Borrowing it
Nothing to install: this file belongs to joshsmithxrm/power-platform-developer-suite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/joshsmithxrm/power-platform-developer-suite/main/.claude/skills/qa/SKILL.mdgit clone --depth 1 https://github.com/joshsmithxrm/power-platform-developer-suiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/qa)<a href="https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/qa"><img src="https://agentmods.dev/badge/skills/joshsmithxrm/power-platform-developer-suite/qa/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/qa"><img src="https://agentmods.dev/badge/skills/joshsmithxrm/power-platform-developer-suite/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 75 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Rogue Agent · line 421 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium MCP Rug Pull · line 396 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.04472 |
| Opus 5.5 | $0.00018 | $0.01789 |
| Sonnet 5.5 | $0.00009 | $0.00894 |
| Haiku 4.5 | $0.00004 | $0.00447 |
Grade A, and why
qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA — Three-Agent Blind Verification
Dispatches three specialized agents with no source code access to verify quality from different angles: functional correctness, cross-panel consistency, and UX heuristics. Each agent interacts with the running product exactly as a user would.
Why three agents: A single verifier optimizes for its checklist and misses everything else. A functional tester won't notice inconsistent styling. A consistency auditor won't test button behavior. A UX evaluator won't verify sort order. Three lenses catch three categories of defects.
Usage
/qa — auto-detect from recent commits
/qa extension — verify extension changes via CDP
/qa cli — verify CLI changes by running commands
/qa mcp — verify MCP changes via Inspector
/qa "SELECT TOP 5 should return 5 rows" — explicit behavior description
Process
Step 1: Scope the Work
If $ARGUMENTS is a quoted description: Use it directly as the behavior to verify.
If $ARGUMENTS is a mode (extension/cli/mcp) or empty: Auto-generate from branch work:
# Ensure local main ref is current (worktrees can be stale)
git fetch origin main --quiet
# All commits on this feature branch
git log main..HEAD --format="%s%n%b" --no-merges
# All files changed on this branch
git diff main...HEAD --name-only
From the commits, extract observable behaviors:
feat(query): add X→ "X should be visible/functional in the UI"fix(ext): guard against Y→ "Y scenario should not crash"feat(extension): add Z to panel→ "Z should render in the panel"
From the changed files, identify which panels were modified — these are the panels that need exploratory inventory in Phase 1.
Be specific. Not "query works" — instead: "Execute SELECT TOP 5 name FROM account, verify exactly 5 rows in the results table."
Step 2: Detect Mode
From $ARGUMENTS or changed files:
src/PPDS.Extension/→ extension mode (CDP)src/PPDS.Cli/Commands/(not Serve/) → CLI mode (run commands)src/PPDS.Mcp/→ MCP mode (Inspector)src/PPDS.Cli/Tui/→ TUI mode (tui-verify)- Mixed → run applicable modes sequentially
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 453 lines · 44 tokens per session scan A 12ce4d3761b3
qa is a skill published in the GitHub repository joshsmithxrm/power-platform-developer-suite (7 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 4,472 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
PowerAppsControl
Drive the PowerAppsControl MCP server to UX-test a Power App end to end: open and verify an app URL, let the user choose a mode (smoke test = in-depth read-only exploration that produces a repeatable natural-language test plan; or run my test plan), then run it in a recorded session and produce a video + HTML report…
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.