Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

improvement: simplify Skill node description in exported MD files#547

Merged
breaking-brake merged 1 commit intomainbreaking-brake/cc-wf-studio:mainfrom
improvement/simplify-skill-node-export-descriptionbreaking-brake/cc-wf-studio:improvement/simplify-skill-node-export-descriptionCopy head branch name to clipboard
Feb 7, 2026
Merged

improvement: simplify Skill node description in exported MD files#547
breaking-brake merged 1 commit intomainbreaking-brake/cc-wf-studio:mainfrom
improvement/simplify-skill-node-export-descriptionbreaking-brake/cc-wf-studio:improvement/simplify-skill-node-export-descriptionCopy head branch name to clipboard

Conversation

@breaking-brake
Copy link
Copy Markdown
Owner

@breaking-brake breaking-brake commented Feb 7, 2026

Summary

Simplify Skill node output in exported MD files to prevent AI coding agents from misinterpreting verbose descriptions.

What Changed

Skill node descriptions in exported slash command / skill MD files were too verbose, causing some AI agents to read the MD file content instead of executing the Skill properly.

Before

  • Exported Skill nodes included 7+ lines of metadata (Description, Scope, ValidationStatus, SkillPath, ExecutionMode, etc.)
  • Verbose execution instructions confused AI agents into "reading and interpreting" instead of "executing as Skill"

After

  • Concise single-line prompt format: skill "name", skill "name" "prompt", or skill "name" load-skill-knowledge-into-context-only
  • Clear, actionable instructions that AI agents can follow without ambiguity

Changes

  • src/extension/services/workflow-prompt-generator.ts - Simplified Skill node section in generateExecutionInstructions() from ~30 lines to ~6 lines per node

Testing

  • Build passes (npm run format && npm run lint && npm run check && npm run build)
  • Manual E2E testing pending

🤖 Generated with Claude Code

- Remove verbose metadata (Description, Scope, ValidationStatus, SkillPath, ExecutionMode)
- Use concise prompt-style format for Skill nodes
- load mode: skill "name" load-skill-knowledge-into-context-only
- execute mode: skill "name" or skill "name" "executionPrompt"

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@breaking-brake breaking-brake merged commit 3fc1f6c into main Feb 7, 2026
3 checks passed
@breaking-brake breaking-brake deleted the improvement/simplify-skill-node-export-description branch February 7, 2026 16:44
@breaking-brake breaking-brake mentioned this pull request Feb 7, 2026
braking-brake-semantic-release Bot pushed a commit that referenced this pull request Feb 7, 2026
## [3.20.0](v3.19.2...v3.20.0) (2026-02-07)

### Features

* add Roo Code skills integration (export & run) ([#543](#543)) ([913eba0](913eba0))

### Improvements

* add persistent memory setting to SubAgent and SubAgentFlow nodes ([#541](#541)) ([b48acd7](b48acd7))
* add Roo Code skills detection and documentation ([#545](#545)) ([5db6252](5db6252))
* simplify Skill node description in exported MD files ([#547](#547)) ([3fc1f6c](3fc1f6c))
@braking-brake-semantic-release
Copy link
Copy Markdown

🎉 This PR is included in version 3.20.0 🎉

The release is available on GitHub release

Your semantic-release bot 📦🚀

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant

Morty Proxy This is a proxified and sanitized view of the page, visit original site.