alexion/dev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(skills): reorganize grill flow

Browse Source
This commit is contained in:
alexion
2026-09-08 10:34:51 -04:00
parent bf5249f74e
commit bf1c37c852
1 changed files with 24 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
src/skills/grill/SKILL.md
View File

@@ -6,8 +6,8 @@ description: Stress-test a plan, decision, or design through a one-question-at-a
# grill
Interview the user until the design tree has no open questions.
The design tree contains each decision and the decisions that depend on it.
Open questions define the ending condition for the grill session.
The design tree tracks which decisions depend on other decisions.
Do not create glossary, context, or ADR files during grill.
Do not begin implementation during or after grill without an explicit user instruction.
@@ -33,41 +33,40 @@ A completed grill summary is not an instruction to build.
Present the full open-question list in short form.
Include titles only, not full question bodies.
Mark each unresolved question with `- [ ]`.
Then start the interview in the same turn with the first numbered question.
Then ask the first numbered question in the same turn.
Finish when the user sees the open-question list and the first question.
4. Ask one question at a time.
End each active grill turn with exactly one next numbered question.
Give concrete options with trade-offs.
Give a recommendation and rationale.
Wait for the user's answer before the next question.
Finish when the user has answered the current question.
5. Update the open-question list.
Apply the rules in [Open-question accounting](#open-question-accounting).
4. Run the question loop.
Show the full open-question list on every active grill turn.
Ask one numbered question at a time.
Apply [Question format](#question-format) to each question.
Wait for the user's answer.
Apply [Open-question accounting](#open-question-accounting) before asking again.
Resolve newly answerable facts yourself before asking again.
Finish when every list change has an explicit marker and cause.
Finish when one answer has been accounted for.
6. Challenge weak decisions.
Probe vague words, overloaded terms, and hidden assumptions.
Use concrete scenarios to test concept boundaries and edge cases.
When code contradicts the user's claim, quote both the claim and the code behavior.
Finish when the next open question accounts for the challenge.
7. Close the interview.
5. Close the interview.
Stop when the open-question list is empty.
Output a concise summary of every decision reached.
Include speculative follow-up questions that were not added to the open-question list.
Do not act on the summary unless the user gives a new implementation instruction.
Finish when the summary is delivered and grill waits.
## Question format
End each active grill turn with exactly one numbered question.
Give concrete options with trade-offs.
Give a recommendation and rationale.
Probe vague words, overloaded terms, and hidden assumptions.
Use concrete scenarios to test concept boundaries and edge cases.
When code contradicts the user's claim, quote both the claim and the code behavior.
## Open-question accounting
Show the full open-question list on every active grill turn.
Use `- [ ]` for unresolved questions.
Use `- [+]` for questions added by the latest answer.
Use `- [u]` for questions updated by the latest answer.
@@ -94,6 +93,9 @@ Use this format:
Preserve agent judgment when the user reframes or invalidates a question.
Show the resulting list change instead of following a rigid reframe algorithm.
When the user catches incorrect open-question handling, briefly explain the error.
Then show the corrected open-question list.
## Turn endings
While grill is active, every assistant turn must end with exactly one of these items:
@@ -103,5 +105,3 @@ While grill is active, every assistant turn must end with exactly one of these i
- a plain statement that grill is paused because the user changed tasks
If the turn includes a correction, file edit, apology, or explanation, still end with the next numbered question.
When the user catches incorrect open-question handling, briefly explain the error.
Then show the corrected open-question list.