grill-me
Use only when explicitly invoked to deeply interview the user about a plan, product idea, or design until every material decision branch is resolved.
Skill by JobsHwang
Chalk Labs
Need help deploying grill-me?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/jobshwang-grill-me
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: design
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-me
What's inside
- Skill name
grill-me- Description
- Use only when explicitly invoked to deeply interview the user about a plan, product idea, or design until every material decision branch is resolved.
- License
- MIT
- Instructions
- 14 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Grill Me Reach shared understanding before any artifact or implementation is produced. 1. Inspect the workspace and current conversation first. Do not ask the user for facts that can be discovered safely. 2. Privately form a decision tree. Ask exactly one unresolved, high-leverage decision per turn. 3. Put the recommended answer first, then the meaningful alternatives, tradeoffs, and what the decision changes. 4. When a safe assumption is enough, adopt it and say so. If the user accepts defaults, keep moving rather than reopening settled branches. 5. Challenge contradictions, hidden scope, boundary cases, and unstated success criteria. Avoid low-value preference questions. 6. Stop when the remaining uncertainty would not materially change the result. Do not write files, code, PRDs, or specs. Finish with a concise agreement summary covering the goal, decisions, assumptions, risks, and unresolved items. Suggest the next useful explicit action, such as `to-prd`, but never invoke another workflow automatically.
From JobsHwang/skills, MIT.
More from JobsHwang/skills
- 0.563score
obsidian-doc-organizer
JobsHwang
Organize an Obsidian vault inbox or a user-selected set of notes by inspecting the vault's existing conventions, proposing safe destinations, normalizing…
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
to-spec
JobsHwang
Use only when explicitly invoked to turn agreed requirements or a PRD into an actionable technical delivery contract grounded in the current repository.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
handoff
JobsHwang
Compact the current work into a concise handoff for another agent or session.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
to-prd
JobsHwang
Use only when explicitly invoked to synthesize the current conversation or supplied notes into a concise product requirements document without inventing…
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
arch-scan
JobsHwang
Use only when explicitly invoked to survey a repository for architectural deepening opportunities and report ranked, evidenced candidates without changing code.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
slice-spec
JobsHwang
Use only when explicitly invoked to split a large delivery spec into independently verifiable vertical slices with explicit dependency edges.
SkillBFreshness: B★ 2Claude Code +9 - 0.549score
clarify
JobsHwang
Use only when explicitly invoked to resolve the minimum set of requirement questions that materially affect safe delivery.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 3, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/JobsHwang/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from JobsHwang
- 0.563score
obsidian-doc-organizer
JobsHwang
Organize an Obsidian vault inbox or a user-selected set of notes by inspecting the vault's existing conventions, proposing safe destinations, normalizing…
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
to-spec
JobsHwang
Use only when explicitly invoked to turn agreed requirements or a PRD into an actionable technical delivery contract grounded in the current repository.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
handoff
JobsHwang
Compact the current work into a concise handoff for another agent or session.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
to-prd
JobsHwang
Use only when explicitly invoked to synthesize the current conversation or supplied notes into a concise product requirements document without inventing…
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
arch-scan
JobsHwang
Use only when explicitly invoked to survey a repository for architectural deepening opportunities and report ranked, evidenced candidates without changing code.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
slice-spec
JobsHwang
Use only when explicitly invoked to split a large delivery spec into independently verifiable vertical slices with explicit dependency edges.
SkillBFreshness: B★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get grill-me running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
grill-me skill. Agent Mart. https://agentmart.dev/skills/jobshwang-grill-me (last updated 2026-10-24)