refactor(bugfix): remove manual skill-loading boilerplate#107
Open
jwm4 wants to merge 1 commit intoambient-code:mainfrom
Open
refactor(bugfix): remove manual skill-loading boilerplate#107jwm4 wants to merge 1 commit intoambient-code:mainfrom
jwm4 wants to merge 1 commit intoambient-code:mainfrom
Conversation
The bugfix workflow was engineered around a platform bug where the skill tool wasn't working. Skills were loaded via the Read tool with explicit file paths, and every phase skill had dispatch/return blocks telling the agent which file to re-read after completion. Now that the skill tool works, this scaffolding is unnecessary and actively harmful — it encourages the agent to bypass the platform's native skill invocation. Changes across 13 files in workflows/bugfix/: - Replace file paths with skill names in controller and speedrun - Remove "How to Execute" Read tool instructions from orchestrators - Remove dispatch blocks from all 7 phase skills - Remove return-and-re-read instructions from all phase skills - Remove "Always read skill files" rule from controller - Update ambient.json systemPrompt and CLAUDE.md to use skill names The actual phase logic, gating rules, artifact paths, and recommendation logic are all unchanged. ADR: docs/adr/2026-04-14-skill-invocation-cleanup.md Made-with: Cursor
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: ASSERTIVE Plan: Pro Plus Run ID: 📒 Files selected for processing (14)
💤 Files with no reviewable changes (8)
WalkthroughThe pull request implements an ADR to simplify the bugfix workflow by removing manual skill-invocation boilerplate. Phase skills no longer include dispatch blocks or re-read instructions. The controller and speedrun skills are updated to reference phases by skill name instead of hardcoded file paths. System prompt and documentation are adjusted accordingly. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 🚥 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)
Warning Review ran into problems🔥 ProblemsTimed out fetching pipeline failures after 30000ms Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
Author
Contributor
|
✅ Actions performedReview triggered.
|
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.
Summary
.claude/skills/*/SKILL.md) with skill names (the assess skill) so the agent uses the platform's native skill invocation instead of the Read toolContext
The bugfix workflow was engineered around a platform bug where the skill tool wasn't working. Skills were loaded via the Read tool with explicit file paths, and every phase skill had dispatch/return blocks telling the agent which file to re-read after completion. Now that the skill tool works, this scaffolding is unnecessary — it encourages the agent to bypass native skill invocation and makes the workflow non-portable across different runners.
ADR:
docs/adr/2026-04-14-skill-invocation-cleanup.mdWhat changed
ambient.jsonCLAUDE.mdcontroller/SKILL.mdspeedrun/SKILL.mdpr/SKILL.mdsummary/SKILL.mdWhat did NOT change
Test plan
ambient.jsonparses correctly/diagnose)Custom Workflow fields for testing
https://github.com/jwm4/workflows.gitrefactor/bugfix-skill-invocation-cleanupworkflows/bugfixMade with Cursor