Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A sophisticated, highly actionable multi-phase workflow with strong validation checkpoints. Its main weaknesses are a monolithic structure with no external references and some verbose passages that could be tightened.
Suggestions
Move the RICE scoring rubric (Reach/Impact/Confidence/Effort anchors) and the opportunity output template into a references/ file (e.g. RICE.md), keeping SKILL.md a concise overview that links one level deep.
Convert the narrative Effort guidelines (0.25 through '10+') into a compact table to cut tokens without losing the anchors.
Tighten the 'Writing standards' bullet list by merging redundant style rules and dropping guidance that restates general good writing practice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean operational directives, but the RICE effort-guidelines prose (anchored narrative from 0.25 to '10+') and the 'Writing standards' block could be tightened into a table or trimmed; a few explanatory asides exceed what the workflow strictly needs. | 2 / 3 |
Actionability | Gives concrete, executable guidance throughout — exact tool calls with parameters (e.g. search with isOfficial: true, sortOrder: 'viewCount', limitPerQuery: 15), call budgets, the RICE formula, and a copy-paste opportunity template with word counts. | 3 / 3 |
Workflow Clarity | A clearly sequenced five-phase process with explicit validation in Phase 4 (partial-data artifacts, seasonality, already-shipped fixes, correlation vs causation) and a RICE>=100 quality gate that acts as a checkpoint before delivery. | 3 / 3 |
Progressive Disclosure | Sections are well organized, but the ~240-line body is monolithic with no reference files; the RICE rubric, opportunity template, and examples are inline detail that could be split into one-level-deep references for easier navigation. | 2 / 3 |
Total | 10 / 12 Passed |