AGENT SKILL

session-report

Produce, save, and file the end-of-session QA summary for a WAY 1 (browser) or WAY 2 (API) run — execution counts, failed test cases, accessibility table (WAY 1), schema/performance flags (WAY 2), bugs filed. Replaces the former session-reporter agent.

License 许可
MIT
最近更新
2026-11-06
Stars
★ 5
Forks
4

01 前言 Front Matter

name
session-report
description
Produce, save, and file the end-of-session QA summary for a WAY 1 (browser) or WAY 2 (API) run — execution counts, failed test cases, accessibility table (WAY 1), schema/performance flags (WAY 2), bugs filed. Replaces the former session-reporter agent.

03 SKILL.md 正文

session-report

Apply in the main session at the end of WAY 1 (Phase 5) or WAY 2 (Phase 4). Everything it needs is already in context, so it runs inline:

  • Environment URL (WAY 1) or API base URL + spec source (WAY 2)
  • test-execution-agent's results YAML. Each entry has status, page, a11y: { checked, violations }, and for API scenarios the api-responses/ capture
  • Bugs filed in this session: ref, title, labels (from the bug-report skill + tracker)

Where it goes

  1. Save to ./qa-artifacts/sessions/session-<YYYY-MM-DD-HH-MM>.md (WAY 1) or ./qa-artifacts/sessions/api-<YYYY-MM-DD-HH-MM>.md (WAY 2)
  2. Print it to chat
  3. WAY 1: file it as an issue labeled qa-session-report (issue.create, per tracker), with the same body

WAY 1 template

Build the Accessibility Report by grouping results on their page field and counting violations by impact.

# QA Session Report
**Date:** [ISO date]
**Environment:** [URL]
**Triggered by:** [Feature name or issue ref]

---

## Test Execution Summary

| Status | Count |
|---|---|
| ✅ Passed | N |
| ❌ Failed | N |
| ⚠️ Blocked | N |
| ⏭️ Skipped | N |
| **Total** | **N** |

---

## Failed / Blocked Test Cases

| Test | Title | Status | Failure point | Artifact |
|---|---|---|---|---|
| Test#02 | Login rejects invalid password | ❌ fail | Step 3 — no error message shown | runs/<id>/artifacts/… |

---

## Not Filed as Bugs

| Test | Why | Follow-up |
|---|---|---|
| Test#04 | 🩹 healed: button "Submit" → "Send" | confirm the rename is intended |
| Test#05 | 📸 visual baseline created | compared from the next run |
| Test#06 | 🧊 quarantined (flaky) | tracked in <flaky-test ref> |

(or "none")

---

## Accessibility Report

| Page | Critical | Serious | Moderate | Minor |
|---|---|---|---|---|
| /login | 0 | 1 | 2 | 0 |

**A11y bugs filed:** #N (sev-2), …   (or "none")

---

## Bugs Filed

| Issue | Title | Severity | Labels |
|---|---|---|---|
| #42 | [Login] Error message not shown on invalid password | Sev-3 | bug, sev-3, p2, e2e |

---

## Artifacts Location
- Test cases: `./qa-artifacts/test-cases/<feature>-<date>/`
- Run report: `./qa-artifacts/runs/<run-id>/results.json`
- Failure artifacts: `./qa-artifacts/runs/<run-id>/artifacts/`
- This report: `./qa-artifacts/sessions/session-<timestamp>.md`

---
🤖 _Generated by DevOps QA Agent — review before acting on this._

WAY 2 template

# API Session Report
**Date:** [ISO date]
**API base URL:** [URL]
**Spec source:** [URL | file | "manual"]

---

## Results
Endpoints tested: N · Test cases: N · ✅ Passed: N · ❌ Failed: N · ⚠️ Blocked: N

## Failed Test Cases
| Test | Endpoint | Expected | Actual | Capture |
|---|---|---|---|---|
| Test#03 | POST /v1/users | 400 | 500 | api-responses/POST-v1-users-….json |

## Schema Violations
| Endpoint | Field | Problem |
|---|---|---|
(or "none")

## Performance Flags (> API_PERF_THRESHOLD_MS)
| Endpoint | Time (ms) | Threshold |
|---|---|---|
(or "none")

## Bugs Filed
| Issue | Title | Severity | Labels |
|---|---|---|---|

---
🤖 _Generated by DevOps QA Agent — review before acting on this._

Rules

  • Always include the Accessibility section in WAY 1 reports, even when it shows 0 violations, and the Schema/Performance sections in WAY 2 reports, even when empty ("none")
  • Counts must add up: Passed + Failed + Blocked + Skipped = Total
  • Always list artifact paths
  • Always end with the watermark footer (CLAUDE.md's Output Watermark). It is part of both the saved file and the filed issue body

04 同仓库更多 Skills

GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

write-tests

WAY 4 — write test cases only, no execution. Use when the user says "write it", "write tests", "generate test cases" — an approved test plan (`Plan:`), or requirements (text or a tracker issue) planned and approved first, optional App/Spec/MR or PR → exactly the planned test files.

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

verify-fix

WAY 9 — verify that a bug is fixed by running its regression test. Use when the user says "verify it", "verify fix", "is #142 fixed", "check the fix" with one or more bug refs (#142, SHOP-142), or "verify all" for every open bug that has a regression test.

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

user-story-format

Reference only — the single definition of this project's user-story body (story, Gherkin ACs, Missing Information, DoD) and its AC/scenario rules. Read by user-story-enhancer (WAY 6) and benchmark-gap-story-writer (WAY 8) so stories they write stay identical in shape and WAY 6 can re-score WAY 8's output. Not a workflow on its own.

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

tracker

Provider-neutral contract for every issue-tracker and code-host action (create/update/comment/close issues, attach files, comment on MRs/PRs, read CI runs and logs) plus label conventions and failure handling. Every WAY calls these operations; the matching provider-* skill says how to perform them on GitLab, GitHub, Jira, Azure DevOps, or Bitbucket.

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

traceability

WAY 14 — requirements traceability matrix for a user story (each acceptance criterion) or a test folder written from plain text (each R-NN requirement) → the tests covering it → their latest result → open bugs. Use when the user says "trace it", "traceability", "is #148 covered", "coverage of SHOP-148", "trace it <folder>".

★ 5
GhassenAZZOUZ
GhassenAZZOUZ/claude-qa-agent

test-plan

WAY 19 — design a test plan before any test code. Use when the user says "plan it", "plan tests", "test plan", "design tests" with requirements (text or a tracker issue), optional App/Spec/MR or PR. Output is the test plan (scope, levels, one row per Test#<nn> with category, tags, covers, priority, coverage, entry/exit criteria, risks), reviewed by `review-plan` (WAY 20), filed for approval; `write it Plan:` / `e2e it Plan:` then write exactly that plan. Also holds the plan format every other WAY reads.

★ 5