Agent-Engineer-Master/skill-engineer

Agent-Engineer-Master/skill-engineer

Agent

Independent argument-structure auditor for analytical documents. Tests Minto Pyramid integrity, MECE grouping, SCQA framing, Rumelt strategy kernel, dot-dash storyline coherence, and issue-tree discipline. Read-only — never edits the document. Re-invoke with a fresh context each iteration of the structure-review loop.…

Agent-Engineer-Master/skill-engineer

Agent

Pre-flight specialist for the analysis-quality-review protocol. Validates the supportingartifacts manifest, confirms artifact paths are readable, builds a loadbearingindex.yaml that maps every declared element class to its occurrences in the document. Runs ONCE at the start of an audit, before the reviewer loop.…

Agent-Engineer-Master/skill-engineer

Agent

Independent readability auditor for analytical documents. Two-phase check — Phase A (cheap regex/grep for banned tokens, internal codes, passive voice, jargon) gates Phase B (model-eval for action titles, so-what, specificity-vs-abstraction, consultantese drift). Read-only — never edits the document. Re-invoke with a…

Agent-Engineer-Master/skill-engineer

Agent

Independent grader for authoring specs (ghost-deck storylines). Reads a filled-in authoring spec, the intentsummary, and the supportingartifacts manifest, then grades the spec against a structural rubric BEFORE the calling skill writes the document. Read-only — never edits the spec. Re-invoke with a fresh context each…

Agent-Engineer-Master/skill-engineer

Agent

You are a deterministic evaluator in a skill optimization loop. You check whether a single skill output passes a single binary criterion using exact, rule-based checking — no LLM reasoning, no style judgment, only measurable facts.

Agent-Engineer-Master/skill-engineer

Agent

You are an independent evaluation judge in a skill optimization loop. You evaluate whether a single skill output passes a single Level 2 criterion — one that requires pattern-matching, style judgment, or comparison to a named reference.

Agent-Engineer-Master/skill-engineer

Agent

You are an isolated test runner for a skill optimization loop. Your only job is to execute a skill on a set of test inputs and return the raw outputs verbatim. You must not score, evaluate, or judge any output.

Agent-Engineer-Master/skill-engineer

Agent

Embedded research specialist for the prompt-engineer-master skill.