one-pager
Skill2 starsChanged 7 months agoMITView on GitHub
Turn raw notes, transcripts, or longform content into a tight one-page executive brief. Use whenever the user wants a one-pager, exec brief, briefing doc, or asks to compress longer content into a structured one-page summary. Triggers on phrases like "write a one-pager", "make this a brief", "summarize for an exec", "turn these notes into a brief", or when the user uploads notes or meeting transcripts and wants a tight structured summary. Always use this skill rather than free-form summarizing when the user asks for a "brief" or "one-pager", even if they do not say "use the one-pager skill".
13 other projects use a version of this.
Adopted by
Most recently taken up by
- CSPulse/customer-success-skillstheir own version, first seen Nov 8, 2026
- Sach1ng/PM-operating-OStheir own version, first seen Nov 1, 2026
- plannotator/effective-htmltheir own version, first seen Nov 1, 2026
- backnotprop/brotheir own version, first seen Nov 1, 2026
- JScottCarter/Claude_skillstheir own version, first seen Oct 11, 2026
- youdcode/open-companytheir own version, first seen Sep 21, 2026
Other versions13 projects use a version of this.
Word for word · 1
- 0xelitesystem/claude-skills-templates★ 2100% same
Edited · 0
None found.
Wrote their own version · 12
- plannotator/effective-html★ 3.8ksame name
- backnotprop/bro★ 176same name
- GTMify/aigtm★ 25same name
- Sach1ng/PM-operating-OS★ 3same name
- CSPulse/customer-success-skills★ 2same name
- ouachitalabs/skills★ 2same name
- youdcode/open-company★ 2same name
- ianklassen/ai-pm-system★ 1same name
- jingjing-yxng/claude-skills★ 0same name
- JScottCarter/Claude_skills★ 0same name
2 more not listed
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 repository4 other files it gives its agents.
- brand-voiceSkill
- code-reviewerSkill
- csv-cleanerSkill
- decision-docSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Always use these five sections in this order.
- Distinctive: line 36
No em-dashes. Use commas, semicolons, or split into two sentences.
- Distinctive: line 37
No filler openings. Skip "In today's...", "It is worth noting that...", "When it comes to...".
- Distinctive: line 38
No banned vocabulary: delve, leverage as a verb, seamless, robust for non-statistical claims, navigate the landscape, paradigm shift, …
- Very specific: line 45
If the source content is too thin to fill all five sections honestly, do not invent content.
“Common” is measured: kept by at least 6 in 10 of the 12 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.
Files
One-Pager Writer
Converts raw input (notes, transcripts, source articles, research dumps) into a structured one-page brief.
Output structure
Always use these five sections in this order.
TL;DR
One sentence. The headline finding or recommendation. If the reader stops here, they should know what changed.
Context
Two to four sentences. What prompted this? What is the reader supposed to know to make sense of the rest?
Findings
Three to five bullets. Each is a specific, sourced claim. If a claim has a number, include the number. If it has a source, attribute it.
Recommendation
One paragraph. What should the reader do, decide, or believe? If there is a decision to make, state it. If the recommendation is conditional, state the condition.
Next Steps
Three to five concrete actions, each with an owner placeholder if known. Each action should be doable in a week or less.
Style rules
- No em-dashes. Use commas, semicolons, or split into two sentences.
- No filler openings. Skip "In today's...", "It is worth noting that...", "When it comes to...".
- No banned vocabulary: delve, leverage as a verb, seamless, robust for non-statistical claims, navigate the landscape, paradigm shift, journey as a metaphor, unlock the power, harness the power, foster as a verb.
- Concrete over abstract. "Revenue rose 18% in Q3" beats "significant revenue growth was observed".
- Active voice. Name the actor.
- Length cap: roughly 350 words total. If you exceed it, cut bullets, not sections.
When you do not have enough input
If the source content is too thin to fill all five sections honestly, do not invent content. Mark the thin section with [needs input: <what is missing>] and ask the user one specific question per gap.
Output format
Render as plain markdown. Section headings as ###. No tables unless the user asks for one. No code blocks unless the source contains code worth quoting.
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
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.