feat: improve requirements command prompt quality#187
Closed
tractorjuice wants to merge 1 commit intomainfrom
Closed
feat: improve requirements command prompt quality#187tractorjuice wants to merge 1 commit intomainfrom
tractorjuice wants to merge 1 commit intomainfrom
Conversation
Expand NFR subcategories from 5 generic to 7 specific (added Availability/Resilience, Usability, Maintainability/Observability with sub-prefixes). Add explicit use case structure (UC-xxx with main/alt/exception flows), Given/When/Then acceptance criteria, and persona structure guidance. Found via autoresearch experiment loop (score 8.4 → 9.2). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
tractorjuice
added a commit
that referenced
this pull request
Mar 27, 2026
Merged 6 pre-autoresearch prompt quality PRs into the combined branch: - #187 requirements: user personas, UC structure, Given/When/Then AC - #188 adr: measurable consequences with project-specific metrics - #189 backlog: strict acceptance criteria rules (testable, thresholds) - #191 wardley: math-validated stage boundaries table - #192 wardley.value-chain: visibility rationale and validation checklist - #194 wardley.climate: recommended action field with specificity rules All autoresearch additions (scores, traceability) preserved alongside the quality improvements. Lint passes. Converter regenerated. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Owner
Author
|
Merged into #265 (combined autoresearch PR) |
tractorjuice
added a commit
that referenced
this pull request
Apr 6, 2026
Merged 6 pre-autoresearch prompt quality PRs into the combined branch: - #187 requirements: user personas, UC structure, Given/When/Then AC - #188 adr: measurable consequences with project-specific metrics - #189 backlog: strict acceptance criteria rules (testable, thresholds) - #191 wardley: math-validated stage boundaries table - #192 wardley.value-chain: visibility rationale and validation checklist - #194 wardley.climate: recommended action field with specificity rules All autoresearch additions (scores, traceability) preserved alongside the quality improvements. Lint passes. Converter regenerated. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
How these changes were found
Used the autoresearch command prompt optimiser — an autonomous experiment loop that runs the command, scores output quality, tweaks the prompt, and keeps/discards based on score delta.
Net: +6 lines of prompt, score 8.4 → 9.2
Test plan
/arckit:requirementsagainst a test project and verify output includes all 7 NFR subcategoriespython scripts/converter.pyto regenerate extension formats🤖 Generated with Claude Code