Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aivrar/grill-me
Adversarial plan interview before implementation.
4 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 4 comparable cases; this report requires 8.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Please review the following code changes in our existing authentication controller diff: ```ts export async function login(req: Request, res: Response) { const user = await db.user.findFirst({ where: { email: req.body.email } }); if (user && user.password === req.body.password) { return res.json({ token: jwt.sign({ id: user.id }, 'secret') }); } return res.status(401).send('Unauthorized'); } ``` Identify security vulnerabilities and bugs in this code.
| Checked | Without skill | With skill |
|---|---|---|
| The response identifies the plaintext password comparison vulnerability directly in the provided code. | Missed | Passed |
| The response refrains from starting an adversarial design interview process. | Missed | Passed |
The instructions your model reads when the skill loads.
Stress-tests a plan through structured adversarial questioning before any code is written. Models the plan as a design tree — every decision branches into the decisions that hang off it — and interviews the user in rounds until every branch is resolved and nothing is silently assumed.
Combines the phase discipline of the original with the frontier-rounds
mechanic from mattpocock/skills' grilling.
subagent-driven-development decompositionDo NOT use for existing code (use requesting-code-review) or simple one-off
tasks.
None. The skill works on any plan or raw idea.
Map the plan as a design tree. The frontier is every decision whose prerequisites are already settled — the questions you can ask NOW without guessing at answers you haven't heard yet.
Work in rounds: ask the whole current frontier in one message, numbered, each question carrying your recommended answer. Then wait. A question whose answer depends on another question still open in this round belongs to a LATER round, not this one.
Format each round like so:
❓ Q1 — <question title>: <question body, options if relevant>
➡️ Recommendation: <your recommended answer + one-line why>
test cases passed with the skill
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.