Purpose
Convert a raw list of sustainability topics and stakeholder groups into a defensible, ranked materiality dataset — scoring every topic on stakeholder importance and business impact using a transparent weighting method — so the sustainability team can plot a materiality matrix and justify topic prioritization to auditors, leadership, and GRI reviewers without ad-hoc guesswork.
When to Use
Invoke this skill when the user asks to:
- Prioritize or rank sustainability/ESG topics for a materiality assessment
- Build the input data or scoring for a materiality matrix
- Run a GRI-aligned stakeholder engagement and topic-weighting process
- Decide which ESG topics are "material" for a sustainability report
- Reconcile conflicting stakeholder priorities into a single ranked list
- Apply double materiality (impact + financial) scoring to a topic set
Inputs Required
Before starting, collect:
- Sustainability topics: The list of topics/issues to assess (e.g., GHG emissions, water use, labor practices, data privacy)
- Stakeholder groups: The groups being represented (e.g., investors, employees, customers, regulators, communities, suppliers)
- Stakeholder weights: Relative influence of each group (or leave blank to weight equally)
- Company context: Sector, size, and geography — needed to calibrate business impact
- Engagement inputs: Any survey scores, interview notes, or ranking data per group (or note that qualitative estimates should be used)
- Materiality approach: Single materiality (stakeholder view) or double materiality (impact + financial); default to double
- Reporting framework: GRI, ESRS/CSRD, SASB, or other alignment target; default to GRI
If stakeholder weights or engagement data are missing, weight groups equally, estimate scores from company context, and clearly flag each estimate as an assumption to be validated.
Instructions
Step 1: Confirm the Scoring Model
Establish the two axes before scoring anything.
- Axis A — Stakeholder Importance (outward view): How much each stakeholder group cares about the topic. Scored 1–5 per group, then combined into a weighted average using stakeholder weights.
- Axis B — Business Impact (inward view): How much the topic affects the company's ability to create or erode value — risk, cost, revenue, license to operate, resilience. Scored 1–5.
- If double materiality is selected, split Axis B into Impact Materiality (effect on people/environment) and Financial Materiality (effect on enterprise value), each scored 1–5, then take the higher of the two per ESRS logic. Note which driver dominates.
- State the 1–5 scale anchors explicitly: 1 = negligible, 2 = minor, 3 = moderate, 4 = significant, 5 = critical.
Step 2: Score Stakeholder Importance Per Topic
For each topic, score every stakeholder group 1–5, then aggregate.
- Use provided engagement/survey data where available; otherwise estimate from the group's known priorities and company context, marking estimates as assumptions.
- Apply stakeholder weights: Weighted Importance = Σ(group score × group weight) ÷ Σ(weights). If weights are equal, this is a straight average.
- Record the highest- and lowest-scoring group per topic to expose divergence.
Step 3: Score Business Impact Per Topic
For each topic, score 1–5 on business impact (or on Impact + Financial if double materiality).
- Anchor scores to concrete drivers: regulatory exposure, cost/revenue linkage, operational dependency, reputational risk, and long-term resilience.
- For double materiality, note whether Impact or Financial materiality is the binding constraint for each topic.
- Calibrate to sector: a topic critical in one industry may be minor in another — use company context to justify each score.
Step 4: Compute Composite Priority and Rank
Combine the two axes into a single ranking.
- Composite Score = (Weighted Stakeholder Importance + Business Impact) ÷ 2, reported to one decimal. Keep the two axis scores visible so the matrix can be plotted.
- Rank all topics from highest to lowest composite score.
- Break ties in favor of the topic with the higher Business Impact score (financial/operational risk takes precedence in tie situations).
Step 5: Assign Materiality Quadrants
Map each topic to a matrix quadrant using a 3.0 threshold on each axis.
- Priority / Material (Importance ≥ 3.0 AND Impact ≥ 3.0): Report-in-full, manage actively.
- Monitor — Stakeholder-Driven (Importance ≥ 3.0, Impact < 3.0): Watch and disclose; may rise in importance.
- Monitor — Business-Driven (Importance < 3.0, Impact ≥ 3.0): Manage internally; communicate proactively.
- Low Priority (both < 3.0): Note only; no active disclosure required.
Step 6: Flag Divergences and Assumptions
Surface where the analysis needs human validation.
- List every topic with high stakeholder–business divergence (axis gap ≥ 1.5) — these are the discussion points for the next engagement round.
- List all scores derived from estimates rather than data.
- Note any topic likely to shift in a re-assessment (emerging regulation, changing sentiment).
Output Format
- Structure: A ranked scoring table for all topics, followed by quadrant assignments and a divergence/assumptions section
- Length: 700–1,100 words plus the tables (scales with topic count)
- Format: Primary output is a table; supporting analysis in structured bullets
- Sections: Scoring model summary → Master scoring table (Topic | Weighted Stakeholder Importance | Business Impact | Composite | Rank | Quadrant) → Quadrant groupings → Divergence & assumptions flags → Recommended material topic list for reporting
- Tone: ESG analyst — methodical, evidence-anchored, audit-ready; every score defensible, no vague qualifiers
Quality Checklist
Before delivering output, verify:
- [ ] Every topic provided has a stakeholder importance score, a business impact score, a composite, a rank, and a quadrant
- [ ] Stakeholder weights are applied consistently (or equal weighting is explicitly stated)
- [ ] All 1–5 scores map to the stated scale anchors — no scores outside 1–5
- [ ] Composite scores are correctly averaged and ranking order matches the scores
- [ ] Quadrant assignments correctly follow the 3.0 threshold rule on both axes
- [ ] Every estimated (non-data) score is flagged as an assumption to validate
Notes
- The output is decision-support input, not a final materiality determination — the "Priority / Material" list should be reviewed and signed off by stakeholders before publication.
- For GRI alignment, the ranked list feeds directly into identifying material topics and their boundaries; for CSRD/ESRS, double-materiality scoring supports the impact-and-financial screening required by the standard.
- Divergence flags (axis gap ≥ 1.5) are the most valuable output for engagement planning — they show exactly where stakeholder expectations and business reality disagree.
- Re-run this skill each reporting cycle; comparing composite scores year-over-year reveals shifting materiality trends.
How to use this skill
This file is a Claude Code skill in Anthropic's standard format — markdown with YAML frontmatter at the top.
Installing in Claude Code:
~/.claude/skills/<folder-name>/SKILL.md— auto-loads in every session anywhere on your machine (recommended for skills you'll use across multiple projects)<your-project>/.claude/skills/<folder-name>/SKILL.md— auto-loads only when working in that project (recommended for project-specific skills)
Restart Claude Code or open a new session to register.
Using in Claude.ai, ChatGPT, Gemini, or other AI tools:
- Drag this file into a new chat, or copy and paste its contents
- Send your task or request as your next message — the AI will apply the skill where it fits
For Claude Code skill details: https://docs.anthropic.com/en/docs/claude-code/skills