agentleFS
LwhieldonLwhieldon/claude-project-mgmt-playbook/.claude/skills/exec-summary/SKILL.md

exec-summary

Skill4 starsChanged 33 days agoMITView on GitHub

Compress a long document (SOW, report, assessment, change request) into a one-page executive summary for a C-suite or board audience. Use when a decision-maker will not read the full document. Usage - /exec-summary path/to/document.md -- audience notes

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the whole document before summarizing.

    line 19
  2. Distinctive:

    Use concise, executive-level prose.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Executive Summary

Compress a long document into a tight one-page executive summary. Written for a C-suite or board audience who will not read the full document.

Input

$ARGUMENTS is the path to the document, optionally followed by audience context after --:

/exec-summary sample-projects/globex-erp-migration/sow.md -- audience is the CFO, focus on cost and timeline

Read the whole document before summarizing. If no path was given, ask for one.

Output

Executive Summary: [Document Title] Prepared for: [Audience if specified | Senior Leadership] Date: [Today's date]


Situation (2 to 3 sentences): What is this document about? What decision or context does it address?

Key Findings / What's in This Document:

  • 3 to 5 bullets covering the most important points
  • Lead with the "so what": not just what it says, but why it matters

Risks or Open Issues:

  • Top 2 to 3 risks, gaps, or items requiring attention or decision

Recommendations / Proposed Next Steps:

RecommendationOwnerTarget Date

Bottom Line: One sentence. If the reader remembers one thing from this document, it should be this.

Drafted with Claude Code on YYYY-MM-DD; reviewed by [NAME]


Use concise, executive-level prose. No jargon without explanation. Bullets 12 words or fewer. The total summary should fit on one printed page (roughly 350 to 450 words). Every figure in the summary must appear in the source document; do not round, extrapolate, or combine numbers.

Example Output

Executive Summary: Acme Corp Data Warehouse SOW Prepared for: CFO and Project Sponsor Date: May 8, 2025

Situation: This Statement of Work defines the scope, timeline, and pricing for a 6-month data warehouse modernization project. It replaces Acme's on-premise SQL Server environment with a cloud-based Snowflake platform to support faster reporting and analytics.

Key Findings:

  • Total contract value: $485,000 fixed-price
  • Go-live target: December 12, 2025 (assumes client data access by June 1)
  • Three workstreams: data migration, reporting layer, and user training

Risks or Open Issues:

  • Acceptance criteria are not defined; "fully functional" language creates ambiguity
  • Change control process is absent; any scope additions will require a CR process to be established

Bottom Line: The SOW is directionally sound but needs two additions before signing: defined acceptance criteria and a change control clause.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.