
Grill With Docs
- 577k installs
- 192k repo stars
- Updated July 27, 2026
- mattpocock/skills
grill-with-docs is a Claude Code skill that sharpens a plan through a relentless grilling interview while writing resolved terminology to a CONTEXT.md glossary and hard decisions to ADRs as it goes.
About
grill-with-docs runs a relentless interview (a /grilling session) to sharpen a plan or design, and leaves a paper trail as it goes: it drives the /domain-modeling skill so resolved terminology lands in CONTEXT.md and hard-to-reverse decisions become ADRs. It is the stateful variant of the repo's grilling primitive, meant for when you have a codebase whose documented language the plan should be tested against; /grill-me is the stateless alternative when no repo exists. In the repo's main idea-to-ship flow it is the recommended starting point, before spec and ticket writing. Reach for it to stress-test an idea against your project's existing vocabulary and documented decisions while keeping those docs current.
- Runs the repo's /grilling interview primitive against your plan or design
- Drives the /domain-modeling skill so resolved terminology lands in CONTEXT.md and hard decisions become ADRs
- Stateful counterpart to /grill-me: it retains what it learns in the repo's docs, leaving a paper trail
- Recommended first step of the repo's idea-to-ship flow when a codebase exists
Grill With Docs by the numbers
- 576,514 all-time installs (skills.sh)
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
grill-with-docs capabilities & compatibility
- Capabilities
- plan review · glossary maintenance · adr authoring · requirements interview
- Use cases
- planning · documentation
- Runs
- Runs locally
- Pricing
- Free
What grill-with-docs says it does
Interview me relentlessly about every aspect of this plan until we reach a shared understanding.
Only offer to create an ADR when all three are true:
npx skills add https://github.com/mattpocock/skills --skill grill-with-docsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 577k |
|---|---|
| repo stars | ★ 192k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | mattpocock/skills ↗ |
How do I pressure-test a plan against my codebase's documented language and keep the glossary and decision records current while deciding?
Sharpen a plan or design through a relentless grilling interview that writes resolved terminology to CONTEXT.md and hard decisions to ADRs as it goes.
Who is it for?
Developers with an existing codebase who want a plan interrogated and the resulting terminology and decisions documented as they crystallise.
Skip if: Skip when there is no codebase to persist docs into; the repo's stateless grill-me variant covers that case.
When should I use this skill?
You have a codebase and a plan or design to sharpen, and want the interview's resolved terms and decisions captured in CONTEXT.md and ADRs as you go.
What you get
A sharpened plan plus updated CONTEXT.md glossary entries and ADRs recording the decisions made during the interview.
- CONTEXT.md glossary updates
- ADR files
By the numbers
- ADR offered only when all 3 conditions are true
Files
<what-to-do>
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>
Domain awareness
During codebase exploration, also look for existing documentation:
File structure
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.
During the session
Challenge against the glossary
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?"
Sharpen fuzzy language
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."
Discuss concrete scenarios
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.
Cross-reference with code
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?"
Update CONTEXT.md inline
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.
CONTEXT.md should be totally devoid of implementation details. Do not treat CONTEXT.md as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.
Offer ADRs sparingly
Only offer to create an ADR when all three are true:
1. Hard to reverse — the cost of changing your mind later is meaningful 2. Surprising without context — a future reader will wonder "why did they do it this way?" 3. The result of a real trade-off — there were genuine alternatives and you picked one for specific reasons
If any of the three is missing, skip the ADR. Use the format in ADR-FORMAT.md.
</supporting-info>
CONTEXT.md Format
Structure
# {Context Name}
{One or two sentence description of what this context is and why it exists.}
## Language
**Order**:
{A one or two sentence description of the term}
_Avoid_: Purchase, transaction
**Invoice**:
A request for payment sent to a customer after delivery.
_Avoid_: Bill, payment request
**Customer**:
A person or organization that places orders.
_Avoid_: Client, buyer, accountRules
- Be opinionated. When multiple words exist fo
Related skills
How it compares
Use instead of ad-hoc chat planning; the interview is stateful and leaves ADRs and a glossary behind rather than losing decisions to chat history.
FAQ
What does grill-with-docs do?
It runs a relentless grilling interview to sharpen a plan or design, driving the domain-modeling skill so resolved terms land in CONTEXT.md and hard-to-reverse decisions become ADRs.
How is grill-with-docs different from grill-me?
Both run the same grilling primitive. grill-with-docs is stateful and assumes a codebase: it leaves a paper trail in CONTEXT.md and ADRs. grill-me is stateless and saves nothing locally.
Where does it fit in the repo's main flow?
It is step one of the idea-to-ship flow: sharpen the idea first, then move to to-spec and to-tickets for multi-session builds, or straight to implement for small ones.
Is Grill With Docs safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.