grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
Skill by DixieIT
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/dixieit-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, productivity
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
- Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
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. ## After the plan is finalized Once we reach shared understanding and the implementation plan is settled, do this automatically: 1. **Guard the base branch.** Read the current branch (`git branch --show-current`). If it is `main`, `master`, `test`, or `develop`, STOP — do not touch YouTrack or create a branch. Tell the user to switch to a feature branch first. 2. **Resolve the issue key.** Extract the YouTrack key from the branch name (pattern `[A-Z]+-\d+`, e.g. `feature/KL-2505-audit` → `KL-2505`). A feature branch always maps to an existing issue — if no key is in the name, search YouTrack (`mcp__plugin_youtrack_youtrack__search_issues`) or ask the user for the key. Never create an issue. 3. **Prettify the plan into the issue.** Format the finalized plan as clean Markdown (summary, decisions made, step-by-step tasks) and write it to that issue via `mcp__plugin_youtrack_youtrack__update_issue` (description). Confirm the write. 4. **Cut the agent branch.** From the current feature branch, create and checkout `agent-feature/<name>`, where `<name>` is the current branch name with any leading type prefix stripped (`feature/`, `fix/`, `bugfix/`, etc.) — so both `KL-2552-refactor-audit-portal` and `feature/KL-2552-refactor-audit-portal` become `agent-feature/KL-2552-refactor-audit-portal`. If it already exists, just check it out.
From DixieIT/skills, MIT.
More from DixieIT/skills
- 0.479score
self-reminder-memory
DixieIT
Reliable reminders with OpenClaw cron plus memory logging.
SkillCFreshness: CClaude Code +9 - 0.479score
progress-relay
DixieIT
Send short progress updates to Lele while work is running.
SkillCFreshness: CClaude Code +9 - 0.476score
ticket
DixieIT
Take a YouTrack issue end to end — interview it into a real spec, hand it to a lele agent running in its own Herdr worktree/pane, verify the result yourself…
SkillCFreshness: CClaude Code +9 - 0.476score
check-branches-from-test
DixieIT
Analyze remote branches not yet merged into test, compare them against what is already in origin/test, and judge whether each open branch still adds practical…
SkillCFreshness: CClaude Code +9 - 0.475score
auto-document
DixieIT
Keep automatic work notes in Obsidian during tasks.
SkillCFreshness: CClaude Code +9 - 0.471score
lele-exec
DixieIT
Drive lele as an execution harness for an approved spec: feed the spec to lele, verify its output yourself, and iterate with session continuity (lele -p -s…
SkillCFreshness: CClaude Code +9 - 0.468score
klens-fe-labels-pipeline
DixieIT
Gestisce la pipeline FE + labels repo: raccoglie nuove chiavi i18n, controlla branch su klens-frontend e labels, aggiunge traduzioni en-US/it-IT, esegue…
SkillCFreshness: CClaude Code +9 - 0.450score
find-skills
DixieIT
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 11, 2026 (3 months ago)
- Last release
- Jul 11, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/DixieIT/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from DixieIT
- 0.479score
self-reminder-memory
DixieIT
Reliable reminders with OpenClaw cron plus memory logging.
SkillCFreshness: CClaude Code +9 - 0.479score
progress-relay
DixieIT
Send short progress updates to Lele while work is running.
SkillCFreshness: CClaude Code +9 - 0.476score
ticket
DixieIT
Take a YouTrack issue end to end — interview it into a real spec, hand it to a lele agent running in its own Herdr worktree/pane, verify the result yourself…
SkillCFreshness: CClaude Code +9 - 0.476score
check-branches-from-test
DixieIT
Analyze remote branches not yet merged into test, compare them against what is already in origin/test, and judge whether each open branch still adds practical…
SkillCFreshness: CClaude Code +9 - 0.475score
auto-document
DixieIT
Keep automatic work notes in Obsidian during tasks.
SkillCFreshness: CClaude Code +9 - 0.471score
lele-exec
DixieIT
Drive lele as an execution harness for an approved spec: feed the spec to lele, verify its output yourself, and iterate with session continuity (lele -p -s…
SkillCFreshness: CClaude Code +9
Cite this page
grill-me skill. Agent Mart. https://agentmart.dev/skills/dixieit-grill-me (last updated 2026-10-24)