Call the Skill tool with "grilling".
A relentless interview to sharpen a plan or design.
Ask your Agent
Use this Skill: https://skilld.dev/gh/mattpocock/skills/grill-me
This session only. Nothing lands on disk.
≈15 tokens always: the name and description. ≈9 when used: this file. ≈35 more on demand in 1 file.
Source: SKILL.md on GitHub
Third-party checks
No alerts17d5 checks · Risk SAFE
- Gen Agent Trust Hub17d
No security issues detected. This skill is a prompt-based interview tool designed to help refine user plans or designs without any executable code, external dependencies, or network operations.
- Socket17d
No alerts
- Snyk17d
Risk: LOW · No issues
- Runlayer6mo
1 file scanned · No issues
- ZeroLeaks5mo
Score: 93/100 · 2 sections analyzed
Provenance
Signed by skilld at fcf0071. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub 2 days ago.
Activeupdated 2 months ago
Capability
- disable-model-invocation
- true
Topics
- Design
- interview
- planning
- decision-tree
- requirements
- stress-test
- architecture
README badge
What it does
Conducts a structured interview about a plan or design, asking questions one at a time to expose gaps and resolve dependencies until both you and the user reach shared understanding. Use this when stress-testing an architecture, vetting a design decision, or when the user explicitly asks to be grilled.
Generated from the current SKILL.md.
Frequently asked
When should I use this skill instead of just discussing my plan normally?
Use this when you want the agent to systematically stress-test a plan or design by asking probing questions one at a time until you reach shared understanding, rather than having a casual conversation.
Does the skill ask questions about existing code?
Yes. If a question can be answered by exploring the codebase, the skill will explore it instead of asking you.
How does the skill structure its questions?
It walks down each branch of the decision tree one at a time, resolving dependencies between decisions sequentially. For each question, it provides a recommended answer.
Generated from the current SKILL.md. These answers refresh after source changes.