[PM-33941] llm: Refine skills and commands for agent reliability#6703
Open
SaintPatrck wants to merge 2 commits intomainfrom
Open
[PM-33941] llm: Refine skills and commands for agent reliability#6703SaintPatrck wants to merge 2 commits intomainfrom
SaintPatrck wants to merge 2 commits intomainfrom
Conversation
- work-on-android: Use Skill() invocation syntax so agents trigger skills correctly instead of treating them as prose - build-test-verify: Add detekt precommit flag guidance and output filtering to capture violations on first run - testing-android-code: Promote @Suppress("MaxLineLength") rule from buried bullet to prominent stop-warning to prevent agents from copying the annotation without verifying line length
github-actions
bot
added
the
t:llm
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #6703 +/- ##
==========================================
- Coverage 85.67% 85.63% -0.04%
==========================================
Files 852 926 +74
Lines 59107 60201 +1094
Branches 8435 8519 +84
==========================================
+ Hits 50641 51555 +914
- Misses 5524 5683 +159
- Partials 2942 2963 +21
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Contributor
|
Claude finished @SaintPatrck's task in 1m 27s —— View job Code Review Complete
SummaryReviewed all 3 changed files. No new actionable findings — the previous review's suggestions (article consistency in The changes are well-scoped and improve agent reliability:
No blocking issues. |
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
Contributor
|
Fixed Issues (1)Great job! The following issues were fixed in this Pull Request
|
Fix inconsistent Invoke phrasing in work-on-android command and replace git add -A with git add -u in detekt command to avoid staging unintended files.
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.
🎟️ Tracking
https://bitwarden.atlassian.net/browse/PM-33941
📔 Objective
Improves Claude Code skill and command reliability for agent-driven development:
Skill()invocation syntax so agents trigger skills correctly instead of treating references as prose-Pprecommit=trueflag guidance and output grep filtering to capture violations on the first run@Suppress("MaxLineLength")rule from a buried bullet to a prominent blockquote warning, preventing agents from reflexively copying the annotation without verifying line length