Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add 2ykwang/agent-skills --skill create-qa-listgit clone --depth 1 https://github.com/2ykwang/agent-skillsWrote 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/2ykwang/agent-skills/create-qa-list)<a href="https://agentmods.dev/skills/2ykwang/agent-skills/create-qa-list"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/create-qa-list/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/2ykwang/agent-skills/create-qa-list"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/create-qa-list.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00126 | $0.01745 |
| Opus 5 | $0.00063 | $0.00873 |
| Sonnet 5 | $0.00025 | $0.00349 |
| Haiku 4.5 | $0.00013 | $0.00175 |
Grade A, and why
create-qa-list 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 9d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-qa-list
Build a QA test-case list a non-developer QA tester can read and run without opening the code — as CSV, HTML, or both.
The two rules that govern everything
Every decision in this skill follows the two rules below. They pull in different directions (one is presentation, one is accuracy) and both must hold for every row.
Rule 1 — The reader is a non-developer. They run the product and watch what happens. They don't read code. So every case is written in behavior-and-scenario language — what the user does and what they see. Function names, file paths, table/column names, and code symbols never appear in the output. This rule drives the tone, the columns, and the verification steps.
Rule 2 — Every case must match the code. Don't make things up. A QA list that diverges from real behavior is worse than none: the tester tests behavior that doesn't exist, files bugs that aren't real, or marks a real bug as "pass". So every scenario and expected result must rest on something you actually verified (code, spec, this conversation). If you can't verify a behavior, do one of three things: read the code to confirm, ask the user, or drop the case. Don't write a guessed expected result as if it were fact. Flag any case resting on an unverified assumption as needs-confirmation instead of exporting it silently.
Together they are the skill's mission: translate verified code behavior into language a non-developer can act on — translate, but don't invent, and don't leak the code.
Input can be anything
The user might give you: specs and planning docs, a URL, a PR/diff, pasted requirements, a one-line request, or just "make a QA list for what we built." The current conversation is itself valid input — if you've been building or discussing a feature, that context is the input.
The first job is to figure out which feature/behavior is the target. Infer from everything available first, then confirm — don't assume.
Workflow — 4 steps, then Build
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 87 lines · 126 tokens per session scan A e0ab0a5ecff9
create-qa-list is a skill published in the GitHub repository 2ykwang/agent-skills (19 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 1,745 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
phpunit-integration-test-reviewing
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
phpunit-migration-test-reviewing
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
phpunit-test-adversarial-reviewing
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
phpunit-test-team-reviewing
Use this skill when the user asks for a team-based, consensus, multi-reviewer, or red-team review of Shopware PHPUnit tests — trigger phrases like "team review these tests", "consensus review the tests in PR.
phpunit-unit-test-reviewing
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
phpunit-integration-test-generation
Use this skill when the user asks to generate, write, or create integration tests for a Shopware 6 source class whose contract requires wired-up code — phrases like "generate integration tests for X", "write an integration test for this controller", "test this indexer", "create an integration test for the message…