improve: enhance prompt-engineer agent#456
Merged
Merged
Conversation
- Fix broken reasoning framework: complete Ordering field and Necessity scale - Remove OpenAI attribution from description; add invocation example block - Restrict tools to Read only (text-transformation agent needs no writes) - Add XML Structure and CoT Opportunity dimensions to reasoning template - Move meta-instruction NOTE out of output template, place as agent directive - Fix stray markdown bold markers on Reasoning Before Conclusions guideline - Integrate orphaned examples bullet into the Examples guideline line - Add concrete worked example section (classify customer feedback) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
|
| Metric | Count |
|---|---|
| Total Components | 753 |
| ✅ Passed | 360 |
| ❌ Failed | 393 |
| 999 |
❌ Failed Components (Top 5)
| Component | Errors | Warnings | Score |
|---|---|---|---|
vercel-edge-function |
3 | 4 | 81/100 |
prompt-engineer |
2 | 0 | 90/100 |
neon-expert |
2 | 2 | 88/100 |
agent-overview |
2 | 1 | 89/100 |
unused-code-cleaner |
2 | 1 | 89/100 |
...and 388 more failed component(s)
📊 View Full Report for detailed error messages and all components
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Automated Component Improvement
Changes
Necessity: ()is now fully defined as a 1-5 scale;Ordering:sentence was truncated and is now complete<example>block showing orchestrator routing patternRead, Bash, Grep, Glob, Edit, Writeto justRead; this is a text-transformation agent with no need for filesystem writes or shell executionXML StructureandCoT Opportunityfields to the<reasoning>template[NOTE: you must start with a <reasoning> section...]out of the output template footer and placed it as a clear agent directive above the framework**fromReasoning Before Conclusions**:headingWhat kinds of examples...bullet into the Examples guideline line# Examplesection shows vague input, completed<reasoning>block, and resulting improved prompt (classify customer feedback)Research Summary
The original component had two broken fields in its core reasoning framework (
Necessitywas empty,Orderingwas a sentence fragment), which would cause inconsistent agent output. The description contained a third-party attribution that misrepresented the component's basis. The tool list granted unnecessary filesystem write access to a read-only text-transformation agent. Two Anthropic-recommended prompting considerations (XML structure and chain-of-thought) were absent from the evaluation framework.Validation
name,description,tools,model)prompt-engineer)data-ai/)Automated review cycle by Component Improvement Loop
Summary by cubic
Enhances the prompt-engineer agent to produce more consistent, safe, and useful prompt rewrites. Fixes gaps in the reasoning template, tightens tool permissions, and adds a clear example.
cli-tool/components/); modifiedagents/data-ai/prompt-engineer.md. No new components; no catalog (docs/components.json) regeneration needed; no new env vars or secrets.NecessityandOrdering; addedXML StructureandCoT Opportunity.Readto match a text-only transformation agent.Written for commit f44ba7e. Summary will update on new commits.