agentleFS
nickstellarstreamainickstellarstreamai/ai-opportunity-finder/skills/opportunity-scanner/SKILL.md

opportunity-scanner

Skill11 starsChanged 9 months agoMITView on GitHub

Generate AI opportunity hypotheses for your company. Identifies where AI and automation can save time, reduce errors, and create competitive advantages based on your industry, company size, and known pain points. Use when starting an AI discovery initiative or when you need a structured starting point for finding AI opportunities.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    When you run this skill, I'll ask you a few questions about your company, then generate a structured hypothesis document you can use to …

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

AI Opportunity Scanner

Generates 3-5 testable AI opportunity hypotheses for your organization based on industry patterns, company size, and known challenges. This is Step 1 of the Discovery Sprint methodology — giving you a structured starting point instead of "where do we even begin?"

How It Works

When you run this skill, I'll ask you a few questions about your company, then generate a structured hypothesis document you can use to guide interviews, audits, and deeper investigation.

What I Need From You

Provide the following (I'll ask for anything missing):

  1. Company name
  2. Industry (e.g., Healthcare, Manufacturing, Professional Services, Retail, Finance, Technology, etc.)
  3. Company size (approximate employee count)
  4. 2-5 known challenges or pain points (what keeps leadership up at night?)
  5. Key departments to focus on (optional — if you already know where the biggest problems are)

What You'll Get

A Hypothesis Document containing:

For Each Hypothesis (3-5 total):

HYPOTHESIS: We believe that [DEPARTMENT/FUNCTION] spends significant time on
[ACTIVITY] which could be [AUTOMATED/AUGMENTED] using [AI APPROACH],
resulting in [ESTIMATED IMPACT].

VALIDATION METHOD:
- Who to interview: [Roles/people]
- Questions to ask: [Specific questions]
- Data to collect: [Metrics to validate]

CONFIDENCE: [High/Medium/Low] based on industry pattern strength
POTENTIAL IMPACT: [Hours/year saved or $ value range]

Plus:

  • Interview Priority List — Who to talk to first, organized by the U-shaped method (executives first, then frontline, then back to executives)
  • Pattern Alerts — Common patterns your industry typically exhibits (so you know what to watch for)
  • Quick Win Candidates — 1-2 hypotheses most likely to yield fast, visible results

Industry Pattern Library

I draw on validated patterns seen across multiple organizations:

PatternDescriptionIndustries Where Common
Data Without InsightsLots of data in tables/systems but no synthesis into actionable intelligenceAll industries with data teams
Manual Scheduling CascadeSchedule changes require manual updates across multiple people/systemsOperations-heavy, multi-department
Report Assembly LineSame information reformatted for different audiences manuallyAny org with reporting requirements
Institutional Knowledge in HeadsCritical processes depend on specific people's memoryMature orgs, specialized domains
Communication SilosInformation flows through personal relationships, not systemsMulti-department, 50+ employees
Analytics Capacity CrunchAnalytics team is bottleneck; can't serve all departmentsAny org with central analytics
Text/Email as System of RecordCritical info lives in messages, not structured systemsOrgs that outgrew their tools

How I Generate Hypotheses

  1. Match your industry to known automation patterns
  2. Adjust for company size (smaller = more quick wins; larger = more strategic initiatives)
  3. Cross-reference your stated challenges with pattern library
  4. Estimate impact ranges using industry benchmarks
  5. Prioritize by likelihood — hypotheses backed by strong patterns rank higher

Output Format

I'll create a markdown file you can save and reference throughout your discovery process:

# AI Opportunity Hypotheses: [Company Name]
Generated: [Date]
Industry: [Industry] | Size: [Employees] | Focus: [Departments]

## Executive Summary
[2-3 sentences on the most promising opportunity areas]

---

## Hypothesis 1: [Title]
**Department:** [Department]
**Pattern Match:** [Which known pattern this maps to]

**We believe that** [department/function] spends [estimated time] on [activity]
**which could be** [automated/augmented] using [AI approach],
**resulting in** [estimated impact: hours saved, cost reduction, quality improvement].

**Why we think this:**
- [Industry benchmark or pattern evidence]
- [Connection to stated challenge]

**To validate, interview:**
- [Role 1] — Ask: "[Specific question]"
- [Role 2] — Ask: "[Specific question]"

**Confidence:** [High/Medium/Low]
**Potential Impact:** [Range]
**Quick Win Potential:** [Yes/No — and why]

---

[Repeat for each hypothesis]

---

## Recommended Interview Order

### Phase 1: Executives (Days 1-2)
| Person/Role | Why Interview Them | Key Questions |
|-------------|-------------------|---------------|

### Phase 2: Frontline Workers (Days 3-7)
| Person/Role | Why Interview Them | Key Questions |
|-------------|-------------------|---------------|

### Phase 3: Back to Executives (Days 8-10)
| Purpose | What to Validate |
|---------|-----------------|

---

## Patterns to Watch For
Based on your industry and size, keep an eye out for:
- [Pattern 1 with description]
- [Pattern 2 with description]
- [Pattern 3 with description]

---

## Next Steps
1. Run `/interview-builder` to create tailored interview guides for each target
2. Run `/workflow-audit` to deep-dive into the highest-confidence hypothesis
3. After interviews, run `/insight-analyzer` to process findings

---
Built with the AI Opportunity Finder by Morningside AI
Want expert help? → https://morningside.ai

Tips for Best Results

  • Be specific about challenges. "Sales is slow" is less useful than "Reps spend 3+ hours/day on CRM data entry and prospecting research."
  • Name departments if you can. The more specific you are, the more targeted the hypotheses.
  • It's OK to be wrong. These are hypotheses, not conclusions. The point is to have a starting direction. You'll validate (or invalidate) through interviews.

What Comes Next

After generating hypotheses:

  1. /workflow-audit — Deep-dive into a specific process you suspect is wasteful
  2. /interview-builder — Create interview guides for the people identified in your hypothesis document
  3. /insight-analyzer — Process interview transcripts into structured findings

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.