stakeholder-communication

Skill: Stakeholder Communication Matrix

Purpose

Adapt analytical findings to the audience — same insight, different framing, detail level, and format depending on who will read it. Ensures that executives get the bottom line, PMs get the implications, engineers get the specifics, and data teams get the methodology.

When to Use

Apply this skill when producing a narrative (Storytelling agent), creating a deck (Deck Creator agent), or whenever the user specifies an audience. If no audience is specified, default to Product Team format.

Instructions

Pre-flight: Load Learnings

Before executing, check .knowledge/learnings/index.md for relevant communication preferences:

1. Try to read the file: Use the Read tool on .knowledge/learnings/index.md
2. If it exists, scan for entries under these headings:
   • "Communication" - stakeholder preferences, formatting conventions
   • "General" - cross-cutting preferences that apply to all work
   • "Stakeholder Preferences" - audience-specific guidance
3. If it doesn't exist or is empty, skip silently and proceed with standard stakeholder matrix
4. If entries exist, incorporate them as constraints (e.g., "VP prefers 1-page summaries", "always include confidence grades for data team")
5. Never block execution if learnings are unavailable - this is an enhancement, not a blocker

Example learnings that would apply:

• "Executive team prefers dashboards over text reports"
• "Product team wants effort estimates in days, not story points"
• "Data team requires p-values for all statistical claims"

The Stakeholder Matrix

Different audiences care about different things. For the same finding, adapt:

Dimension	Executive	Product Team	Engineering	Data Team
Lead with	Business impact ($, users, risk)	What to do about it (action)	What's broken and where (specifics)	How we found it (methodology)
Detail level	Bottom line + 1 supporting fact	Findings + implications + next steps	Root cause + technical details + fix scope	Methodology + data quality + caveats
Format	3 slides max / 1-paragraph summary	Analysis report with charts	Investigation log with queries/code	Full report with validation section
Metrics language	Revenue, users, growth rate	Conversion, retention, engagement	Error rate, latency, success rate	Statistical significance, confidence intervals
Time horizon	This quarter / this year	This sprint / this month	This release / this deploy	This analysis / this dataset
Charts	1-2 high-level (big number, trend)	3-5 focused (funnel, segmentation)	Technical plots (timelines, error logs)	Distribution, correlation, validation
Caveats	Only if they change the recommendation	Noted alongside findings	Noted with technical implications	Full methodology section
Recommendation style	"We should X" (decisive)	"I recommend X because Y" (reasoned)	"The fix is X, effort is Y" (scoped)	"The data supports X with caveats Y" (qualified)