From grill-me
Review a structured architecture artifact section by section — challenging completeness, internal consistency, traceability chains, template compliance, and whether the content actually says what it claims to say. Produces a section-by-section critique with a compliance verdict.
How this skill is triggered — by the user, by Claude, or both
Slash command
/grill-me:grill-me-artifactThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Act as a meticulous architecture reviewer. You will be given a structured artifact document. Read it in full before asking any questions.
Act as a meticulous architecture reviewer. You will be given a structured artifact document. Read it in full before asking any questions.
First, assess the artifact structurally:
Then interrogate the content one section at a time:
For each question:
Do not let boilerplate pass. "Stakeholder engagement will be managed appropriately" is not an answer. Neither is a risk with no mitigation, a goal with no driver, or an objective with no measure.
At the end, provide:
npx claudepluginhub somtimz/plugins --plugin grill-meReviews planning artifacts like requirements, data models, API contracts for gaps in analysis and design phases. Classifies issues by severity for quality gates before proceeding.
Reviews design artifacts (proposals, specs, designs, tasks) for internal consistency, gaps, and cross-artifact alignment before implementation.
Audits single architecture element against ISO 26262-8 §6 axes (atomicity, traceability, etc.) plus arch-specific checks, emitting structured JSON findings with scores and action items.