grill-me
Manually interview the user about a plan, design, or idea until shared understanding is reached
Skill by OrestesK
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/orestesk-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 and code. Checked Nov 2, 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
- Manually interview the user about a plan, design, or idea until shared understanding is reached
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- to-prd.md · references/
- to-spec.md · references/
- to-tickets.md · references/
SKILL.md (first lines)
# Grill Me Identify the plan, decision, or idea to discuss from the active conversation. If it is unclear, ask one question to establish it. Then interview the user until shared understanding is reached: - Address one decision at a time, starting with decisions that later choices depend on - Ask exactly one question, then wait for the user’s answer - Research facts in the codebase, with tools, or in documentation between questions - Apart from one opening question to establish the subject, ask the user only to make decisions that evidence cannot settle - Do not create files, change the project, or start implementation during the interview - Do not impose an arbitrary question limit; continue only while unresolved decisions remain Once the important decisions are settled: 1. Summarize the shared understanding 2. Ask one final question offering: - No additional output - A product requirements document - A technical specification - Implementation tickets - Handoff to native `/plan` 3. Do not create an output unless the user selects one For a selected document, read exactly one private procedure: - Product requirements document: [references/to-prd.md](references/to-prd.md) - Technical specification: [references/to-spec.md](references/to-spec.md) - Implementation tickets: [references/to-tickets.md](references/to-tickets.md) Return the selected document in chat unless the user names a writable destination. For `/plan`, provide a concise handoff summary and tell the user to enter Plan Mode. Do not create a competing implementation plan.
From OrestesK/omp, MIT.
More from OrestesK/omp
- 0.570score
authenticated-web-access
OrestesK
Reuse an existing browser login for bounded authenticated website requests when the user asks to read site data, download a file, inspect a network-backed…
SkillAFreshness: AClaude Code +9 - 0.567score
excalidraw-skill
OrestesK
Use for planning, creating, refining, validating, or exporting Excalidraw technical diagrams, including text-only layout proposals before drawing
SkillAFreshness: AClaude Code +9 - 0.565score
pr-slack-post
OrestesK
Draft a short Slack message that posts a pull request for review.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-authoring
OrestesK
Write or revise reusable skill instructions.
SkillAFreshness: AClaude Code +9 - 0.565score
pi-config
OrestesK
Write and maintain clear, consistent Oh My Pi configuration.
SkillAFreshness: AClaude Code +9 - 0.561score
review
OrestesK
Use for independent review of nontrivial implementation proposals before approval and nontrivial implementations before final evidence; also use for explicit…
SkillAFreshness: AClaude Code +9 - 0.561score
session-analysis
OrestesK
Use to analyze past sessions, reconstruct what happened, identify errors and unresolved work, or extract user preferences and workflow friction that could…
SkillAFreshness: AClaude Code +9 - 0.558score
github-pull-requests
OrestesK
Use to prepare, review, update, or respond to feedback on GitHub pull requests
SkillAFreshness: AClaude Code +9 - 0.558score
github-pr-comments
OrestesK
Draft, refine, place, or post actionable GitHub pull-request review comments from validated findings
SkillAFreshness: AClaude Code +9 - 0.558score
github-issue-authoring
OrestesK
Use for triaging, drafting, or improving GitHub issues from verified evidence
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/OrestesK/omp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from OrestesK
- 0.570score
authenticated-web-access
OrestesK
Reuse an existing browser login for bounded authenticated website requests when the user asks to read site data, download a file, inspect a network-backed…
SkillAFreshness: AClaude Code +9 - 0.567score
excalidraw-skill
OrestesK
Use for planning, creating, refining, validating, or exporting Excalidraw technical diagrams, including text-only layout proposals before drawing
SkillAFreshness: AClaude Code +9 - 0.565score
pi-config
OrestesK
Write and maintain clear, consistent Oh My Pi configuration.
SkillAFreshness: AClaude Code +9 - 0.565score
pr-slack-post
OrestesK
Draft a short Slack message that posts a pull request for review.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-authoring
OrestesK
Write or revise reusable skill instructions.
SkillAFreshness: AClaude Code +9 - 0.563score
skill-authoring
OrestesK
Create, review, or make substantial changes to local Pi skills.
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/orestesk-grill-me (last updated 2026-10-24)