Install
$ agentstack add skill-upsolve-labs-upstack-qa-review ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Update Check (run first)
_UPD=$(~/.claude/skills/upstack/bin/upstack-update-check 2>/dev/null || .claude/skills/upstack/bin/upstack-update-check 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
If output shows UPGRADE_AVAILABLE : read ~/.claude/skills/upstack/skills/upgrade/SKILL.md and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If JUST_UPGRADED : tell user "Running upstack v{to} (just updated!)" and continue.
QA Review
You are performing independent exploratory QA. This is not tied to a specific branch or feature — you are testing the app as a user would.
Step 1: Find Documentation
Read existing end-user documentation (README, docs/, wiki, etc). If you cannot find it: AskUserQuestion for the documentation location.
Step 2: Stand Up the App
Start a local instance of the app, or connect to one the user provides. If you need auth or environment setup: AskUserQuestion.
Step 3: Discover Flows
Identify all documented workflows and user-facing flows. If you found too many flows or want to confirm scope: AskUserQuestion with the list of flows you found. Let the user select which to test.
Step 4: Test Each Flow
For each selected flow, use agent-browser:
Happy path:
agent-browser open— navigate to starting pointagent-browser snapshot -i— read the page structure- Walk through the flow step by step, clicking @refs, filling forms
agent-browser screenshot evidence/qa/-step-N.pngat key states
Edge cases:
- Empty inputs, boundary values
- Rapid repeated actions, back button, refresh mid-flow
- Missing permissions, expired sessions
- Unexpected data shapes
Note every issue found with:
- What happened vs what was expected
- Screenshot of the broken state
- Steps to reproduce
Step 5: Report
Summarize findings in an MD report with annotated screenshots.
Step 6: Log Issues
List all findings to the user. AskUserQuestion: "Which of these should I log as TODOs?" Present each finding as a numbered option. Only create TODOS.md entries (and Linear tickets if MCP available) for the ones the user approves.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Upsolve-Labs
- Source: Upsolve-Labs/upstack
- License: MIT
- Homepage: https://upsolve.ai/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.