Run any Skill in Manus with one click

grill-me

Stars3

Forks2

UpdatedJune 12, 2026 at 15:24

Interrogate the user about a plan or design one question at a time, walking the decision tree branch by branch and recommending an answer for each, until every decision is resolved and understanding is shared. User-invoked only via explicit phrases like 'grill me', 'interrogate this plan', 'stress-test this design', or '/grill-me'. Never auto-fires. Distinct from plan mode (explores and proposes) and a premortem (runs after a rough decision); grill-me runs before a plan solidifies, to extract and resolve the open decisions.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

BioInfo

BioInfo/claudelicious

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Project Management SpecialistsBusiness and Financial Operations Occupations·SOC 13-1082

SKILL.md

readonly

name	grill-me
description	Interrogate the user about a plan or design one question at a time, walking the decision tree branch by branch and recommending an answer for each, until every decision is resolved and understanding is shared. User-invoked only via explicit phrases like 'grill me', 'interrogate this plan', 'stress-test this design', or '/grill-me'. Never auto-fires. Distinct from plan mode (explores and proposes) and a premortem (runs after a rough decision); grill-me runs before a plan solidifies, to extract and resolve the open decisions.
disable-model-invocation	true
model	opus

grill-me

Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved and understanding is shared.

Runs BEFORE a plan solidifies: extract the open decisions, resolve them. This is not plan mode (which explores and proposes without forcing per-decision resolution) and not a premortem (which runs after a rough decision: "imagine it failed, why"). Grill first, then plan or implement.

Trigger

User-explicit only: "grill me", "interrogate this plan", "stress-test this design", "/grill-me". Never auto-invoke. The disable-model-invocation: true in the frontmatter is what enforces "never auto-fires": the skill is invocable by the user but the model cannot reach for it on its own.

Mechanics

Ask one question at a time. Wait for the answer before the next.
For every question, give your recommended answer with a one-line reason.
If a question is answerable from the codebase, go read the codebase instead of asking.
Walk the decision tree branch by branch. Resolve dependencies between decisions in order, so a settled decision constrains the ones downstream of it.

Stop condition

Stop when every branch is resolved and you and the user share the same picture of the plan.

Closing artifact

When done, emit a short Resolved decisions summary:

One bullet per settled decision (the answer, not the deliberation)
A short Open / deferred list for anything punted

Keep it a bullet list, not a template. It should drop straight into a plan or implementation.

Why this is a good example

It is tiny, it is dispatch-disabled so it never fires by accident, and it does one thing the model is bad at on its own: forcing a decision tree to resolve before code is written, one question at a time, instead of dumping a wall of questions or quietly assuming defaults. The whole skill is the discipline.

Credit

Adapted from Matt Pocock's grill-me skill (github.com/mattpocock/skills). The interrogation pattern is his; this version adds a stop condition and the Resolved-decisions artifact.

More from this repository

same repository

learn

BioInfo/claudelicious

Takes any external artifact you link (a repo, a paper, a tool, a blog post, a thread) and decides what to lift from it into your own stack. Resolves the artifact, maps it against what you already have (your notes, skills, rules, memory), extracts only the genuine deltas, red-teams each delta against your real setup, and returns a per-delta decision: borrow, build, install, or skip. ALWAYS invoke when the user shares a link and asks "should we adopt this", "what do we take from this", "what do we lift from X", or "is this worth stealing". NOT a review of the artifact on its own merits (that is a different, grade-it-in-isolation skill); this one grades the artifact against YOUR systems and outputs a lift plan.

2026-07-203

commit

BioInfo/claudelicious

Create a well-formatted git commit using conventional-commit format. ALWAYS invoke when the user says "commit", "commit this", "make a commit", or asks to save work to git. NOT for pushing (that has its own gitleaks gate) and NOT for staging review.

2026-06-123

council

BioInfo/claudelicious

Convenes a council of orthogonal thinker-lenses (Munger, Taleb, Thiel, plus idea-lenses base-rates and second-order-effects, plus a functional skeptic seat) to pressure-test a decision from multiple perspectives, force disagreement, then synthesize. Stateless three-phase engine: blind parallel reads, a dissent round against the consensus, then a synthesis (where they agree, sharpest live dissent, the lens you ignored, decision-shaped close). Invoke when the user says 'convene the council', 'council this', 'pressure-test this decision', or wants multiple mental-model perspectives on a decision before committing. Seats fan out in parallel; the main session synthesizes.

2026-06-123

designing-frontend-uis

BioInfo/claudelicious

Build or improve any frontend UI (component, page, app, dashboard, landing, marketing site) so it does not look like generic AI output. Enforces a brief-read, three dials, and a countable pre-flight gate instead of vague 'be distinctive' advice. Invoke when the user asks to build/create/redesign/improve a web UI, a React/Vue/Svelte component, a page, a dashboard, or an app, or says it 'looks generic / boring / AI-slop / templated'. Pulls a NAMED design style only when the user names one; otherwise reads the brief and picks a fitting direction. Does NOT auto-clone any template and does NOT default to any one font.

2026-06-123

dream

BioInfo/claudelicious

Consolidates memory across all layers (the durable memory files, the learnings log, project continuity) by pruning stale entries, merging duplicates, and resolving contradictions. Invoke when the user says 'dream', 'consolidate memory', 'clean up memory', 'merge duplicates', or after a heavy session that produced many similar entries. Different from per-correction capture (memory and the learning loop write new entries; dream cleans the corpus). Run periodically when memory feels noisy or after a multi-day push.

2026-06-123

post-update

BioInfo/claudelicious

Dispatch an already-approved status update to a channel (chat, social, a webhook) via a CLI. ALWAYS invoke when the user says "post the update", "send the update", "broadcast this", after they have approved the text. This is a DISPATCH point, not an author — it never writes the content itself.

2026-06-123

name	grill-me
description	Interrogate the user about a plan or design one question at a time, walking the decision tree branch by branch and recommending an answer for each, until every decision is resolved and understanding is shared. User-invoked only via explicit phrases like 'grill me', 'interrogate this plan', 'stress-test this design', or '/grill-me'. Never auto-fires. Distinct from plan mode (explores and proposes) and a premortem (runs after a rough decision); grill-me runs before a plan solidifies, to extract and resolve the open decisions.
disable-model-invocation	true
model	opus

grill-me

Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved and understanding is shared.

Trigger

Mechanics

Ask one question at a time. Wait for the answer before the next.
For every question, give your recommended answer with a one-line reason.
If a question is answerable from the codebase, go read the codebase instead of asking.
Walk the decision tree branch by branch. Resolve dependencies between decisions in order, so a settled decision constrains the ones downstream of it.

Stop condition

Stop when every branch is resolved and you and the user share the same picture of the plan.

Closing artifact

When done, emit a short Resolved decisions summary:

One bullet per settled decision (the answer, not the deliberation)
A short Open / deferred list for anything punted

Keep it a bullet list, not a template. It should drop straight into a plan or implementation.

Why this is a good example

Credit

Adapted from Matt Pocock's grill-me skill (github.com/mattpocock/skills). The interrogation pattern is his; this version adds a stop condition and the Resolved-decisions artifact.