All skills

Use this Skill: https://skilld.dev/gh/garrytan/gstack/qa

This session only. Nothing lands on disk.

templatesfunctional-report-template.md

≈764 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Functional QA Report: {TARGET}

Field Value
Date / branch / revision {DATE / BRANCH / COMMIT AND WORKING-TREE INPUTS}
Caller / authority / depth {qa-only, qa, review or ship; permitted writes; bound}
Surfaces / scope {API, CLI, job, worker, webhook; changed and adjacent contracts}
Runtime / native tools {VERSIONS AND REPOSITORY-SUPPORTED COMMANDS}
Fixture ownership / destinations {ISOLATED ROOT, STORES, DOWNSTREAM TARGETS}
Duration / stop reason {MEASURED DURATION, COMPLETE OR BOUND/BLOCKER}

Contract outcomes

Contract and source Exact probe / evidence Expected → observed Outcome
{CONTRACT, DOC/TEST/USER SOURCE} {COMMAND OR REQUEST, EVIDENCE PATH} {OUTPUT AND DURABLE EFFECT} pass / fail / blocked / not run / inconclusive / not applicable (reason)

No visual score applies to this functional section. In a mixed report, keep the browser section's score and evidence separate, and link both surfaces' replay evidence and regression baselines. Do not combine their scores or outcomes.

Findings

ISSUE-NNN: {Reproduced defect or setup blocker}

  • Classification / severity: {PRODUCT DEFECT / SETUP / INCONCLUSIVE; IMPACT}.
  • Intended contract and source: {EXPECTED BEHAVIOR, NOT MERELY CURRENT IMPLEMENTATION}.
  • Reproduction: {WORKING DIRECTORY; SAFE SETUP/RESET; ENVIRONMENT NAMES ONLY; EXACT COMMAND OR METHOD/PATH/HEADERS/BODY USING SYNTHETIC VALUES}.
  • Observed: {EXIT/STATUS; STDOUT; STDERR; INITIAL/FINAL DURABLE STATE; REPLAY/RETRY ORDER}.
  • Evidence: {EXACT SAFE OUTPUT AND STATE PATHS; REVISION/RUNTIME; REDACTION AND REPRODUCIBILITY LIMITS}.
  • Diagnosis / next action: {CAUSAL EVIDENCE OR SPECIFIC PREREQUISITE; NO SPECULATIVE FIX}.

Discoveries and permanent tests

Link each exploration-NNN.json checkpoint, saved before its next probe, in this report. Each checkpoint receipt prints its link; .qa-evidence/NNN capture folders are not checkpoints. Use one Markdown entry per checkpoint, for example:

Use the actual filename and a path relative to this report (or its owned absolute path); plain or backticked filenames are not links. Include superseded checkpoints as history, not current passing evidence. Keep these original notes with the report.

Hypothesis / discovery Native test or proposed case Red evidence before repair Green + original + adjacent evidence Parent disposition
{OBSERVATION THAT CHANGED THE NEXT PROBE} {UNIT / INTEGRATION / E2E; PATH OR REPORT-ONLY PROPOSAL} {EXACT DEFECT FAILURE OR HEALTHY CONTRACT} {ACTUAL RESULTS OR NOT RUN} {AUTHORIZED CHANGE / SUGGESTION / DEFERRED}

Coverage limits and cleanup

List unexecuted charters, unavailable prerequisites, denied effects, ambiguous contracts, incomplete observations and remaining risk. Do not count them as passes. Name owned processes/state cleaned and anything left behind. State whether later changes invalidated evidence. Report-only must identify proposals separately from tests actually created.

Source: SKILL.md on GitHub

1 alert3d4 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    The skill is a QA automation tool for web application testing and bug fixing. It manages security risks by directing the agent to treat all external web content as data only, utilizes vendor-specific binaries for operational tasks, and employs standard shell tools for project management.

  • Socket3d

    No alerts

  • Snyk3d

    Risk: MEDIUM · 1 issue

  • Runlayer6mo

    1/3 files flagged

Signed by skilld at 96764e8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 15 hours ago.

Activeupdated 2 days ago
What it can do
Runs commands Reads files Edits files Network
preamble-tier
4
version
2.0.0
triggers
[
  "qa test this",
  "find bugs on site",
  "test the site"
]
All 8 allowed tools
BashReadWriteEditGlobGrepAskUserQuestionWebSearch

README badge

README badge for garrytan/gstack/qa

Runs systematic QA testing on a web application, detects bugs, and iteratively fixes them in source code with atomic commits. Offers three testing tiers (quick, standard, exhaustive) and produces before/after health scores and a ship-readiness summary.

Generated from the current SKILL.md.

What QA severity levels does this skill test?
Three tiers: Quick tests critical/high-severity bugs only, Standard adds medium-severity issues, and Exhaustive includes cosmetic problems. Use /qa-only for report-only mode without fixes.
Does this skill fix bugs automatically or just report them?
It iteratively tests, finds bugs, fixes them in source code with atomic commits, and re-verifies each fix. It produces a before/after health score and ship-readiness summary.
When should I invoke this skill?
Use it when asked to test, find bugs, or fix issues on a running web application. The skill can be invoked directly or suggested proactively when a user indicates a feature is ready for testing or asks 'does this work?'
What tools does this skill use to perform QA?
It uses Bash, Read, Write, Edit, Glob, and Grep for testing and fixing code, plus AskUserQuestion for decisions and WebSearch if needed.

Generated from the current SKILL.md. These answers refresh after source changes.