Adoption

Agent Skills are supported by leading AI development tools.

VS Code Gemini CLI GitHub Goose Amp Cursor Claude Code Letta OpenCode Claude OpenAI Codex Factory VS Code Gemini CLI GitHub Goose Amp Cursor Claude Code Letta OpenCode Claude OpenAI Codex Factory

athal7/qa

Name: qa
Author: athal7

skills/qa/SKILL.md

npx skillsauth add athal7/dotfiles qa

Clean

TrivyContainer and dependency vulnerability scanner

Clean

SemgrepStatic code analysis for vulnerabilities

Clean

mcp-scan (Snyk)Model Context Protocol security validation

Skipped

Snyk (dep)Open source security scanning

Skipped

Socket.devSupply chain security analysis

Skipped

VirusTotalMulti-engine malware detection

Skipped

CrowdStrikeAdvanced threat intelligence

Skipped

OSV-ScannerOpen Source Vulnerability database check

Skipped

OWASP Dep-Check

Perform QA verification using Firefox DevTools browser automation.

Setup

Read issue context — check openspec/changes/ for an active change proposal, or .opencode/context-log.md if no OpenSpec change exists. Look for acceptance criteria and components to test.
Detect Port — Run source .envrc && echo $PORT, fall back to 3000
Verify Server — curl localhost:PORT before browser automation
If server not running — Report clearly and stop

Session Audit Trail

At the start of every run, create the session directory and initialize the report:

SESSION_DIR="$HOME/.local/share/qa/$(basename "$PWD")/qa-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$SESSION_DIR"
cat > "$SESSION_DIR/report.html" <<'HEADER'
<html><head><style>body{font-family:system-ui,sans-serif;max-width:1100px;margin:2em auto;padding:0 1em}.step{display:flex;gap:1.5em;margin:2em 0;align-items:start}.step img{width:55%;border:1px solid #ccc;border-radius:4px;flex-shrink:0}.step .info{padding-top:.25em}.step .info h3{margin:0 0 .5em}.step .info p{margin:0 0 .5em;color:#333}.step .info a{color:#0969da;word-break:break-all}</style></head><body>
HEADER

Reports persist per-project under ~/.local/share/qa/ so they can be referenced later (e.g. by the demo command).

After every browser action (navigate, click, fill, submit), scroll then screenshot:

Interacted with a specific element → evaluate_script with (el) => el.scrollIntoView({ block: 'center' }), passing the element's UID as an arg
General page-state shot → evaluate_script with () => window.scrollTo(0, 0)

Save the screenshot, then capture the page URL via evaluate_script with () => location.href, then append a report section:

screenshot_page saveTo="$SESSION_DIR/001-page-name.png"

cat >> "$SESSION_DIR/report.html" <<STEP
<div class="step">
  <img src="001-page-name.png">
  <div class="info">
    <h3>Short step title</h3>
    <p>One-line description of what was verified or happened.</p>
    <p><a href="THE_URL">THE_URL</a></p>
  </div>
</div>
STEP

Number files sequentially (001-, 002-, …). Use a short descriptive slug. Substitute the actual step title, description, filename, and captured URL into each section.

After all testing is done, close and open the report:

printf '</body></html>' >> "$SESSION_DIR/report.html" && open "$SESSION_DIR/report.html"

Verification

Use firefox-devtools MCP tools. Check project AGENTS.md for selectors/credentials.

Verify the main flow, then edge cases (empty states, errors, boundaries). Screenshot key states. Check tab navigation and focus for accessibility.

Resilience

Element not found → try alternative selectors, wait longer, scroll into view
Timeout → increase wait time, check if page is still loading
Try at least 3 approaches before giving up
When truly blocked: report what was verified, what failed, and why

Output

Pass/fail summary with issues found
Session directory path (e.g. ~/.local/share/qa/<project>/qa-20260515-143022/)
HTML report opened for inspection (all screenshots in sequence)
Steps to reproduce failures

athal7/qa

skills/qa/SKILL.md

QA verification with Firefox DevTools browser automation — load when a diff touches UI, views, or user-facing flows and needs functional verification before committing

6 stars

tools

Updated Jun 4, 2026

$ install --global

skillsauth

npx skillsauth add athal7/dotfiles qa

Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.

Security Scan Results

3 of 9 scanners reported clean

Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.

Scanners Passed

Scanners in report

Clean

TrivyContainer and dependency vulnerability scanner

95%

Clean

SemgrepStatic code analysis for vulnerabilities

95%

Clean

mcp-scan (Snyk)Model Context Protocol security validation

95%

Skipped

Snyk (dep)Open source security scanning

50%

Skipped

Socket.devSupply chain security analysis

50%

Skipped

VirusTotalMulti-engine malware detection

50%

Skipped

CrowdStrikeAdvanced threat intelligence

50%

Skipped

OSV-ScannerOpen Source Vulnerability database check

50%

Skipped

OWASP Dep-Check

50%

Last scanned: Jun 4, 2026, 2:53 AM93.6s1 file scanned

SKILL.md

name:: qa
description:: QA verification with Firefox DevTools browser automation — load when a diff touches UI, views, or user-facing flows and needs functional verification before committing
license:: MIT
compatibility:: opencode

Perform QA verification using Firefox DevTools browser automation.

Setup

Read issue context — check openspec/changes/ for an active change proposal, or .opencode/context-log.md if no OpenSpec change exists. Look for acceptance criteria and components to test.
Detect Port — Run source .envrc && echo $PORT, fall back to 3000
Verify Server — curl localhost:PORT before browser automation
If server not running — Report clearly and stop

Session Audit Trail

At the start of every run, create the session directory and initialize the report:

SESSION_DIR="$HOME/.local/share/qa/$(basename "$PWD")/qa-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$SESSION_DIR"
cat > "$SESSION_DIR/report.html" <<'HEADER'
<html><head><style>body{font-family:system-ui,sans-serif;max-width:1100px;margin:2em auto;padding:0 1em}.step{display:flex;gap:1.5em;margin:2em 0;align-items:start}.step img{width:55%;border:1px solid #ccc;border-radius:4px;flex-shrink:0}.step .info{padding-top:.25em}.step .info h3{margin:0 0 .5em}.step .info p{margin:0 0 .5em;color:#333}.step .info a{color:#0969da;word-break:break-all}</style></head><body>
HEADER

Reports persist per-project under ~/.local/share/qa/ so they can be referenced later (e.g. by the demo command).

After every browser action (navigate, click, fill, submit), scroll then screenshot:

Interacted with a specific element → evaluate_script with (el) => el.scrollIntoView({ block: 'center' }), passing the element's UID as an arg
General page-state shot → evaluate_script with () => window.scrollTo(0, 0)

Save the screenshot, then capture the page URL via evaluate_script with () => location.href, then append a report section:

screenshot_page saveTo="$SESSION_DIR/001-page-name.png"

cat >> "$SESSION_DIR/report.html" <<STEP
<div class="step">
  <img src="001-page-name.png">
  <div class="info">
    <h3>Short step title</h3>
    <p>One-line description of what was verified or happened.</p>
    <p><a href="THE_URL">THE_URL</a></p>
  </div>
</div>
STEP

Number files sequentially (001-, 002-, …). Use a short descriptive slug. Substitute the actual step title, description, filename, and captured URL into each section.

After all testing is done, close and open the report:

printf '</body></html>' >> "$SESSION_DIR/report.html" && open "$SESSION_DIR/report.html"

Verification

Use firefox-devtools MCP tools. Check project AGENTS.md for selectors/credentials.

Verify the main flow, then edge cases (empty states, errors, boundaries). Screenshot key states. Check tab navigation and focus for accessibility.

Resilience

Element not found → try alternative selectors, wait longer, scroll into view
Timeout → increase wait time, check if page is still loading
Try at least 3 approaches before giving up
When truly blocked: report what was verified, what failed, and why

Output

Pass/fail summary with issues found
Session directory path (e.g. ~/.local/share/qa/<project>/qa-20260515-143022/)
HTML report opened for inspection (all screenshots in sequence)
Steps to reproduce failures

Related Skills

athal7/zoom

development

VerifiedTrustedCommunity

Zoom meeting captions — file locations and format

6SKILL.mdUpdated May 24, 2026

athal7/dictation

tools

VerifiedTrustedCommunity

macOS dictation custom vocabulary — sync knowledge base names and terms to the system spelling dictionary

6SKILL.mdUpdated May 24, 2026

athal7/knowledge-base

testing

VerifiedTrustedCommunity

Look up people, projects, products, and decisions locally first: contact info (email, Slack ID, GitHub handle), titles and teams, project/product status, who works on what, and past decisions. Check before searching Slack, email, calendar, or GitHub — this is the first stop for any contact detail, project context, or decision-history question.

6SKILL.mdUpdated May 21, 2026

athal7/knowledge-base

athal7/communication

testing

VerifiedTrustedCommunity

Communication style, audience awareness, and AI-authorship markers for human-facing prose — load when composing chat messages, review comments, merge request descriptions, emails, doc bodies, or ticket descriptions

6SKILL.mdUpdated May 21, 2026

Download

For Claude Desktop. Download once, then upload the file in the app — no terminal needed.

Need help? View full Cowork setup guide →

Install manually

Choose your platform

# Clone the repo
git clone https://github.com/athal7/dotfiles.git

# Copy into Claude Code skills folder (global)
cp -r dotfiles/skills/qa ~/.claude/skills/

Claude Code Skills — official skills path docs.

Repository

athal7/dotfiles

6 stars

Compatible with

Claude Code

OpenAI Codex CLI

ChatGPT