Feat/quality analyst agent#17
Merged
Merged
Conversation
Adds a Claude Code subagent that generates requirement-driven test plans with a --type argument to generate only the sections needed. Supported --type values: manual → Section A: happy path, edge cases, boundary inputs, roles functional → Section B: acceptance criteria, business rules, data integrity performance → Section C: baseline time, data volume, concurrency, pagination security → Section D: auth/IDOR, input sanitisation, data exposure, CSRF accessibility → Section E: keyboard nav, screen reader, contrast, responsive usability → Section F: design system, error messaging, confirmations reliability → Section G: network failure, logging, i18n, compliance all → All sections A-G (default when --type is omitted) Comma-separated multi-section support: --type manual,security The agent performs static code analysis before generating test cases to auto-assign priorities (HIGH/MEDIUM/LOW) based on detected risk signals. Code analysis is skipped for manual/accessibility/usability-only runs. Also updates root README.md to list the new recipe.
Collaborator
Author
|
@rathorevaibhav can you review the PR |
deepankar-sajwan
requested review from
rathorevaibhav
and removed request for
pokhiii
…r sections - Remove standalone Section A (Manual) — manual execution steps (Actor, Preconditions, Steps, Expected result) are now embedded in every functional test case so testers need only one section to execute tests - Expand Section A (Functional, formerly B) with FT-01–FT-10 covering happy path, alternative path, empty state, boundary inputs, error path, business rules, data integrity, state transitions, role-based access, and integration tests — all with full manual execution format - Add manual-style Steps + Pass criteria blocks to all usability cases (UX-01, UX-02, UX-03) while keeping checklists for quick reference - Renumber sections C–G → B–F and update all references accordingly - Remove `manual` from --type supported values table and skipped sections note Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
rathorevaibhav
approved these changes
May 13, 2026
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
2 participants
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
quality-analyst-agentthat generates structured, requirement-driven test plans from GitHub issues, PRs, or plain-text requirements--typeflag (manual,functional,performance,security,accessibility,usability,reliability,all)business-analystandimplementation-executor(rich description with examples,color,memory: project, Persistent Agent Memory section)Changes
claude/agents/quality-analyst/quality-analyst.md— agent definition with 7 test sections (A–G), step-by-step generation process, code diff scanning, risk summaries, and agent rulesclaude/agents/quality-analyst/README.md— setup guide,--typereference table, and usage examplesTest plan
--type manualgenerates only Section A and appends a skipped sections note--type performance,securitygenerates only Sections C and Ddocs/test-plans/when no GitHub context is provided--typevalue prints the supported values table and stops🤖 Generated with Claude Code