alihan/repomix
1
0
Fork 0
mirror of https://github.com/yamadashy/repomix.git synced 2025-06-11 00:25:54 +03:00
Code Issues Packages Projects Releases Wiki Activity

docs(claude): Clarify dialogue section format in commit messages

Browse Source 
Based on user conversation:
- User wanted dialogue part to be clearly distinguishable
- User suggested using headers like 'Generated from the following user dialogue:'
- User preferred bullet point format for dialogue summary
- Assistant updated examples to show clear section separation
- Makes it obvious which part contains user-AI conversation context

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Kazuki Yamada
2025-06-08 18:09:15 +09:00
parent 60ecce1ce7
commit 19476abfcb
1 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
CLAUDE.md
View File

@@ -121,15 +121,16 @@ npm run test
- Follow [Conventional Commits](https://www.conventionalcommits.org/) with scope: `type(scope): Description` - Follow [Conventional Commits](https://www.conventionalcommits.org/) with scope: `type(scope): Description`
- Write detailed commit messages focusing on the "why" rather than the "what" - Write detailed commit messages focusing on the "why" rather than the "what"
- **Include user dialogue context**: Reference the specific conversation or request that led to the change in the commit body - **Include user dialogue context**: Reference the specific conversation or request that led to the change in the commit body
- Format: Use title for technical change, body for user context and reasoning with clear dialogue markers - Format: Use title for technical change, body with clear dialogue section marker
- Use dialogue format with "User:" and "Assistant:" or narrative descriptions of the conversation flow - Start dialogue section with header like "Generated from the following user dialogue:" or "Based on user conversation:"
- Examples: - Examples:
``` ```
feat(cli): Add new --no-progress flag feat(cli): Add new --no-progress flag
User: "Can we disable progress output for CI environments?" Generated from the following user dialogue:
Assistant: Added --no-progress flag to reduce noise in build logs - User requested disabling progress output for CI environments
and improve automation compatibility. - Progress output creates noise in build logs
- Assistant implemented --no-progress flag for automation compatibility
🤖 Generated with [Claude Code](https://claude.ai/code) 🤖 Generated with [Claude Code](https://claude.ai/code)
@@ -138,14 +139,13 @@ npm run test
``` ```
perf(metrics): Optimize token counting for top files perf(metrics): Optimize token counting for top files
User: "Is token counting only used for top files display?" Based on user conversation:
Assistant: Explained it's used for multiple purposes including total output size - User asked: "Is token counting only used for top files display?"
User: "Since chars and tokens correlate, why not pre-filter by chars first?" - Assistant explained multiple use cases including total output size
Assistant: Implemented character-based pre-filtering with 10x multiplier - User suggested: "Since chars and tokens correlate, pre-filter by chars first"
User: "Can we increase to 10x?" → Changed from 5x to 10x for better accuracy - User requested increasing multiplier from 5x to 10x for better accuracy
User: "Change display order to tokens first" → Updated CLI and website - User requested changing display order to show tokens before characters
- Assistant implemented optimization reducing computation by ~90%
Reduces computation by ~90% while maintaining ranking accuracy.
🤖 Generated with [Claude Code](https://claude.ai/code) 🤖 Generated with [Claude Code](https://claude.ai/code)