docs: clarify README and agent skill#152
Conversation
Code Review SummaryStatus: No Issues Found | Recommendation: Merge Files Reviewed (1 file)
Previous Review Summaries (3 snapshots, latest commit 4ef96d2)Current summary above is authoritative. Previous snapshots are kept for context only. Previous review (commit 4ef96d2)Status: No Issues Found | Recommendation: Merge Files Reviewed (2 files)
Previous review (commit dd7a8f3)Status: 1 Issue Found | Recommendation: Address before merge Overview
Issue Details (click to expand)WARNING
Files Reviewed (5 files)
Fix these issues in Kilo Cloud Previous review (commit a5528a0)Status: No Issues Found | Recommendation: Merge Files Reviewed (2 files)
Reviewed by kimi-k2.6-20260420 · Input: 56.2K · Output: 3.9K · Cached: 109.1K |
There was a problem hiding this comment.
Pull request overview
Documentation-focused update that rewrites the README and bundled agent skill to emphasize concrete repository questions, first-use workflows, stable output shapes, and explicit tradeoffs/freshness rules.
Changes:
- Restructures
README.mdinto question-driven workflows with abbreviated durable output examples and updated onboarding guidance. - Reworks
codegraph-skill/codegraph/SKILL.mdinto a task-to-command decision guide, including explicit--rootboundary rules and MCP freshness/lifecycle guidance.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| README.md | Rewrites the top-level README around concrete questions, first-run workflows, durable output shapes, and updated agent setup guidance. |
| codegraph-skill/codegraph/SKILL.md | Restructures the bundled skill into a decision guide with explicit project-boundary, output-consumer, sensitive-file, and MCP freshness rules. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Summary
Review findings addressed
explorecounts and ordering with a durable abbreviated output shapeorientbudget, which skips health analysis by defaultWhy not just grep or an LSP?table-of-contents entryVerification
npm run check- 178 test files passed; 2,178 tests passed; 1 skippednpx vitest run tests/package-metadata.test.ts- 37 tests passed