# Executive Summary Writer

> Writes an executive summary for a longer report or proposal. Distills to: what happened, what it means, what's next.

- **Type:** Skill
- **Install:** `agentstack add skill-nicholashidalgo-claude-skillforge-technical-to-business-summarizer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [nicholashidalgo](https://agentstack.voostack.com/s/nicholashidalgo)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [nicholashidalgo](https://github.com/nicholashidalgo)
- **Source:** https://github.com/nicholashidalgo/claude-skillforge/tree/main/writing/technical-to-business-summarizer

## Install

```sh
agentstack add skill-nicholashidalgo-claude-skillforge-technical-to-business-summarizer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# executive-summary-writer

**Purpose:** Take a full report or document and synthesize it into a 150-300 word executive summary that a decision-maker can act on without reading the full document.

## Input Schema

| Field | Type | Required |
|---|---|---|
| `source_title` | string | yes |
| `source_content` | string | yes - full document or long excerpt |
| `audience` | string | yes |
| `key_findings` | string[] | yes - top 3-5 findings to surface |
| `recommended_actions` | string[] | yes |
| `preserve_facts` | string[] | yes |

```json
{
  "source_title": "Q1 2024 Platform Engineering Report",
  "source_content": "...",
  "audience": "VP Engineering",
  "key_findings": ["CI build time improved 60%", "On-call volume down 40%", "2 critical infra migrations completed"],
  "recommended_actions": ["Approve Q2 headcount for observability", "Extend Kubernetes rollout to remaining 12 services"],
  "preserve_facts": ["60%", "40%", "12 services", "Q1 2024"]
}
```

## Output Schema

```json
{
  "title": "Executive Summary: Q1 2024 Platform Engineering",
  "summary": "...",
  "findings": ["..."],
  "recommended_actions": ["..."],
  "word_count": 215
}
```

## Prompt Flow

**Pass 1:** Three-part structure: What happened (findings), What it means (interpretation in 1-2 sentences), What's next (recommended actions). Remove: P1, P3, P4, P5, P6, P7, P14, P15, P22, P23, P24. Preserve all facts.

**Pass 2:** "What in this summary is padding?" -> cut aggressively to under 300 words. Every sentence must do work.

## Examples

### Short - findings sentence
**Before:** "The platform team has made significant strides, showcasing their commitment to fostering a culture of continuous improvement that underscores their vital role in the organization's evolving landscape."
**After:** "CI build time dropped 60% in Q1; on-call volume fell 40%."

### Medium - full summary
**Before:** "In conclusion, the future looks bright for our platform infrastructure. Exciting times lie ahead as we continue this journey toward excellence and scalability."
**After:** "Q1 work shipped two critical migrations and cut on-call load nearly in half. Q2 priority: extend Kubernetes to the remaining 12 services and hire 2 observability engineers to avoid repeating the January monitoring gap."

### Long

## Unit Tests

```python
# tests/skills/test_executive_summary_writer.py
from ai_pattern_scrubber import detect_patterns

FINDING = "CI build time dropped 60% in Q1; on-call volume fell 40%."
CLOSE = "Q2 priority: extend Kubernetes to 12 services and hire 2 observability engineers."

def test_finding_no_significance_inflation():
    assert not [h for h in detect_patterns(FINDING) if h.id == 1]

def test_close_no_generic_conclusion():
    assert not [h for h in detect_patterns(CLOSE) if h.id == 24]

def test_finding_no_high_severity():
    assert not [h for h in detect_patterns(FINDING) if h.severity == "high"]
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [nicholashidalgo](https://github.com/nicholashidalgo)
- **Source:** [nicholashidalgo/claude-skillforge](https://github.com/nicholashidalgo/claude-skillforge)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-nicholashidalgo-claude-skillforge-technical-to-business-summarizer
- Seller: https://agentstack.voostack.com/s/nicholashidalgo
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.