Content
72%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured advisory skill body: terse, competence-assuming prose, concrete metric targets, and clean one-level-deep disclosure into real bundle files. The main weakness is workflow clarity — sequences and a pre-recommendation checkpoint exist, but validation/feedback loops are implicit rather than explicit.
Suggestions
Add an explicit validation loop to the budget workflow, e.g. "Compare marketing_budget_modeler.py projected MQL output against last quarter's actuals and recalibrate CAC assumptions before finalizing allocation."
Number the budget-allocation derivation end-to-end (revenue target → new customers needed → MQLs needed → spend by channel) as a checklist with a final sanity-check step, mirroring the explicitness of the hiring sequence.
Remove the Keywords section (duplicates the frontmatter description's triggers) and the Resources section (duplicates Quick Start's file listing) to tighten the body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes competence ("Scale what's improving. Cut what's worsening. Don't optimize a channel that isn't in the strategy") with no basic-concept padding. Not 5 because the Keywords section duplicates the frontmatter description's trigger terms and the Resources section re-lists the reference and script paths already given in Quick Start. | 4 / 5 |
Actionability | Executable Quick Start commands ("python scripts/marketing_budget_modeler.py"), concrete thresholds ("LTV:CAC ratio > 3:1", "Pipeline coverage ratio 3–4x quarterly quota"), and a request-to-artifact table give mostly executable guidance. Not 5 because the script invocations lack example inputs/outputs, so the common cases aren't fully copy-paste covered. | 4 / 5 |
Workflow Clarity | Sequences exist — budget: "new customers needed → conversion rates by stage → MQLs needed → spend by channel based on CAC"; hiring: "generalist first, then specialist..., then PMM, then marketing ops" — and "Ask these before making any strategic recommendation" acts as a pre-check. But validation remains implicit: there is no feedback loop such as comparing modeler projections against actuals before finalizing a budget, so checkpoints are missing rather than explicit. | 3 / 5 |
Progressive Disclosure | The body is an overview with well-signaled one-level-deep references ("**Reference docs (load when needed):** `references/brand_positioning.md` — category design, messaging architecture, battlecards, rebrand framework") and "Details →" pointers per responsibility; all three reference files and both scripts referenced in the body exist in the bundle, and nothing is nested deeper than one level. | 5 / 5 |
Total | 16 / 20 Passed |