grill
Calibrated interrogation of a fuzzy idea before it becomes a spec.
Skill by JuliusBrussee
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/juliusbrussee-grill
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/grill
What's inside
- Skill name
grill- Description
- Calibrated interrogation of a fuzzy idea before it becomes a spec. Asks one question at a time, recommends an answer, and lands each answer in §G (goal) or §C (constraints) — unknowns parked as `?` items, never guessed. The cheapest place to kill a bad idea is before §T exists. Triggers when the user has a vague idea, says "grill me", "stress-test this", "challenge my plan", "interview me before I spec", or invokes /ck:grill. Defers the actual write to the spec skill.
- License
- MIT
- Instructions
- 72 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# grill — sharpen idea before spec **One question at a time. Every answer lands in a § or gets parked `?`. Never guess a constraint into existence.** Plan-then-execute guesses the fuzzy parts & builds the wrong thing. Grill drags the fuzz into §G/§C *before* a single §T row exists. A bad assumption caught here costs one question. Caught in §B it costs a bug. ## WHEN TO GRILL - Idea is one sentence & you can feel the holes. - Multiple readings of the goal exist & you are about to pick one silently. - Before `/spec new` on anything non-trivial. - User asks to be challenged / stress-tested. Skip for a typo or a one-line fix. Grill scales to uncertainty, ⊥ to ego. ## CALIBRATE FIRST One opening read, not a quiz: 1. How well does user know this domain? (sets question depth) 2. How locked is the idea? (exploring vs committed) 3. Pressure wanted: light / normal / brutal. Match it. Brutal grilling on a half-formed idea just demoralizes. Light grilling on a committed plan misses the load-bearing flaw. ## QUESTION LADDER Climb in order. Each rung, ask **one** question, **recommend** an answer, wait. 1. **Goal** — what must the code *do*, in one line? (→ §G) 2. **Done** — how do we know it works? name the observable. (→ §C / future §V) 3. **Boundary** — what is explicitly out of scope? (→ §C) 4. **Lock** — what tech/lib/pattern is non-negotiable? what is forbidden? (→ §C) 5. **Surface** — what does the outside world touch — cmd, api, file, env? (→ §I) 6. **Edge** — the one input that breaks the happy path? (→ future §V) 7. **Unknown** — what do we *not* know yet? (→ park as `?` §C bullet) Stop climbing the moment the spec would be unambiguous. Do not ask all seven by reflex. ## ANSWER FORMAT Each question carries a recommended answer so the user can grunt "yes" & move: > Q: auth — session cookie or JWT? > rec: JWT — stateless, you named horizontal scaling as a §C. > (a) JWT (b) cookie (c) something else? ## HANDOFF When done, emit a compact block — goal line, constraint bullets, surfaced unknowns as `?` — and hand to the **spec** skill to write §G/§C. Grill proposes; spec is the sole mutator. Never write SPEC.md directly. ## WHEN TO STOP Done when ALL hold: - §G is one line, one reading, zero "or maybe". - §C covers every non-negotiable the user stated or implied. - Every blocking unknown is either answered or parked as an explicit `?`. Unresolved blocking unknown that needs the outside world → recommend `/research`, not a guess. ## BOUNDARIES - ⊥ make product decisions for the user. Recommend, never decide. - ⊥ write SPEC.md. Hand structured answers to spec. - ⊥ ask in bulk. One question, one recommendation, wait. - ⊥ grill a trivial change. Right-size or skip.
From JuliusBrussee/cavekit, MIT.
More from JuliusBrussee/cavekit
- 0.719score
spec
JuliusBrussee
Create, amend, or backprop bugs into SPEC.md at repo root.
SkillCFreshness: C★ 1.2KClaude Code +9 - 0.719score
review
JuliusBrussee
Adversarial senior review of the spec before any code is written.
SkillCFreshness: C★ 1.2KClaude Code +9 - 0.719score
deepen
JuliusBrussee
Optional design-improvement pass for when you have spare usage to drain.
SkillCFreshness: C★ 1.2KClaude Code +9 - 0.719score
build
JuliusBrussee
Plan-then-execute implementation against SPEC.md.
SkillCFreshness: C★ 1.2KClaude Code +9 - 0.719score
check
JuliusBrussee
Read-only drift detector.
SkillCFreshness: C★ 1.2KClaude Code +9 - 0.719score
research
JuliusBrussee
Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library…
SkillCFreshness: C★ 1.2KClaude Code +9 - 0.644score
backprop
JuliusBrussee
Bug → spec protocol.
SkillDFreshness: D★ 1.2KClaude Code +9 - 0.644score
caveman
JuliusBrussee
Caveman encoding for SPEC.md and spec-adjacent writes.
SkillDFreshness: D★ 1.2KClaude Code +9
Signals
- Stars
- 1,157
- Forks
- 89
- Open issues
- 12
- Last commit (this folder)
- Jun 18, 2026 (4 months ago)
- Last release
- Apr 18, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/JuliusBrussee/cavekit
- Website
- caveman.so/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from JuliusBrussee
- 0.888score
caveman-compress
JuliusBrussee
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-learn
JuliusBrussee
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-optimize
JuliusBrussee
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-evidence-review
JuliusBrussee
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.885score
caveman-manage
JuliusBrussee
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution.
SkillAFreshness: A★ 114.8KClaude Code +9 - 0.882score
caveman-review
JuliusBrussee
Compressed code review - one line per finding with location, problem and fix.
SkillAFreshness: A★ 114.8KClaude Code +9
Cite this page
grill skill. Agent Mart. https://agentmart.dev/skills/juliusbrussee-grill (last updated 2026-10-24)