Add estimate and debug skills#2048
Conversation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
✅ Files skipped from review due to trivial changes (1)
📝 WalkthroughWalkthroughThis PR adds two skill documentation files ( Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
skills/estimate.md (1)
17-17: Tighten repeated phrasing for readability.Line 17 repeats “If … ask …” patterns several times in one sentence. Consider splitting into shorter bullets for easier parsing.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@skills/estimate.md` at line 17, The sentence that begins "Look for any compose.yaml files in the current directory or parent directories..." is overly repetitive; rewrite it as short bullets describing the sequence of checks and user prompts: 1) search for compose.yaml files and if multiple are found prompt the user to select one, 2) if none are found ask whether to create a new compose.yaml, and 3) if they choose to create, prompt for desired services and generate the file from their answers; replace the single long sentence with these 3 concise bullets to remove repeated "If … ask …" phrasing and improve readability.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@skills/debug.md`:
- Line 25: Update the guidance around "Note the active stack (provider, region,
deployment mode)." to explicitly handle the case where `defang stack ls` returns
no stacks: add a branch that states "No deployment found yet" and instruct the
user to deploy first (e.g., run the project's deploy command) or verify they're
in the correct project directory; also keep the existing advice to select/set a
default stack (e.g., `defang stack default STACK_NAME`) if stacks are present.
Ensure the new text clearly contrasts the "no stacks" path from the existing
"stack exists but not selected" path so users aren't left at a dead-end.
---
Nitpick comments:
In `@skills/estimate.md`:
- Line 17: The sentence that begins "Look for any compose.yaml files in the
current directory or parent directories..." is overly repetitive; rewrite it as
short bullets describing the sequence of checks and user prompts: 1) search for
compose.yaml files and if multiple are found prompt the user to select one, 2)
if none are found ask whether to create a new compose.yaml, and 3) if they
choose to create, prompt for desired services and generate the file from their
answers; replace the single long sentence with these 3 concise bullets to remove
repeated "If … ask …" phrasing and improve readability.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: be9780a4-6079-4b5c-b7a9-6924d00ae91d
📒 Files selected for processing (4)
.agents/plugins/marketplace.json.claude-plugin/marketplace.jsonskills/debug.mdskills/estimate.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Summary
/defang:estimateskill — guides through finding a compose.yaml, selecting a stack (or prompting for provider/region/mode), runningdefang compose estimate, and explaining the cost breakdown/defang:debugskill — checks deployment status viadefang compose ps, fetches recent logs, scans for common error patterns, and produces a structured diagnosis with next steps.agents/plugins/marketplace.jsonand.claude-plugin/marketplace.jsonto reference all three skillsTest plan
/defang:estimateon a project with an existing stack and verify it runsdefang compose estimateand explains results/defang:estimateon a project with no stacks and verify it prompts for provider/region/mode/defang:debugon a healthy deployment and verify status + log summary/defang:debugon a deployment with errors and verify it surfaces the root cause and recommends next steps🤖 Generated with Claude Code
Summary by CodeRabbit
New Features
Documentation
Chores