Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Vs Core Grill

ASecurity

Socratic interview to reach shared understanding before starting work. Use this skill when the user wants to discuss a plan, design, or approach before implementing. Also use when the user says "grill me", "interview me", "let's think through this", "what should we consider", or when starting a complex task where requirements are unclear.

6 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsgobash

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add Lallapallooza/vs-skills --skill vs-core-grill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Vs Core Grill?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Vs Core Grill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lallapallooza-vs-core-grill/badge)](https://www.skillsdirectory.com/skills/lallapallooza-vs-core-grill)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: vs-core-grill
description: Socratic interview to reach shared understanding before starting work. Use this skill when the user wants to discuss a plan, design, or approach before implementing. Also use when the user says "grill me", "interview me", "let's think through this", "what should we consider", or when starting a complex task where requirements are unclear.
allowed-tools: Read Glob Grep Bash AskUserQuestion
---

## Artifact Profile

Read `../vs-core-_shared/prompts/artifact-persistence.md` for the full protocol.

- **stage_name**: grill
- **artifact_filename**: grill.md
- **write_cardinality**: single
- **upstream_reads**: none
- **body_format**:
  ```
  ## Shared Understanding
  ### Decisions Made
  - [Decision 1]
  ...
  ### Open Questions (if any)
  ### Recommended Next Step
  ```

# Socratic Interview

Interview the user relentlessly about every aspect of this plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.

## Artifact Flow

1. **Before the interview begins**: Run ARTIFACT_DISCOVERY (see artifact-persistence.md). Establish the feature slug silently if unambiguous. If `.spec/{slug}/mission.md` exists, read it; skip questions whose answers are present in its Decision Log.
2. **After producing the Shared Understanding summary**: Run WRITE_ARTIFACT -- write `grill.md` to `.spec/{slug}/` with the frontmatter schema and the Shared Understanding block as the body.

## Rules

- Ask questions **one at a time**
- For each question, **provide your recommended answer as a single declarative sentence the user can accept with "yes" or reject with "no"**. If you need a table, multiple paragraphs, or a "here are your options" list to explain the recommendation, the question is either premature (explore the codebase first) or actually several questions in disguise (split it). A recommendation the user has to interpret is a blank canvas with extra steps.
- If a question can be answered by **exploring the codebase**, explore the codebase instead of asking the user
- Resolve dependencies in order: don't ask about implementation details before agreeing on the approach
- Challenge assumptions: if the user's answer seems to conflict with what you know about the codebase or domain, push back respectfully
- Keep going until every branch of the design tree has been resolved to a concrete decision
- Summarize the shared understanding at the end as a bullet list of decisions made

## Output Contract

When the interview is complete, produce a structured summary:

```
## Shared Understanding

### Decisions Made
- [Decision 1]
- [Decision 2]
...

### Open Questions (if any)
- [Question that needs more investigation]

### Recommended Next Step
[What should happen next -- /vs-core-implement, /vs-core-rfc, /vs-core-arch, or something else]
```

This output format allows composite skills (like `/vs-core-rfc`) to consume the grill results programmatically.

Attribution

LallapalloozaLallapallooza
View sourceSee grades on GitHubMore from Lallapallooza →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →