Content
81%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 strong, expert-level body: concrete numbers throughout, a sequenced lifecycle with pre-launch validation checkpoints, an operational checklist, and an appropriately split-off reference for the volume-UGC variant. The remaining gaps are minor — a few editorial sentences could be cut, ready-to-use templates (outreach note, brief, agreement clause) are delegated rather than included, and the long body could shed one or two sections into reference files.
Suggestions
Trim editorial asides that don't change behavior (e.g., the 'Disclosure done well doesn't hurt performance' closer and the 'relationship than transaction' spectrum commentary) to tighten conciseness toward level 5.
Add one compact fill-in template — a short outreach note or creative-brief skeleton — since cold-email and ad-creative only cover fragments, closing the actionability gap.
Consider moving the Ambassador Program Design section (or the compensation rate tables) into a references/ file linked from the body, slimming SKILL.md toward a true overview and lifting progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and information-rich — tier tables, rate ranges, and checklists where every row carries non-obvious domain knowledge (e.g., "$100 – $1,500" micro rates, "~1–3% is healthy on IG/TikTok"), with no padding that explains concepts Claude already knows. It sits at level 4 rather than 5 because a few editorial asides could be trimmed ("Disclosure done well doesn't hurt performance — audiences expect it, and the FTC has never found '#ad' to tank a genuinely good integration"; "The further right you go, the more it's about relationship than transaction"). It is clearly above level 3: the unnecessary explanation is minor, not a pattern. | 4 / 5 |
Actionability | Guidance is consistently concrete for an instruction-only skill: exact tier follower ranges, negotiable dollar ranges per tier ("Nano ... Free product – $100"), a five-item vetting checklist, specific deal clauses ("usage rights ... commonly 3–6 months"), and a full run-of-show checklist. It is not level 5 because the fill-in artifacts are delegated rather than provided — no sample outreach note, brief template, or agreement clause text inline; it is well above level 3 since the specific numbers and steps cover the common cases. | 4 / 5 |
Workflow Clarity | The lifecycle is clearly sequenced (§1 Finding → §2 Outreach → §3 Deal → §4 Compliance → §5 Brief → §6 Measurement, plus a phase-organized run-of-show checklist), with explicit validation checkpoints: "Set up tracking ... *before* content goes live," "Confirm the disclosure actually shipped where viewers can see it," and "Review the draft if you have approval rights — without over-scripting." Post-campaign steps include an iterate/double-down decision loop ("double down on the top decile; graduate strong ambassadors to paid partnerships"), matching the level-5 anchor with checklists and feedback loops; this is not a destructive/batch operation, so no cap applies. | 5 / 5 |
Progressive Disclosure | The one bundle reference is well-signaled and one level deep — "See [references/ugc-creator-program.md] ... for the full system — playbook-first concepts, the four formats, trial-week vetting ..." (verified: the file exists and contains that content), and the UGC detail was appropriately split out rather than inlined. It sits at 4 rather than 5 because the SKILL.md body itself is a ~190-line full playbook; sections like Ambassador Program Design and the rate tables are core but make the 'overview' heavy, and there are no further reference splits to distribute that weight. | 4 / 5 |
Total | 17 / 20 Passed |