executive-summary
Skill2 starsChanged 3 months agoMITView on GitHub
Distills a question/topic from quantitative survey data (CSV) for leadership: a one-pager with a TL;DR, 3–5 key findings each with a number and an implication, and next steps. Result as Markdown to reports/. Use when results need to be condensed for an executive / stakeholder audience. Invoke with your request as the argument, e.g. /executive-summary <question/topic>.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- jonmagic/skillstheir own version, first seen Nov 8, 2026
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- microsoft/aibast-agents-librarytheir own version, first seen Oct 13, 2026
- SkillMedev/document-studiotheir own version, first seen Oct 5, 2026
- poorvith-mp/skills-writingtheir own version, first seen Aug 19, 2026
- zrosenfield/sharepoint-ai-skillstheir own version, first seen Aug 4, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- zrosenfield/sharepoint-ai-skills★ 96same name
- devstefancho/skills★ 13same name
- microsoft/aibast-agents-library★ 8same name
- jonmagic/skills★ 6same name
- Nomanriaz786/claude-consulting-team★ 1same name
- SkillMedev/document-studio★ 1same name
- CAPP-Financials/Consulting_Brain★ 0same name
- poorvith-mp/skills-writing★ 0same name
- sted9000/claude-skills★ 0same name
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 repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- data-checkSkill
- daten-checkSkill
- decision-briefSkill
- entscheidungsvorlageSkill
- freitext-themenSkill
- hypothese-checkSkill
- hypothesis-checkSkill
- management-summarySkill
- segment-profileSkill
- segment-profilSkill
- survey-contextSkill
- survey-reportSkill
- umfrage-kontextSkill
- umfrage-reportSkill
- verbatim-themesSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Run these from the project root.
- Very specific: line 33
If a context document sits next to the CSV (<name>.context.md, or survey-context.md when the folder holds exactly one CSV), read it first.
- Distinctive: line 83
Every key finding carries a concrete number (absolute + %).
“Common” is measured: kept by at least 6 in 10 of the 8 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
Executive Summary
Goal: For the topic named in the user's request, produce a
decision-oriented one-pager for leadership/stakeholders — condensed, implication-led,
without methodological ballast. Result as Markdown in reports/.
Tool
python3 scripts/survey.py <cmd> [...] [--file CSV]Run these from the project root. If scripts/survey.py is not there, check .claude/scripts/survey.py or locate survey.py in the project.
profile— column overview (always first).freq COL [--by COL2] [--filter "COL=VALUE"] [--sig]— distribution/cross-tab (+significance).text COL [--filter ...] [--sample N]— free text for one crisp verbatim quote.
COL = index (from profile) or an unambiguous name part.
Survey context
If a context document sits next to the CSV (<name>.context.md, or survey-context.md
when the folder holds exactly one CSV), read it first. Two parts of it matter most here:
the audience (who reads this and what they decide with it — pitch the one-pager at
them) and the subject/glossary (so the summary uses the reader's own words, not the
column wordings). Figures still come only from the engine.
This format has no method section, which makes it the easiest place to lose the study design — so keep one thing: if the recruiting route materially qualifies the message (the "Who is missing" section), say so in half a sentence where it belongs, not in a separate block. "Among active users surveyed via the app, 71% …" costs four words and stops a leadership audience from reading a partial picture as the whole one.
Expectations listed in the document are something to test, never something to support —
a summary must not become the confirmation someone was hoping for. If no such document
exists, proceed as before and mention survey-context once at the end.
Approach
- Profile, then translate the topic into the 2–4 most telling analyses — that count
is on top of
profile, which is the mandatory first step, not one of them. - Analyze and pull the most important numbers. Less is more — one solid number per key finding.
- Condense to implications. For each finding ask: "So what? What does it mean for the business/product/users?" That is what goes into the summary.
- Save the report to
reports/(date +%F+ kebab title, never overwrite) and give the TL;DR + path in your reply.
Report format (max one page)
# <topic as a meaningful heading>
**Data basis:** <file> · n = <…> · <date>
## TL;DR
2–4 sentences carrying the central message. Most important first.
## Key findings
1. **<finding>** — <number absolute + %>. *Implication:* <what it means>.
2. …
(3–5 findings, each a number + implication, one line each)
## Recommendation / next steps
2–3 concrete, prioritized steps.
<optional: one crisp verbatim user quote if it reinforces the message>Rules
- Short and implication-oriented — leadership reads messages, not tables. One screen max.
- Every key finding carries a concrete number (absolute + %). No vague statements.
- Drop jargon and method detail (at most one line "Basis: n=…").
- Claim nothing the data doesn't support; note uncertainty in half a sentence — including who the survey could not reach, when that changes how the message should be read.
- Report language = language of the request (default English).
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.

