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".
Use this Skill: https://skilld.dev/gh/brianlovin/agent-config/grill-me Nothing lands on disk. Nothing to clean up.
Edit a local copy. It keeps the author and licence.
≈60 tokens for metadata: the name and description. ≈83 when used: this file.
Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.
In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈242 characters, or 3.0%.
The 1% threshold is a size suggestion. Longer descriptions can still fit.
Your model, settings, and other Skills decide how much text your Agent can read.
The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.
Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.
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.
If a question can be answered by exploring the codebase, explore the codebase instead.
Source: SKILL.md on GitHub
No rule matched.
skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.
skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.
The skill is designed to interview the user to stress-test designs and plans, including codebase exploration. It is generally safe but carries a low risk of indirect prompt injection because it incorporates external codebase content into its reasoning process without explicit boundary markers.
No alerts
Risk: LOW · No issues
Signed by skilld at 1a9819e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub last week.
Conducts systematic interviews about a plan or design, asking probing questions down each decision branch until reaching shared understanding. Use when stress-testing an architecture, design decision, or plan—the skill walks dependencies methodically and suggests answers where codebase context exists.
Generated from the current SKILL.md.
Generated from the current SKILL.md. These answers refresh after source changes.