microsoft/eu-greenwashing-analysis
Use this skill whenever the user submits a product description, marketing text, catalog entry, packaging copy, or advertising claim and asks to check it for greenwashing, environmental claim compliance, sustainability wording risks, or alignment with EU Directive 2024/825 or the Green Claims Directive. Produces a structured per-claim findings report with risk levels, regulation references, and recommended corrections.
npx skills add https://github.com/microsoft/cat-agent-skills --skill eu-greenwashing-analysis
Run this procedure whenever a user submits a product description, marketing
text, or catalog entry for review against EU rules on environmental claims
(Directive 2024/825 amending 2005/29/EC, and the proposed Green Claims
Directive COM/2023/166).
The output is always a structured findings report: one block per flagged
claim plus a summary. Do not editorialize outside that structure.
Read the full text and list every statement that references environmental
benefit, sustainability, ecological impact, or climate performance. Examples
include: "eco-friendly", "carbon neutral", "100% natural", "sustainable",
"green", "biodegradable", "zero emissions", "climate positive", "recycled",
"plastic-free", "low carbon", "environmentally safe".
If no such claims exist → output: "No environmental claims detected — Out of Scope." and stop.
For each extracted claim, check ALL of the following:
(e.g., "eco", "green", "sustainable") with no measurable indicator,
certification, or evidence cited? → High risk flag.
the product life cycle (e.g., recyclable packaging) while ignoring other
high-impact phases (manufacturing, transport, end-of-life)? → Medium to
High risk flag.
verification, recognized EU certification, or scientific reference to
support the claim? → Medium to High risk flag.
against an irrelevant benchmark, obsolete product, or omit material
information that would change the consumer's perception? → High risk flag.
zero") rely primarily on carbon offsetting schemes rather than actual
emission reductions? If offsets are not independently verified under
EU-recognized standards → Medium to High risk flag.
label, badge, or logo that is not officially recognized in the EU, or
whose criteria have not been verified? → High risk flag.
(e.g., "will be carbon neutral by 2030") presented in a way that implies
a current state? → Medium risk flag.
non-compliant with EU Directive 2024/825 or the Green Claims Directive.
Immediate corrective action required.
verification, life-cycle scope, or specificity. Corrective action
recommended before publication.
formal certification before final catalog inclusion.
For EACH flagged claim, output one block in this exact format:
Product Claim: [exact quote of the claim as it appears in the text]
Risk Level: 🔴 High / 🟡 Medium / 🟢 Low
Regulation Reference: [e.g., "EU Directive 2024/825, Art. 3 — Prohibition of misleading environmental claims" or "Green Claims Directive COM/2023/166, Art. 5 — Substantiation requirements"]
Issue: [1–2 sentences explaining what makes this claim problematic under EU regulation]
Recommended Correction: [suggested compliant rewrite or specific action the team should take, e.g., "Replace with a specific, verified figure: 'Made with 40% recycled ocean plastic, certified by [recognized body]'"]
After all per-claim blocks, output a summary in this format:
Greenwashing Findings Summary
Take microsoft/eu-greenwashing-analysis from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.