Grill
Trigger: grill me, grill with docs, grill me sdd, grill code, grill docs open, entrevistame, entrevistame sdd. Router for relentless interview modes: plain, docs, or SDD planning.From its SKILL.md
npx -y skills add andresnator/agents-orchestrator --skill grillAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
4.4 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it
Activation Contract
Use when the user wants a relentless interview for a plan, design, code approach, docs-backed exploration, or SDD planning set.
Select exactly one mode:
| Trigger shape | Mode | Behavior |
|---|---|---|
grill me, grill code, entrevistame | plain | Run grilling with native question UX. |
grill with docs, grill docs open | docs | Run grilling plus domain-modeling with native question UX. |
grill me sdd, entrevistame sdd, SDD planning interview | sdd | Interview, then draft OpenSpec proposal.md, specs, design.md, and tasks.md. |
Hard Rules
- Every user-facing question MUST go through the
native-question-uxskill. Use its fallback if the runtime has no native question tool. - Follow the
grillingskill in every mode: one question at a time, attach a recommendation, stop and wait, and explore the codebase instead of asking when possible. - Preserve open-ended interview semantics; do not turn the flow into generic code review.
docsmode also followsdomain-modelingto capture terms, decisions, and context as they emerge.- Interview/summaries/gates use the user's language; artifacts default to English unless the user explicitly requests Spanish artifacts.
sddmode is plan-only: read-only codebase access; no code edits, builds, installs, tests, commits, or state-changing commands. The only side effect is writing approved planning.mdfiles.- In
sddmode, subskills return approved drafts only; this orchestrator owns the single write step.
Plain Mode
- Load
grilling. - Ask each interview question through
native-question-ux. - Stop after each question and wait for the answer.
- Return the next question, recommendation, or conclusion from the active grilling flow.
Docs Mode
- Load
grillinganddomain-modeling. - Ask each interview question through
native-question-ux. - Capture useful terminology, decisions, and context through the
domain-modelingflow when the user approves documentation. - Stop after each question and wait for the answer.
- Return the next question, recommendation, captured-doc status, or conclusion from the active flow.
Decision Gates
| Situation | Action |
|---|---|
| Missing change name | Propose a kebab-case, verb-led name and confirm. |
.ai/orchestrator/changes/{change-name}/ exists | Ask resume vs rename. |
| Product/business uncertainty | Route to sdd-draft-proposal. |
| Observable behavior uncertainty | Route to sdd-draft-spec. |
| Technical/architecture uncertainty | Route to sdd-draft-design. |
| Slicing or task-ordering uncertainty | Route to sdd-draft-tasks. |
| User stops early | Offer to write approved artifacts only. |
Execution Steps
Use these steps only in sdd mode:
- Set language and confirm the change name.
- If an existing change folder exists, ask whether to resume or rename.
- Run
sdd-draft-proposal; loop inline until the proposal draft is approved. - Build the capability work list from proposal Capabilities.
- Ask once whether spec approval should be per-file or batched.
- Run
sdd-draft-specfor each capability or batch; loop until approved. - Run
sdd-draft-design; it must silently explore the real codebase read-only before technical questions or draft. - Run
sdd-draft-taskswith the approved spec and design; loop inline until the tasks draft is approved. - Ask once to write N files under
.ai/orchestrator/changes/{change-name}/. - On yes, write exactly
proposal.md,specs/{capability}/spec.md,design.md, andtasks.md; on no, leave drafts inline.
Output Contract
Return approved drafts, write status, paths written or pending, and unresolved questions. If a referenced skill cannot be resolved by name in the current runtime, say so instead of silently continuing.
References
grillingskillnative-question-uxskilldomain-modelingskillsdd-draft-proposalskillsdd-draft-specskillsdd-draft-designskillsdd-draft-tasksskill
Attribution
Inspired by Matt Pocock's grilling skills at https://github.com/mattpocock/skills; adapted for SDD planning orchestration.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 2 of the 12 instructions most review quality skills give in ~1.0k tokens
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07
- Ask questions one at a timehere, and in 81 of 1048, across 64 files
- Provide a recommended answer for each questionin 73 of 1048, across 50 files
- Explore the codebase instead of asking answerable questionshere, and in 66 of 1048, across 42 files
- Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
- Interview the user relentlessly about the planin 38 of 1048, across 13 files
- Order findings by severityin 31 of 1048
- Resolve each branch of the decision treein 27 of 1048, across 5 files
- Run a grilling sessionin 26 of 1048, across 5 files
- Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
- Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
- Create documentation files lazilyin 24 of 1048, across 5 files
- Assign severity to every findingin 24 of 1048
Said here and by no other author read
- Select exactly one interview mode per request
- Route every user-facing question through native-question-ux
- Attach a recommendation to each interview question
- Capture domain terms and decisions during docs mode
- Conduct interviews and gates in the user's language
- Write approved planning artifacts in English unless requested otherwise
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.