business-intelligence
Skill0 starsChanged 4 months agoMITView on GitHub
Use when research or data findings need to be turned into a decision-ready insight for a business audience — e.g. "what does this mean for us", "should we do X based on this", or preparing findings for executives. Ensures insights connect to organizational priorities, not just interesting facts.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- darker2016/WorkbuddySkillGroups4DSHtheir own version, first seen Aug 14, 2026
- RanNahmany/mamad-challenge-skillstheir own version, first seen Mar 6, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- RanNahmany/mamad-challenge-skills★ 7same name
- darker2016/WorkbuddySkillGroups4DSH★ 6same 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 repository9 other files it gives its agents.
- agent-architecture-advisorSkill
- compliance-reviewSkill
- data-correlationSkill
- document-analysisSkill
- extractionSkill
- financial-analysisSkill
- legal-contract-reviewSkill
- research-methodologySkill
- trace-analysisSkill
The file
Files
Business intelligence
Turns findings (research, data analysis, correlations) into insight an executive or decision-maker can act on. The playbook's research-agent example treats this as the last-mile skill: gathering data isn't the same job as making it useful.
Workflow
- Lead with the so-what, not the methodology. State the actionable insight in the first sentence. Save the "how we found this" for supporting detail underneath.
- Connect explicitly to a decision or priority. An insight that doesn't change what someone would do isn't decision-ready yet — ask "what would this change?" and answer it.
- Quantify the stakes. Where possible, frame impact in terms the audience already tracks (revenue, time, risk, headcount) rather than in the units the raw data came in.
- Give a recommendation with a confidence level. "Recommend X (high confidence — three independent sources agree)" is more useful than a bare recommendation or a bare data dump.
- Surface the strongest counterargument. A decision-maker will find the hole in your reasoning if you don't; naming it first builds more trust than omitting it.
- Keep it to one page of substance. Executive audiences want the top 3-5 points, not the full analysis — link to supporting detail rather than inlining it.
Composition
Typically the last step after research-methodology and/or data-correlation have produced the underlying findings — this skill doesn't gather data itself, it reframes what's already been found.
Quality bar
- The first sentence states an actionable insight, not a topic.
- Impact is quantified in terms the audience tracks, not just the raw metric.
- A confidence level and its basis are stated.
- At least one counterargument or risk is named.
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.