grill
Stage 1 - A relentless Socratic interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Skill by sapientcoffee
Chalk Labs
Need help deploying grill?
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/sapientcoffee-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: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
grill- Description
- Stage 1 - A relentless Socratic interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
- License
- Apache-2.0
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Skill: Grill (Stage 1)
## Objective
Your goal is to conduct an interactive Socratic alignment and requirements gathering session. You must analyze the requirements of the feature or change, identify ambiguities, challenge terms, and stress-test the design before any technical specification or PRD is drafted.
## 00_IDEATION.md Context Check & Plan Directory Reuse
1. **Search for Ideation Output & Existing Plan Directory**: First, check if an existing plan directory under `plans/<feature-slug>/` or an ideation draft file (`00_IDEATION.md`) exists.
- Look under `plans/<feature-slug>/<timestamp>/`. **REUSE that exact plan directory** for all subsequent stage outputs. Do NOT create a new timestamp folder when `ideator` or a prior stage was already run!
- Also check the fallback path `.plans/00_IDEATION.md`.
2. **Use Context if Exists**: If `00_IDEATION.md` exists in the plan directory, read it immediately. Use the identified friction points, target personas, customer user journeys (CUJs), ADK orchestration topologies, and mock JSON schema inside it to prime and guide the grilling session.
3. **Fallback**: If no existing plan directory or `00_IDEATION.md` file is found, proceed with the grilling session using the user's initial prompt and create a new timestamped plan directory `plans/<feature-slug>/<timestamp>/`.
## Instructions
1. Engage in Socratic requirements gathering by running an interactive alignment session with the user.
2. Formulate **3 to 5 targeted Socratic questions** using the `ask_question` tool (or direct interactive text prompt) to challenge assumptions and clarify ambiguities.
3. Align with the `/domain-modeling` skill guidelines:
- Challenge terms against the ubiquitous language.
- Challenge design assumptions and align requirements with Google Cloud Well-Architected Framework pillars (Reliability, Security, Cost Optimization, Operational Excellence, Performance Efficiency), deployment strategies, and SRE/observability best practices.
- Sharpen fuzzy or overloaded terms.
- Discuss concrete scenarios and probe edge cases one-by-one.
- Write or update the global glossary (`docs/glossary.md`) directly on-the-fly as terms are resolved (do NOT write a local `01_GLOSSARY.md` file).
- Record architectural decisions as ADRs inside `docs/adr/` if they meet the ADR criteria.
- **Unified Visual Dashboard (`visual-dashboard.html`) - Stage 1 (Glossary & ADR Tabs)**: Ensure the dashboard exists by executing `python3 scripts/manage_dashboard.py ensure --plan-dir "plans/{feature-slug}/{timestamp}" --moniker "{feature-slug}"` (or invoke the `visual-dashboard` skill). Directly sync terms and ADRs by executing `python3 scripts/manage_dashboard.py sync-glossary --plan-dir "plans/{feature-slug}/{timestamp}" --moniker "{feature-slug}" --stage "Stage 1"`.
- **Zero Intermediate Snippet Files**: Do NOT write any temporary HTML files. `sync-glossary` parses `docs/glossary.md` and `docs/adr/` directly and mirrors to system artifacts.
4. 🛑 **EXECUTION BARRIER**: Present your Socratic questions and **STOP execution immediately**. Do NOT draft `02_PRD.md` or move to subsequent stages until the user answers your questions.From sapientcoffee/bean-to-cup, Apache-2.0.
More from sapientcoffee/bean-to-cup
- 0.521score
assess
sapientcoffee
Exposes the app modernization assessment skill, performing agentic codebase scans, GCP credential verification, cost estimation checks, and executing the…
SkillBFreshness: BClaude Code +9 - 0.521score
rewrite
sapientcoffee
Stage 1/2 - Orchestrate a legacy application rewrite workflow by analyzing modernization assessments and coordinating specialized skills.
SkillBFreshness: BClaude Code +9 - 0.512score
kanban
sapientcoffee
Stage 7 - Generates an interactive Kanban board (Markdown & HTML) and Mermaid flow to visualize and track the status of implementation slices.
SkillBFreshness: BClaude Code +9 - 0.469score
chaos-mitigation
sapientcoffee
Phase 7 - Detects, analyzes, and mitigates active chaos events in the `press-service` using logs and runbooks.
SkillCFreshness: CClaude Code +9 - 0.469score
dev
sapientcoffee
Start the local development environment (backend and frontend)
SkillCFreshness: CClaude Code +9 - 0.467score
deploy-app
sapientcoffee
Phase 7 - Acts as DevOps to automatically detect the application stack, install necessary dependencies, and host the application locally.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 11
- Last commit (this folder)
- Aug 6, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/sapientcoffee/bean-to-cup
- 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 sapientcoffee
- 0.526score
harness-immunizer
sapientcoffee
Velocity Harness Patch self-healing mechanism.
SkillBFreshness: BClaude Code +9 - 0.526score
cycle-telemetry
sapientcoffee
Velocity Chess Clock telemetry tracker.
SkillBFreshness: BClaude Code +9 - 0.526score
code-hygiene
sapientcoffee
Deterministic local code hygiene runner.
SkillBFreshness: BClaude Code +9 - 0.524score
github-workflow
sapientcoffee
Phase 9 - Provides the process for raising git commits, checking branches, and creating PRs using the gh CLI.
SkillBFreshness: BClaude Code +9 - 0.521score
git-delivery
sapientcoffee
Provides an emoji-powered, good-practice delivery pipeline to verify code quality, craft conventional atomic commits, and compile premium "What, Why, How"…
SkillBFreshness: BClaude Code +9 - 0.521score
record
sapientcoffee
Record terminal interactions and compile them to animated GIFs.
SkillBFreshness: BClaude 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 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 skill. Agent Mart. https://agentmart.dev/skills/sapientcoffee-grill (last updated 2026-10-24)