Content
18%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.
The body is a marketing landing page rather than an implementation guide: it describes capabilities and includes one concrete korekta example, but contains no workflows, no schema/API detail, and no bundled reference files — and admits the actual package contents are absent. It functions as a store listing, not as operational skill content.
Suggestions
Replace the promotional sections ("Why this beats prompting it yourself", the purchase FAQ, creator links) with the actual technical content: FA(3) field mapping tables, KSeF 2.0 endpoint/auth examples, and offline24 QR code requirements.
Add explicit step-by-step workflows with validation checkpoints for the three advertised processes (ERP-to-FA(3) mapping, API onboarding per environment, offline24 contingency submission windows).
Ship the promised materials as one-level-deep reference files (e.g. references/fa3-fields.md, references/onboarding.md, references/offline24.md) and reference them clearly from SKILL.md instead of asserting they exist elsewhere.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Several sections are padded sales copy rather than instructions: "Why this beats prompting it yourself", the purchase FAQ ("What specific documentation and assets are included in this purchase", "Which AI agents or models are compatible with this skill"), and trailing creator/promo links. Not 3 because promotional filler is the dominant character of the body rather than incidental over-explanation, and undated time-sensitive claims ("2026 deadlines", "2027 cutoff") add staleness risk. | 2 / 5 |
Actionability | Only one passage gives concrete field-level guidance ("Set RodzajFaktury to 'KOR'... TypKorekty to 'A'... PrzyczynaKorekty... DaneFaKorygowanej"), while the rest describes rather than instructs ("Outlines onboarding workflows", "Defines offline24 contingency procedures", "Generates readiness checklists") with no XML samples, API endpoints, commands, or field tables. Not 3 because concrete guidance is a single isolated example, not 'some concrete guidance' spread across the skill. | 2 / 5 |
Workflow Clarity | No sequenced steps exist anywhere: API onboarding, offline24 handling, and ERP-to-FA(3) mapping are named but never ordered, and there are no validation checkpoints for XML generation and batch submission to KSeF (which alone caps this dimension at 3). Not 2 because not even a rough sequence is present — the body has zero enumerated procedures. | 1 / 5 |
Progressive Disclosure | The skill's claimed depth (FA(3) field mapping guides, onboarding protocols, compliance checklists) belongs in bundled reference files, yet no references/, scripts/, or assets/ exist and the body states "Scripts, extension source, and templates from the original package are not in this folder". Not 3 because the in-file headers organize promotional copy rather than skill content, and there is no reference layer at all for the material the skill promises. | 2 / 5 |
Total | 7 / 20 Passed |