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/mineugene-grilling
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: documents, 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/grilling
What's inside
- Skill name
grilling- Description
- Stress-test a plan, decision, or idea with an interview. Invoke only when the user asks to stress-test their thinking or explicitly asks to grill a plan, decision, or idea. Do not invoke merely because the user mentions grilling, names a skill, or writes 'skill <word>'.
- License
- MIT
- Instructions
- 47 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Grilling ## Decision order Track the decisions the subject needs and which decisions depend on others. A decision is ready to ask when all its prerequisites are settled. ## Procedure Work in rounds: 1. Ask about every ready decision in one round. 2. Number each question `Q1`, `Q2`, and so on. Give one recommended answer per question, and word the question so that `yes` accepts that recommendation. 3. End the round and wait for the user's answers. 4. Use the answers to identify the decisions ready for the next round. If a question depends on an answer still open in the current round, save it for a later round. Finish the rounds when no ready decisions remain. ## Fact ownership - Finding facts is the agent's job. When a decision needs an environment fact, dispatch a subagent to find it rather than asking the user. - While exploration is running, wait only on the decisions that need its result. Ask the other ready decisions in the current round. - Decisions belong to the user. Put each decision to them and wait for an answer. ## Round format ```text Q1 - <question title>: <question body; optionally multiple paragraphs and multiple choices> Recommendation: <your recommended answer> --- Q2 - <question title>: <question body; optionally multiple paragraphs and multiple choices> Recommendation: <your recommended answer> ``` ## Completion Do not act on the subject until the rounds are finished and the user confirms a shared understanding.
From mineugene/pi-dev-config, MIT.
More from mineugene/pi-dev-config
- 0.587score
architecture-design
mineugene
Design or reshape architecture for a feature, subsystem, API, or refactor while preserving repository philosophy.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
architecture-review
mineugene
Critically evaluate an existing architecture, proposed design, or architectural change.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
graphify
mineugene
Build, update, or query a persistent knowledge graph for a codebase or mixed corpus.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
grill-with-docs
mineugene
Interview before implementing an underspecified feature or design, and record resolved domain language and durable decisions.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ponytail
mineugene
Enforce the smallest working scope with existing code, standard libraries, and native features.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ponytail-audit
mineugene
Whole-repo audit for over-engineering.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ponytail-debt
mineugene
Harvest existing shortcut comments in the codebase into a debt ledger, so deliberate shortcuts and deferrals get tracked instead of becoming permanent.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ponytail-review
mineugene
Code review focused exclusively on over-engineering.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
ponytail-gain
mineugene
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
ponytail-help
mineugene
Quick-reference card for Ponytail modes, skills, and commands.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
implement-spec
mineugene
Implement a specification and its tickets in code on one integration branch.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
implement
mineugene
Implement the work described by a specification or set of tickets.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mineugene/pi-dev-config
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mineugene
- 0.587score
architecture-review
mineugene
Critically evaluate an existing architecture, proposed design, or architectural change.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ponytail
mineugene
Enforce the smallest working scope with existing code, standard libraries, and native features.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
graphify
mineugene
Build, update, or query a persistent knowledge graph for a codebase or mixed corpus.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
grill-with-docs
mineugene
Interview before implementing an underspecified feature or design, and record resolved domain language and durable decisions.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
architecture-design
mineugene
Design or reshape architecture for a feature, subsystem, API, or refactor while preserving repository philosophy.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ponytail-audit
mineugene
Whole-repo audit for over-engineering.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
grilling skill. Agent Mart. https://agentmart.dev/skills/mineugene-grilling (last updated 2026-10-24)