skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
hu3rror/my-skills68 installs

grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

How do I install this agent skill?

npx skills add https://github.com/hu3rror/my-skills --skill grilling
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill is a design-interrogation framework for stress-testing ideas. It is generally safe but possesses an indirect prompt injection surface because it is instructed to ingest and rely on facts from the local environment, such as architectural records and filesystem data, which may contain untrusted content.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

What does this agent skill do?

Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.

Work the tree in rounds. 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. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.

Format a round like so:

❓ Q1 - <question title>: <the question and the context it needs, one or two sentences>

<label> <alternative>; <what it costs or enables>

<label> <alternative>; <what it costs or enables>

➡️ <your recommended answer>


❓ Q2 - <question title>: <the question and the context it needs, one or two sentences>

➡️ <your recommended answer>

Word each question so "yes" accepts your recommended answer; on a choice question, the recommended label is that "yes"; a bare "yes" takes every recommendation of the round.

One tier per line: ❓ carries the items one answer settles together (a security model, a storage layer); an item the user could answer apart from its neighbours gets its own question. A choice question lists its alternatives one per line, and drops them when one answer settles them all.

Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.

Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent with a fresh context window to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.

A recommended answer is a claim, not an opinion: it must rest on a fact you have verified (via the filesystem, tools, docs, or a sub-agent) and name the source, so the fact carries an evidence chain a later round can re-check. When a recommendation depends on a fact you have not verified, label it (待验证) inline, name the missing fact and how you would check it — never present it as settled. A round is complete only when every recommendation has passed this check.

Before presenting a round, run the consistency check: hold every recommendation against (a) this effort's recorded decisions, (b) the precedents you cite, and (c) your own statements in this session, including the other recommendations of this round; flag any conflict inline. A recommendation that contradicts a recorded decision or your own earlier statement is a defect to resolve, not a fresh idea to float.

Decisions and precedents are records, not context: when a session starts clean (a wayfinder ticket session), fetch them — the map's Decisions-so-far, the closed tickets' resolutions, the ADRs — before the first round. An unread record is a (待验证) gap, never an empty set.

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/hu3rror/my-skills/grilling">View grilling on skillZs</a>