Content
67%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-organized, information-dense advisory skill whose real value — the 2026 Omnibus scope/ESRS changes — is surfaced prominently and consistently, with actionable output formats and verified one-level-deep references. Its main cost is token weight: substantial baseline ESRS/framework content that Claude already knows is inlined in the overview instead of living in the reference files.
Suggestions
Move the full ESRS E1-G1 topic tables and the CSRD-vs-GRI/TCFD/SASB comparison into references/esrs-standards.md, keeping only a one-line standards index in the body.
Link each reference file at its point of use (e.g., in the DMA and ESRS sections) instead of only in the terminal Reference Files section.
Replace the superseded pre-Omnibus timeline table with a single current timeline under the Omnibus banner, and mark pre-2026 wave dates explicitly as superseded to cut length and prevent stale-guidance errors.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is fact-dense and much of it is genuinely non-inferable (the 2026 Omnibus scope change, revised-ESRS dates, assurance timeline), but it also inlines knowledge Claude already has and content duplicated by the bundle: the full ESRS E1-G1 topic tables, the GRI/TCFD/SASB comparison table, and the pre-Omnibus timeline table all largely restate references/esrs-standards.md or common knowledge. Mostly efficient with clear tightening opportunities (move per-standard detail and framework comparison to references), so it sits at anchor 3 rather than 4. | 3 / 5 |
Actionability | For an instruction-only skill the guidance is concrete and executable: a task-to-output-format routing table ("Gap assessment → Table: ESRS Topic | Current State | Gap | Priority | Action"), a citation requirement ("cite... 'Art. 19a CSRD'... 'ESRS E1-6'"), specific decision rules ("A company at 800 employees is no longer a CSRD-mandatory reporter regardless of turnover"), and the mandatory disambiguation question ("Before any gap assessment, ask: current ESRS (2023) basis or revised ESRS (2026) basis?"). Not a 5 because there are no worked examples (e.g., a sample gap-table row or DMA output) to make the formats copy-paste ready. | 4 / 5 |
Workflow Clarity | Four workflows are clearly numbered and sequenced (e.g., 8-step gap assessment ordered confirm-scope-first; value chain setup ends with disclosing methodology), and checkpoints are present ("Confirm current Art. 40a status before advising", "Validate and update — at least annually"). Not a 5 because validation steps are implicit or first-positioned rather than explicit verify-then-proceed checkpoints, and the advisory workflows lack explicit error-recovery guidance. | 4 / 5 |
Progressive Disclosure | The body functions as an overview and the Reference Files section clearly signals three real, one-level-deep bundle files with accurate content descriptions (verified: references/esrs-standards.md, references/double-materiality.md, references/compliance-program.md exist, match their descriptions, and contain no nested references). Not a 5 because the pointers live only in a terminal section rather than at point of use (the ESRS and DMA sections should link to their references inline), and the body at ~250 lines carries per-standard detail that belongs in references/esrs-standards.md. | 4 / 5 |
Total | 15 / 20 Passed |