAUDEmdExport (6 tests) to tests/e2e/test_zerodb_api.py covering file existence, frontmatter, all 6 memory types, dedup logic, --dry-run, and update-vs-create/merge flow Refs #16
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
skills/claudemd-export/SKILL.md— dedicated skill implementing the full/memory export --format claudemdworkflow: project detection via git remote, broad semantic retrieval across 6 query types (up to 200 memories), grouping by memory type, deduplication of semantically equivalent facts, and structured CLAUDE.md generationskills/memory/SKILL.md— replaces the stubclaudemdformat description with a delegation note pointing to the new skill; documents--dry-runand merge modeTestCLAUDEmdExportclass totests/e2e/test_zerodb_api.pywith 6 tests verifying skill file existence, frontmatter validity, all 6 memory type mappings, deduplication logic,--dry-runsupport, and update-vs-create/merge flowTest Plan
TestCLAUDEmdExport— 6 tests, all passing (pytest tests/e2e/test_zerodb_api.py::TestCLAUDEmdExport -v)description:fieldarchitecture,convention,ownership,in-progress,bug,correction) mapped to CLAUDE.md sections--dry-runflag documented and clarified as no-writeRisk/Rollback
Low risk — skill files and tests only, no runtime code changes. Rollback by reverting the three changed files.
Closes #16