grill-with-docs/SKILL.md
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
npx skillsauth add anahelenasilva/skills grill-with-docsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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, waiting for feedback on each question before continuing.
If a question can be answered by exploring the codebase, explore the codebase instead.
</what-to-do> <supporting-info>During codebase exploration, also look for existing documentation:
Most repos have a single context:
/
├── CONTEXT.md
├── docs/
│ └── adr/
│ ├── 0001-event-sourced-orders.md
│ └── 0002-postgres-for-write-model.md
└── src/
If a CONTEXT-MAP.md exists at the root, the repo has multiple contexts. The map points to where each one lives:
/
├── CONTEXT-MAP.md
├── docs/
│ └── adr/ ← system-wide decisions
├── src/
│ ├── ordering/
│ │ ├── CONTEXT.md
│ │ └── docs/adr/ ← context-specific decisions
│ └── billing/
│ ├── CONTEXT.md
│ └── docs/adr/
Create files lazily — only when you have something to write. If no CONTEXT.md exists, create one when the first term is resolved. If no docs/adr/ exists, create it when the first ADR is needed.
When the user uses a term that conflicts with the existing language in CONTEXT.md, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?"
When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' — do you mean the Customer or the User? Those are different things."
When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.
When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?"
When a term is resolved, update CONTEXT.md right there. Don't batch these up — capture them as they happen. Use the format in CONTEXT-FORMAT.md.
Don't couple CONTEXT.md to implementation details. Only include terms that are meaningful to domain experts.
Only offer to create an ADR when all three are true:
If any of the three is missing, skip the ADR. Use the format in ADR-FORMAT.md.
</supporting-info>tools
Merges a specified branch into the current branch using pnpm-based verification (typecheck + tests), resolves conflicts, and optionally closes a GitHub issue via gh CLI. Use when the user mentions "Sandcastle", asks to merge a branch and close an issue, or references the Sandcastle merge protocol.
tools
Autonomously implements open GitHub issues labeled "Sandcastle" one at a time using the RALPH workflow (explore, plan, RGR test-first, verify, commit, close). Use when the user says "implement next Sandcastle issue", "process open issues", "run RALPH", or asks to work through the Sandcastle backlog. Assumes pnpm, gh CLI, and git are configured in the current repo.
development
Reviews and refines code on a branch for the Sandcastle project. Use when asked to "review", "clean up", "refine", or "code review" on a branch. Call as `/sandcastle-code-review` to review the current branch, or `/sandcastle-code-review [branch-name]` to review a specific branch. Makes improvements in place — reads the diff, fixes issues, runs tests, commits. Do NOT use for general code questions or reviews outside the Sandcastle project.
development
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.