Call the Skill tool twice, for "grilling" and "domain-modeling".
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Use this Skill: https://skilld.dev/gh/mattpocock/skills/grill-with-docs Nothing lands on disk. Nothing to clean up.
Edit a local copy. It keeps the author and licence.
≈31 tokens for metadata: the name and description. ≈16 when used: this file. ≈37 more on demand in 1 file.
How this Skill uses context
Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.
This Skill turns off automatic use in Claude Code. Its description stays out of the automatic Skill list by default.
Example settings and source
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.
Source: SKILL.md on GitHub
Skill behaviors
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.
Third-party checks
No alerts2mo3 checks · Risk SAFE
- Gen Agent Trust Hub2mo
The skill is a configuration-only package designed to facilitate design reviews and documentation. It contains no executable code, network operations, or sensitive file access.
- Socket2mo
No alerts
- Snyk2mo
Risk: LOW · No issues
Provenance
Signed by skilld at abeeaf9. 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.
Capability
- disable-model-invocation
- true
Topics
- Documentation
- domain-modeling
- adr
- decision-making
- terminology
- codebase-analysis
- context-mapping
README badge
What it does
Conducts a structured interview about your design plan, walking through each decision branch while checking terminology against your existing domain model and codebase. Updates CONTEXT.md and ADRs inline as shared understanding crystallizes, surfacing contradictions between stated behavior and code implementation.
Generated from the current SKILL.md.
Frequently asked
Does this skill update code, or just documentation?
What if my repo doesn't have CONTEXT.md or an ADR directory yet?
How does this differ from a regular design review?
Can this work with multiple bounded contexts?
Generated from the current SKILL.md. These answers refresh after source changes.