What is the Agent QA Evidence skill?
Agent QA Evidence is a testing skill by darkrishabh for Claude Code, Cursor, Codex and other AI coding agents. Reviews supplied agent-qa run evidence and distinguishes application results from selection checks, setup failures, and incomplete records.
agent-qa combines natural-language web/mobile tests with advanced memidex memory and self-improvement. Review the supplied command observations and run records without executing tests or changing the application.
- Author
- darkrishabh
- Pack
- darkrishabh/agent-skills-eval (2 skills)
- Category
- Testing, #248 of 305
- Alyn Score
- 52 / 99
- Files
- 8
- License
- MIT
- Last updated
- 19 h ago
- Works with
- Claude Code, Claude, Cursor, Codex, Gemini CLI, Copilot
Agent QA Evidence compared to similar skills
| Skill | Alyn Score | GitHub stars | Updated |
|---|---|---|---|
| Agent QA Evidence · darkrishabh | 52 | 817 | 19 h ago |
| Evidence Driven Testing · michaelshimeles | 63 | 1.5k | 12 days ago |
| Agent QA Browser Regression · rrezartprebreza | 63 | 362 | 6 days ago |
| Temporal Python Testing · wshobson | 86 | 43k | 26 h ago |
Install Agent QA Evidence
Pick your agent. Every command is ready to paste.
npx alyn-cli add agent-qa-evidenceDetects your agents (Claude Code, Cursor, Codex and 70+ more) and installs to the right folder. Add -g to install globally.
npx skills add darkrishabh/agent-skills-eval --skill agent-qa-evidenceOr use the open skills CLI directly.
01
Install it
Run the command above, or upload the folder in Claude.
02
Ask naturally
Describe the task. Your agent loads agent-qa-evidence when the request matches its description.
03
Name it if needed
If it does not trigger, say “use the agent-qa-evidence skill”. In Codex, type $agent-qa-evidence.
Review agent-qa evidence
agent-qa combines natural-language web/mobile tests with advanced memidex memory and self-improvement. Review the supplied command observations and run records without executing tests or changing the application.
Decide what the evidence establishes
- Identify the requested test, target, revision, and expected observable outcome. Bind the evidence to that scope; do not inherit another run's result.
- Separate configuration/YAML validation, test discovery, application execution, and memory inspection. Successful validation and
--dry-runselection do not prove application acceptance or a JUnit artifact. - Inspect the selected run's completed verdict and relevant observations. An empty failed-run list can omit incomplete or healed runs. Missing verdicts and
evidence-incompleteknowledge remain unresolved. - Interpret exit status alongside the command and error:
0can mean passed or healed;1can mean a failed/timed-out test or a missing required file;2means the run could not start;130means cancellation. A setup error is not proof of an application defect. - For a healed run, preserve the distinction from a clean pass and explain the recorded correction. Verify that the original expected outcome still holds. Do not weaken assertions or erase memory to create a passing result.
- Treat memidex observations as diagnostic context, not an independent acceptance oracle. Missing knowledge evidence does not establish what was supplied or learned.
Use these report labels for this example; they are not additional agent-qa CLI verdicts:
PASSED: a completed passing run and its observed assertion establish the requested outcome for the stated scope.HEALED: a completed healed run retains the original assertion and has evidence of the correction and resulting outcome.FAILED: observed application behavior contradicts the expected outcome in a completed run.UNVERIFIED: selection-only output, unavailable execution, incomplete evidence, mismatched scope, or missing required observations prevent a supported outcome.
Return the label, evidence supporting it, and the specific remaining check if any. Retain the run ID and relevant command/error when supplied. Distinguish provided observations from inference; do not invent execution, screenshots, reports, or completion. Preserve sensitive-data redaction.
The command semantics above follow agent-qa 0.2.3. Consult the CLI reference and memory inspection guide when interpreting a different version. The evaluator supplies files as text; this skill does not fetch those links.
Tips for Agent QA Evidence
- • Start a fresh session after installing so your agent picks up the new skill.
- • It is part of a pack with 2 skills. Install only the ones you need with --skill to keep triggers precise.
- • If two skills overlap, mention the one you want by name.
Questions about Agent QA Evidence
What does the Agent QA Evidence skill do?
Reviews supplied agent-qa run evidence and distinguishes application results from selection checks, setup failures, and incomplete records.
How do I install Agent QA Evidence?
Run "npx alyn-cli add agent-qa-evidence" in your project. The Alyn CLI installs it for Claude Code, Cursor, Codex and 70+ other agents. In Claude on the web, upload the skill folder as a ZIP under Customize > Skills.
Does Agent QA Evidence work in Cursor and Codex?
Yes. Agent QA Evidence uses the open SKILL.md format, so it works in Claude Code, Claude, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot and other agents that support agent skills.
What is a good alternative to Agent QA Evidence?
Evidence Driven Testing by michaelshimeles is the highest-ranked similar skill from another creator, with an Alyn Score of 63 compared to 52 for Agent QA Evidence.
Is Agent QA Evidence free?
Agent QA Evidence is open source on GitHub under the MIT license. It is free to install; check the license before commercial use.
Who made Agent QA Evidence?
Agent QA Evidence is published by darkrishabh in the darkrishabh/agent-skills-eval repository, together with 1 other skills.


