AGENT SKILL

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.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 107
Forks
120

01 前言 Front Matter

name
eu-greenwashing-analysis
description
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.

02 资源文件 2

03 SKILL.md 正文

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.


Step 1 — Extract all environmental claims

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.


Step 2 — Assess each claim against EU greenwashing criteria

For each extracted claim, check ALL of the following:

  1. Vagueness / Generic claim — Is the claim broad or unsubstantiated (e.g., "eco", "green", "sustainable") with no measurable indicator, certification, or evidence cited? → High risk flag.
  2. Incomplete life-cycle scope — Does the claim highlight one phase of the product life cycle (e.g., recyclable packaging) while ignoring other high-impact phases (manufacturing, transport, end-of-life)? → Medium to High risk flag.
  3. Unverifiable / No third-party certification — Is there no independent verification, recognized EU certification, or scientific reference to support the claim? → Medium to High risk flag.
  4. Misleading comparison — Does the claim compare the product favorably against an irrelevant benchmark, obsolete product, or omit material information that would change the consumer's perception? → High risk flag.
  5. Carbon offset reliance — Does the claim (e.g., "carbon neutral", "net 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.
  6. Unsupported label or logo — Does the product display an environmental label, badge, or logo that is not officially recognized in the EU, or whose criteria have not been verified? → High risk flag.
  7. Forward-looking claim presented as current — Is a future commitment (e.g., "will be carbon neutral by 2030") presented in a way that implies a current state? → Medium risk flag.

Step 3 — Assign a risk level per claim

  • ? High — Claim is clearly unsubstantiated, misleading, or likely non-compliant with EU Directive 2024/825 or the Green Claims Directive. Immediate corrective action required.
  • ? Medium — Claim is partially substantiated but lacks full verification, life-cycle scope, or specificity. Corrective action recommended before publication.
  • ? Low — Claim is specific and plausible but should be reviewed for formal certification before final catalog inclusion.

Step 4 — Fill the standard findings template

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]'"]


Step 5 — Summary assessment

After all per-claim blocks, output a summary in this format:

Greenwashing Findings Summary

  • Total environmental claims reviewed: [N]
  • ? High risk: [N]
  • ? Medium risk: [N]
  • ? Low risk: [N]
  • ✅ Compliant (no action needed): [N]
  • Overall compliance posture: Compliant / Needs Review / Non-Compliant
  • Top priority action: [single most urgent corrective step]

04 同仓库更多 Skills

microsoft
microsoft/cat-agent-skills

stakeholder-and-decision-map

Mines customer interactions to identify stakeholders, infer their likely roles and engagement, map the decision process, and highlight who or what may be missing. Use when asked to "map a deal's buying group", identify influential or missing stakeholders, "assess who has gone quiet", or "explain how the customer will decide". Do not use for phased engagement plans, contact sequences, choosing or drafting outreach to the single next contact, seller or team performance reviews, or contacting, scheduling, or changing records.

★ 107
microsoft
microsoft/cat-agent-skills

sales-progress-update

Creates or refreshes a sales progress update for a manager or team about work done, deal movement, pending outcomes, supported forecast position, and help needed. Use when asked to "create my weekly sales update", "refresh my sales progress deck", "report my forecast position", "where do I stand against my quarter forecast", or "catch my manager up on committed deals". Do NOT use for non-sales project updates, a since-date deal change digest, momentum or blocker analysis, meeting prep, or outreach drafting.

★ 107
microsoft
microsoft/cat-agent-skills

submission-assemble

Put the checked CSR or 510(k) sections together in template order with a reviewer-facing open-items register, as a draft package for human sign-off. Use when the user asks "assemble the CSR draft", "put the module together for review", "build the review package with the open items on top", "compile the 510(k) sections in order" or "package this up for the submission lead". Do NOT use for assembling an unchecked draft - use consistency-check instead. Do NOT use for loading protocol, SAP or TLF sources - use source-ingest instead. Do NOT use for compiling general documents or slide decks - use the built-in docx or pptx skill instead. Do NOT use for filing or submitting to a regulator - use the sponsor's validated gateway, operated by a human, instead. Guardrail: draft for human approval only (L1); status is draft_clean or draft_open_items, never submitted.

行政与办公人员文档处理演示文稿
★ 107
microsoft
microsoft/cat-agent-skills

source-ingest

Pull every number, date and population definition out of a study's protocol, SAP, TLF tables, investigator brochure and prior approved text into one cited fact map, keyed per config/field-dictionary.json, before any CSR or 510(k) section is written. Use when the user asks "here's the locked TLF set and SAP, set up the CSR", "load the protocol and tables before we start drafting", "what figures do we have from the database lock?", "pull the disposition counts out of Table 14.1.1" or "ingest the IB for the 510(k)". Do NOT use for drafting or assembling submission sections - use section-draft or submission-assemble instead. Do NOT use for reconciling a patient's medications - use the discharge-care-transition plugin instead. Guardrail: reads and cites sources only; never estimates, rounds or invents a fact.

★ 107
microsoft
microsoft/cat-agent-skills

section-plan

Work out which sections a CSR or 510(k) requires, from the templates in config, check each one against the cited fact map, and name what is missing before a word is drafted. Use when the user asks "what do we still need before we can draft the CSR?", "which sections are ready to start?", "what's blocking the performance data section?", "do we have everything for the synopsis?" or "map our tables to the E3 structure". Do NOT use for writing section language - use section-draft instead. Do NOT use for cross-checking a finished draft - use consistency-check instead. Do NOT use for outlining general Word documents or business reports - use the built-in docx skill instead. Only structures with a template in config are supported. Guardrail: plans only; never marks a section ready on a missing fact and never invents a structure.

文档处理
★ 107
microsoft
microsoft/cat-agent-skills

section-draft

Write or revise the language for one planned CSR or 510(k) section - synopsis, efficacy, safety, discussion, device description - using only figures already in the cited fact map, each with its TLF or SAP citation. Use when the user asks "draft the Synopsis from our locked tables", "write up safety from Table 14.3.1", "give me a first pass at the discussion", "draft the device description for the 510(k)" or "tighten the wording of the Discussion section". Do NOT use for supplying a number not already in source_facts - use source-ingest instead. Do NOT use for verifying a draft's figures - use consistency-check instead. Do NOT use for appeal letters, clinical notes or discharge summaries - use the matching HLS plugin instead. Guardrail: drafts for human approval only (L1); never asserts an unsourced number or harmonises two figures.

★ 107