mcpField
G
grill-me

grill-me

github.com/alirezarezvaniAgent workflows29.0k1.2k installsUpdated today
Repository

About grill-me

grill-me is an agent skill for clarifying plans through a decision tree, asking focused questions one at a time and recommending an answer for each. It combines codebase exploration, question generation, and session tracking for design discussions that need documented decisions.

Key features

  1. 01Ask questions depth-first through a decision tree
  2. 02Recommend an answer with each question
  3. 03Explore the codebase before asking
  4. 04Generate questions and track sessions

Use cases

  1. 01Identify unresolved points in a software plan
  2. 02Discuss design decisions in dependency order
  3. 03Record discussion and summarize settled decisions

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/alirezarezvani/claude-skills --skill grill-me

After installing, type/grill-mein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
companion_tooling.md
forcing_question_patterns.md
when_to_stop_grilling.md
scripts/
decision_tree_extractor.py
grill_session_tracker.py
question_generator.py

Details

From the project README

Grill Me

Derived from Matt Pocock's grill-me (MIT). Matt's interview discipline preserved verbatim. Additions: extraction + question + session tools + references + cs-* wrapper (see references/companion_tooling.md).

Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.

Ask the questions one at a time.

If a question can be answered by exploring the codebase, explore the codebase instead.

Rules (preserved + amplified)

  1. One question per turn. Never bundle.
  2. Provide a recommended answer with each question. Defaulting to "what do you think?" is lazy.
  3. Explore the codebase before asking. If grep / Read resolves it, do that first. Saves a turn.
  4. Walk the tree depth-first. Finish a branch before opening another.
  5. Track dependencies. If decision B depends on decision A, ask A first.

Workflow

  1. User provides a plan or design (or path to one).
  2. Run scripts/decision_tree_extractor.py to extract branches.
  3. Run scripts/question_generator.py to produce the question list with recommendations.
  4. Start a session: scripts/grill_session_tracker.py --action start.
  5. Walk the tree, one question at a time, recording answers in the session.
  6. When all branches resolved: report "shared understanding reached" + the locked-in decisions.

Output Pattern

Per question turn:

Q[i]/[total]: [question]
Recommended answer: [your call + 1-sentence rationale]

(Or: I explored the codebase and found [evidence]. Confirm?)

Tooling

See references/companion_tooling.md. Tools: extractor + generator + tracker. Agent: cs-grill-master. Command: /cs-grill-me.

Version: 1.0.0 Derived: Matt Pocock (MIT) + this repo's wrapper

Comments

Markdown supported