grill-me
Stress-test a plan, design, decision, or product idea through a relentless one-question-at-a-time interview, optionally grounding decisions in project domain…
Skill by deepaktiwari09
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/deepaktiwari09-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, testing
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
- Stress-test a plan, design, decision, or product idea through a relentless one-question-at-a-time interview, optionally grounding decisions in project domain documentation and recording glossary or ADR updates. Use when the user says grill me, challenge this plan, question my design, or wants shared understanding before implementation.
- License
- MIT
- Instructions
- 44 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- openai.yaml · agents/
- adr-format.md · references/
- context-format.md · references/
- docs-mode.md · references/
SKILL.md (first lines)
# Grill Me Walk the decision tree one branch at a time until the plan is implementable and both sides share the same context. ## Select the mode - Standard: challenge the plan using conversation and discoverable facts. - Documentation-aware: when `CONTEXT.md`, domain docs, or ADRs are relevant, read [references/docs-mode.md](references/docs-mode.md). ## Interview loop 1. Restate the current decision and why it matters. 2. Resolve facts from code or documentation before asking the user. 3. Ask exactly one decision-bearing question. 4. Give a recommended answer and concrete tradeoff. 5. Record the answer and update dependent branches. 6. Continue until no material branch remains unresolved. Do not ask several questions in one message. Do not re-ask resolved questions. Use realistic examples when terminology is ambiguous. ## Question priority Ask in this order when applicable: 1. Outcome and users 2. Scope and exclusions 3. Business rules and invariants 4. Data and lifecycle 5. Failure and recovery behavior 6. Security and permissions 7. Compatibility and migration 8. Verification and rollout ## Finish Summarize: - Decisions - Rejected alternatives and reasons - Remaining assumptions - Changed documentation - Implementation-ready next step
From deepaktiwari09/team-agent-skills, MIT.
More from deepaktiwari09/team-agent-skills
- 0.529score
mobile-development-rule
deepaktiwari09
Apply physical-device Android development, build, wireless ADB, hot-reload, and recovery rules.
SkillBFreshness: BClaude Code +9 - 0.529score
react-native-performance-practices
deepaktiwari09
Apply prioritized React Native and Expo practices for list performance, animations, navigation, native UI, state, rendering, compiler compatibility, and…
SkillBFreshness: BClaude Code +9 - 0.529score
react-performance-practices
deepaktiwari09
Apply prioritized React and Next.js performance practices for data fetching, bundle size, server rendering, client state, re-renders, and JavaScript execution.
SkillBFreshness: BClaude Code +9 - 0.529score
code-review
deepaktiwari09
Review changes since a fixed commit, branch, tag, or merge-base along two independent axes: repository standards and the originating issue, PRD, or spec.
SkillBFreshness: BClaude Code +9 - 0.529score
git-rules
deepaktiwari09
Manage complete Git and GitHub workflows including branches, worktrees, commits, changelogs, pull requests, conflict resolution, tags, and releases.
SkillBFreshness: BClaude Code +9 - 0.529score
business-rule-e2e
deepaktiwari09
Design, implement, run, diagnose, and refresh business-rule-driven end-to-end tests for web and React Native projects.
SkillBFreshness: BClaude Code +9 - 0.529score
project-documentation
deepaktiwari09
Create or update maintainable project documentation for business logic, implemented behavior, product flows, domain relationships, decisions, and edge cases.
SkillBFreshness: BClaude Code +9 - 0.529score
development-logging
deepaktiwari09
Design, add, review, or standardize secure structured development logging across frontend, backend, database, mobile, and integration layers.
SkillBFreshness: BClaude Code +9 - 0.529score
interface-critique
deepaktiwari09
Critique a web or mobile interface across design specificity, hierarchy, information architecture, usability, accessibility, emotional fit, states, content…
SkillBFreshness: BClaude Code +9 - 0.526score
tdd
deepaktiwari09
Build or fix backend, web, and mobile behavior through a test-first red-green-refactor loop.
SkillBFreshness: BClaude Code +9 - 0.524score
human-loop-testing
deepaktiwari09
Guide a human through real web or mobile feature testing one action at a time, capture PASS/FAIL/BLOCKED evidence, diagnose and fix confirmed defects, and…
SkillBFreshness: BClaude Code +9 - 0.524score
distinctive-frontend-design
deepaktiwari09
Create distinctive, production-grade frontend interfaces through intentional aesthetic direction, typography, layout, motion, and copy.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 10, 2026 (2 months ago)
- Last release
- Aug 10, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from deepaktiwari09
- 0.529score
business-rule-e2e
deepaktiwari09
Design, implement, run, diagnose, and refresh business-rule-driven end-to-end tests for web and React Native projects.
SkillBFreshness: BClaude Code +9 - 0.529score
interface-critique
deepaktiwari09
Critique a web or mobile interface across design specificity, hierarchy, information architecture, usability, accessibility, emotional fit, states, content…
SkillBFreshness: BClaude Code +9 - 0.529score
code-review
deepaktiwari09
Review changes since a fixed commit, branch, tag, or merge-base along two independent axes: repository standards and the originating issue, PRD, or spec.
SkillBFreshness: BClaude Code +9 - 0.529score
git-rules
deepaktiwari09
Manage complete Git and GitHub workflows including branches, worktrees, commits, changelogs, pull requests, conflict resolution, tags, and releases.
SkillBFreshness: BClaude Code +9 - 0.529score
development-logging
deepaktiwari09
Design, add, review, or standardize secure structured development logging across frontend, backend, database, mobile, and integration layers.
SkillBFreshness: BClaude Code +9 - 0.529score
mobile-development-rule
deepaktiwari09
Apply physical-device Android development, build, wireless ADB, hot-reload, and recovery rules.
SkillBFreshness: BClaude Code +9
Cite this page
grill-me skill. Agent Mart. https://agentmart.dev/skills/deepaktiwari09-grill-me (last updated 2026-10-24)