Fix regressions in slimmed agent skills - #59
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughUpdated agent skill documentation for reaction retrieval, CLI setup and fallback behavior, Matter automation guidance, and backlog-planning procedures. ChangesAgent guidance
Estimated code review effort: 1 (Trivial) | ~5 minutes Possibly related PRs
Suggested labels: Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
.agents/skills/review-planning/backlog-planner/SKILL.md (1)
31-31: 🗄️ Data Integrity & Integration | 🔵 Trivial | ⚡ Quick winDefine the fallback for repositories with different board statuses.
This is conditional only when the exact
Backlog→Donevalues exist. In repositories with differently named statuses, instruct agents to map semantic stages to existing values or report the intended transition when no equivalent exists.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.agents/skills/review-planning/backlog-planner/SKILL.md at line 31, Update the status guidance in the backlog-planner instructions to apply the named Backlog-through-Done sequence only when those exact board values exist. For repositories with different statuses, instruct agents to map each semantic stage to the closest existing value, or report the intended transition when no equivalent exists, rather than inventing labels.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.agents/skills/productivity/tripsy-cli/SKILL.md:
- Around line 13-14: Add an explicit availability check after resolving
TRIPSY_BIN from the local wrapper or command lookup, and fail with a clear
Tripsy-unavailable message when it is empty or non-executable. Ensure this guard
runs before any doctor or read command uses TRIPSY_BIN.
---
Nitpick comments:
In @.agents/skills/review-planning/backlog-planner/SKILL.md:
- Line 31: Update the status guidance in the backlog-planner instructions to
apply the named Backlog-through-Done sequence only when those exact board values
exist. For repositories with different statuses, instruct agents to map each
semantic stage to the closest existing value, or report the intended transition
when no equivalent exists, rather than inventing labels.
🪄 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: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 28f77380-466f-47f0-8e68-72e3a5b91077
📒 Files selected for processing (5)
.agents/skills/development/pr-babysitter/references/codex-review-signals.md.agents/skills/productivity/matter-cli/SKILL.md.agents/skills/productivity/mela-recipe-manager/SKILL.md.agents/skills/productivity/tripsy-cli/SKILL.md.agents/skills/review-planning/backlog-planner/SKILL.md
💤 Files with no reviewable changes (1)
- .agents/skills/productivity/matter-cli/SKILL.md
There was a problem hiding this comment.
Pull request overview
This PR updates several Codex agent skill documents in this dotfiles repo to address regressions introduced by the “slimmed” skill restructuring, mainly by tightening setup/usage instructions and making repo-specific assumptions conditional.
Review Findings (ordered by severity)
- Bug:
.agents/skills/productivity/tripsy-cli/SKILL.md’sTRIPSY_BINresolution snippet can leave the variable empty when Tripsy isn’t installed, causing later documented commands to fail with a confusing error.
Changes:
- Make backlog planning guidance conditional on the target repository’s existing labels and project field values.
- Ensure Tripsy CLI usage docs resolve the binary once per shell before using it in subsequent commands.
- Update Mela setup docs to install
mela-clivia the pinned venv’s Python, remove Matter automation notes, and fetch all PR reactions (unfiltered) for Codex “eyes” lock visibility.
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| .agents/skills/review-planning/backlog-planner/SKILL.md | Adds repo/label/project-field verification steps and makes taxonomy usage conditional on what exists in the target repo. |
| .agents/skills/productivity/tripsy-cli/SKILL.md | Documents a shell-level Tripsy binary resolution pattern to avoid using an uninitialized path. |
| .agents/skills/productivity/mela-recipe-manager/SKILL.md | Clarifies pinned-venv installation by invoking pip via the venv Python explicitly. |
| .agents/skills/productivity/matter-cli/SKILL.md | Removes automation-location/config guidance from the Matter CLI skill. |
| .agents/skills/development/pr-babysitter/references/codex-review-signals.md | Updates the reactions probe to fetch all reactions so Codex eyes locks aren’t hidden by filtering. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
Addressed CodeRabbit’s review-body status-mapping finding in b3f778d: the default flow now applies only to matching board values, different names map to the closest existing semantic stage, and missing equivalents are reported rather than created. Validation: |
Summary
eyeslocks are visibleThe changes preserve the slimmer GPT-5.6-oriented skill structure and do not restore the deleted Python test suites or redundant general-agent guidance.
Validation
./scripts/check.shgit diff --checkSummary by CodeRabbit
gh apicommand to paginate reactions without filtering to “+1”.meladoctor setup guidance to ensure the CLI is installed inside the created virtual environment.