agentleFS
Sign inStart free
its-janghoonits-janghoon/agent-skills/skills/exec-one-pager/SKILL.md

exec-one-pager

Skill0 starsChanged 2 months agoApache-2.0View on GitHub

English executive or startup one-pager as .docx (problem, solution, product, market, GTM, kill/go, timeline). For one-pager, exec brief, or pitch brief. Not for Korean 정부지원 사업 요약서 (use gov-one-pager).

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. savagemanage/claude-skills★ 0100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask only for missing must-haves.

    line 26
  2. Very specific:

    Run npm install docx --no-save if needed, then node report_generator.js.

    line 29
  3. Distinctive:

    Always include Product for new ventures or products.

    line 42
  4. Distinctive:

    Prefer plain nouns and verbs.

    line 47
  5. Distinctive:

    No em dashes (—). Use a hyphen (-) or a plain sentence.

    line 49
  6. Distinctive:

    Put superscripts on numbers and hard claims.

    line 51
  7. Very specific:

    When the chat already has enough content, fill this privately and write DATA directly (do not make the user paste the skeleton back):

    line 67
  8. Distinctive:

    Do not edit the style engine below the marker comment.

    line 86
  9. Very specific:

    If Calibri is missing, change only the FONT constant.

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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 one-pager

Produce a single-page English .docx brief in label/content table form: startup or corporate exec summary, not a Korean government 요약서.

When to use

  • "Create a one-pager", "exec brief", "pitch one-pager", "one-page summary"
  • English product / market / ask framing without 사업계획서 or 정부지원 cues
  • Reusing the sample table structure for a new topic

For Korean government-style 요약서 / 추진계획(안), use the gov-one-pager skill instead.

Quick workflow

  1. Map user material into the 11 label rows below using the style and fill rules. Ask only for missing must-haves; otherwise draft and note assumptions briefly.
  2. Copy scripts/report_generator.js into the working directory.
  3. Replace only the top-level DATA object (leave the style engine untouched).
  4. Run npm install docx --no-save if needed, then node report_generator.js.
  5. Deliver the .docx to the user.

Format rules

  • Output: one Letter page .docx. If it overflows, cut sentences and compress tables.
  • One main table: left labels, right content.
  • Title on one line with a double underline beneath.
  • Label column: light gray fill, bold, centered.
  • Nested tables: dark header row, white body.
  • Font: Calibri throughout; title bold only.
  • Label order: Opportunity, Summary, Problem, Why now, Solution, Product, Market, Go-to-market, Kill / Go, Timeline, Sources.
  • Always include Product for new ventures or products.

Style rules

  • Short bullets; one fact per line.
  • Prefer plain nouns and verbs; cut hype and filler adjectives.
  • No "not A but B" contrast openers.
  • No em dashes (—). Use a hyphen (-) or a plain sentence.
  • Spare use of quotation marks for emphasis.
  • Put superscripts on numbers and hard claims; list matching sources in Sources.
  • Mark market figures as estimates in Sources.

Fill guidance

  • Summary: at most 4 lines — problem, cause, approach, beachhead.
  • Problem: at most 4 facts.
  • Solution: 3-column nested table (Track / What / Outcome), plus one guardrail line.
  • Product: 2-column nested table (Step / What) for the user flow; one line under for platform, stack, and first users.
  • Market: TAM / SAM / SOM nested table.
  • Kill / Go: two-column nested table.
  • Sources: short citations only.

Intake skeleton

When the chat already has enough content, fill this privately and write DATA directly (do not make the user paste the skeleton back):

- Topic:
- Problem:
- Why now:
- Solution:
- Product (user-flow steps; platform / stack):
- Market (TAM / SAM / SOM):
- Go-to-market:
- Kill / Go:
- Timeline:
- Sources:

Script (scripts/report_generator.js)

  • Edit only DATA, then node report_generator.js (npm install docx required).
  • Do not edit the style engine below the marker comment.
  • Citations: { line: "...", sup: 1 } plus matching Sources rows.
  • Nested tables: { table: { widths, header, body } }.
  • m = bullet glyph, label = bold step label, size = font half-points (default 20).
  • Sample DATA is fictional; replace all of it for real topics.
  • If Calibri is missing, change only the FONT constant.

Pre-delivery checklist

  • All 11 labels in order (Product included)
  • Sample DATA fully replaced
  • No em dashes
  • Claims/numbers have superscripts with Sources matches
  • Market estimates called out in Sources
  • Fits one Letter page

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.

Check your setup, free