Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Stakeholder Communication Skill · a5c-ai | DecimalAI

a5c-ai/Stakeholder Communication

SkillScore91Maintained

Generate stakeholder-specific communications and presentations for product updates

productivityby a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Product Management pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/a5c-ai-stakeholder-communication/SKILL.md

decimalai skills pull a5c-ai-stakeholder-communication --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/a5c-ai-stakeholder-communication/SKILL.md https://app.decimal.ai/s/a5c-ai-stakeholder-communication/SKILL.md

Raw file: /s/a5c-ai-stakeholder-communication/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-stakeholder-communication.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 24d ago

Yes — +48% lift · at higher cost+28% tokens0% turns91% of whole cases pass with skill (21/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	38%	0%
case-05	✗→✓	▲ Improved	66%	0%
case-06	✗→✓	▲ Improved	53%	0%
case-09	✗→✓	▲ Improved	12%	0%
case-10	✗→✓	▲ Improved	44%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/specializations/product-management/skills/stakeholder-comms/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Skill contents

SKILL.md

Stakeholder Communication Skill

Overview

Specialized skill for generating stakeholder-specific communications and presentations. Enables product teams to create targeted communications that resonate with different audiences and maintain alignment.

Capabilities

Executive Communications

Generate executive summaries
Create board-level presentations
Build investor update templates
Create OKR progress reports
Generate strategic initiative updates

Sales and Customer Communications

Build sales-focused feature briefs
Create customer communications
Generate release notes
Build feature announcement templates
Create customer success updates

Internal Communications

Generate internal launch announcements
Build FAQ documents
Create status update templates
Generate cross-functional updates
Build team alignment documents

Presentation Artifacts

Create presentation outlines
Generate talking points
Build visual data summaries
Create demo scripts
Generate Q&A preparation docs

Target Processes

This skill integrates with the following processes:

stakeholder-alignment.js - All stakeholder communications
product-council-review.js - Review presentations
product-launch-gtm.js - Launch communications
quarterly-roadmap.js - Roadmap presentations

Input Schema

json
{
  "type": "object",
  "properties": {
    "communicationType": {
      "type": "string",
      "enum": ["executive-summary", "board-update", "sales-brief", "customer-announcement", "internal-update", "status-report", "faq"],
      "description": "Type of communication to generate"
    },
    "audience": {
      "type": "string",
      "enum": ["executive", "board", "sales", "customer", "engineering", "all-hands"],
      "description": "Target audience"
    },
    "content": {
      "type": "object",
      "properties": {
        "topic": { "type": "string" },
        "keyPoints": { "type": "array", "items": { "type": "string" } },
        "data": { "type": "object" },
        "context": { "type": "string" }
      }
    },
    "tone": {
      "type": "string",
      "enum": ["formal", "professional", "casual", "urgent"],
      "default": "professional"
    },
    "format": {
      "type": "string",
      "enum": ["document", "presentation", "email", "slack"],
      "default": "document"
    }
  },
  "required": ["communicationType", "audience", "content"]
}

Output Schema

json
{
  "type": "object",
  "properties": {
    "communication": {
      "type": "object",
      "properties": {
        "title": { "type": "string" },
        "summary": { "type": "string" },
        "body": { "type": "string" },
        "keyTakeaways": { "type": "array", "items": { "type": "string" } },
        "callToAction": { "type": "string" }
      }
    },
    "presentation": {
      "type": "object",
      "properties": {
        "slides": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "title": { "type": "string" },
              "content": { "type": "string" },
              "speakerNotes": { "type": "string" }
            }
          }
        },
        "talkingPoints": { "type": "array", "items": { "type": "string" } }
      }
    },
    "faq": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "question": { "type": "string" },
          "answer": { "type": "string" },
          "audience": { "type": "string" }
        }
      }
    },
    "metadata": {
      "type": "object",
      "properties": {
        "recommendedChannels": { "type": "array", "items": { "type": "string" } },
        "timing": { "type": "string" },
        "followUp": { "type": "array", "items": { "type": "string" } }
      }
    }
  }
}

Usage Example

javascript
const communication = await executeSkill('stakeholder-comms', {
  communicationType: 'executive-summary',
  audience: 'executive',
  content: {
    topic: 'Q1 Product Review',
    keyPoints: [
      'Launched 3 major features',
      'NPS improved by 15 points',
      'On track for ARR target'
    ],
    data: {
      featuresLaunched: 3,
      npsChange: 15,
      arrProgress: 0.85
    }
  },
  tone: 'professional',
  format: 'presentation'
});

Dependencies

Communication templates
Presentation formats

Illustrative Want to see what a5c-ai/Stakeholder Communication would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/29/2026, 21:36 UTC · 23 cases

Lift

+48%

91% vs 43%

Agent turns

0%

1.0 vs 1.0

Tokens

+28%

3,566.3 vs 2,789.52

fail → pass · 11pass → pass · 10fail → fail · 2

Per-case results (23)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 We need to brief our leadership board on the progress of the Q3 enterprise roadmap. Can you assemble a detailed communication structure for us? Make sure the output contains a core document object with a title, summary narrative, body text, key takeaways, and a call to action, alongside a presentation breakdown with slide contents, speaker notes, and talking points. Please also include metadata regarding recommended channels, timing, and follow-up steps.	fail→fail	31,919	19,835	-38%	1	1	0%	5,345	4,145	-22%	0	0	—
case-02 Our sales team needs an enablement update on the upcoming AI feature package to help them pitch to key prospects. Please draft a communication output that includes a clear title, brief summary, main content body, key takeaways, and actionable next steps. Additionally, provide a list of common questions and answers for sales reps, as well as channel and timing recommendations in the metadata.	fail→pass	15,148	12,782	-16%	1	1	0%	2,422	3,352	+38%	0	0	—
case-03 I need to issue an urgent update to our engineering team regarding a critical infrastructure migration schedule change. Please generate a full stakeholder communication structure containing a formal update message (title, summary, detailed body, key takeaways, call to action), a set of presentation slides with titles, content, speaker notes, and talking points, plus metadata specifying follow-up actions and suggested channels.	fail→fail	30,500	13,408	-56%	1	1	0%	5,497	3,447	-37%	0	0	—
case-04 We are preparing our Q2 OKR progress report for C-level leadership regarding our FinTech payment platform. Someone suggested outputting raw Slack messages with casual tone. Produce the JSON payload matching the expected output schema with professional executive framing.	pass→pass	11,959	17,579	+47%	1	1	0%	2,381	4,412	+85%	0	0	—
case-05 We are presenting our API security redesign to the Product Council for review. Provide the output JSON structure including communication and presentation objects. We want to avoid informal conversational text.	fail→pass	10,808	12,544	+16%	1	1	0%	2,036	3,382	+66%	0	0	—
case-06 Draft an update for our enterprise Cloud Storage overhaul initiative. We need to distribute this across internal executive channels. Provide JSON containing the communication section and publication metadata.	fail→pass	11,997	9,360	-22%	1	1	0%	1,855	2,845	+53%	0	0	—
case-07 Our SaaS CRM product is launching v4.2 with automated pipeline routing. We need a customer-facing announcement output. Make sure the output is structured JSON.	pass→pass	7,786	11,127	+43%	1	1	0%	1,456	3,128	+115%	0	0	—
case-08 Generate an internal Slack announcement for the deployment of our new telemetry pipeline targeting all-hands. Supply structured JSON with communication and metadata objects.	pass→pass	11,176	10,345	-7%	1	1	0%	2,111	3,059	+45%	0	0	—
case-09 Create a product launch FAQ document for our upcoming micro-frontend architecture rollout targeted at engineering teams. Return the JSON structure.	fail→pass	18,471	16,917	-8%	1	1	0%	3,448	3,869	+12%	0	0	—
case-10 Prepare an investor update output for our Series B milestone in the Logistics AI product line. Ensure it is formatted as JSON with structured communication and metadata.	fail→pass	17,073	13,776	-19%	1	1	0%	2,593	3,738	+44%	0	0	—
case-11 Generate a sales-focused feature brief for the new automated compliance auditing module in our Security Suite. Ensure the output is structured JSON.	fail→pass	12,628	19,514	+55%	1	1	0%	2,393	4,190	+75%	0	0	—
case-12 Generate a weekly status report for the Cross-Functional Payments Migration squad targeting engineering and product leads. Return a JSON structure.	pass→pass	15,709	12,036	-23%	1	1	0%	2,522	3,467	+37%	0	0	—
case-13 Create a cross-functional alignment document structure in JSON for the Data Platform team's transition to real-time streaming.	fail→pass	18,621	15,874	-15%	1	1	0%	3,387	3,921	+16%	0	0	—
case-14 We need a demo script and Q&A prep doc for our upcoming Product Showcase on the new search indexer. Output the JSON structure containing presentation slides, talking points, and FAQ items.	pass→pass	17,191	18,501	+8%	1	1	0%	3,002	4,035	+34%	0	0	—
case-15 Assemble the roadmap presentation output JSON for the annual Q1 roadmap sync across all product lines.	fail→pass	24,779	22,172	-11%	1	1	0%	5,120	4,423	-14%	0	0	—
case-16 Draft a customer success health update structure in JSON for our high-touch enterprise accounts regarding platform uptime improvements.	fail→pass	18,786	13,603	-28%	1	1	0%	2,936	3,732	+27%	0	0	—
case-17 Generate an urgent status update JSON for all internal engineering staff regarding an immediate mandatory zero-day library patch.	pass→pass	10,056	13,926	+38%	1	1	0%	1,952	3,126	+60%	0	0	—
case-18 Prepare a quarterly board update JSON output summarizing growth metrics for our Healthcare SaaS platform.	fail→pass	13,303	14,706	+11%	1	1	0%	2,521	3,783	+50%	0	0	—
case-19 Build a launch readiness update JSON payload for the Mobile Banking App release targeting all internal teams.	fail→pass	21,180	16,619	-22%	1	1	0%	3,428	4,146	+21%	0	0	—
case-20 We need to re-prioritize our backlog tickets for the search indexing service using RICE scoring (Reach, Impact, Confidence, Effort). Ticket A-101 has Reach=800, Impact=3, Confidence=80%, Effort=2. Ticket A-102 has Reach=2000, Impact=2, Confidence=50%, Effort=1. Which ticket should be prioritized first?	pass→pass	7,030	6,439	-8%	1	1	0%	1,212	2,340	+93%	0	0	—
case-21 Write a user story with Given-When-Then acceptance criteria for a user resetting their password via email link on our e-commerce site.	pass→pass	11,257	11,640	+3%	1	1	0%	2,139	3,455	+62%	0	0	—
case-22 Write an SQL query for PostgreSQL to compute 30-day user retention cohort breakdown from our active_users table with columns user_id and active_date.	pass→pass	16,004	11,388	-29%	1	1	0%	3,191	3,742	+17%	0	0	—
case-23 Our sprint velocity over the last 4 sprints was 32, 28, 35, and 31 story points. Calculate the average velocity and estimate how many sprints are required to complete a 150-point backlog.	pass→pass	7,368	6,491	-12%	1	1	0%	1,212	2,288	+89%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +48 percentage points is the difference between those two pass rates over the 23 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 43.5%
Pass rate with the skill: 91.3%
Cases attempted: 23
Cases counted toward lift: 23
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/29/2026, 21:36 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-02

Prompt

Our sales team needs an enablement update on the upcoming AI feature package to help them pitch to key prospects. Please draft a communication output that includes a clear title, brief summary, main content body, key takeaways, and actionable next steps. Additionally, provide a list of common questions and answers for sales reps, as well as channel and timing recommendations in the metadata.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run91

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+56% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 23 days ago

Other measured skills in the registry, with their headline benchmark lift.