agentleFS
nickstellarstreamainickstellarstreamai/ai-opportunity-finder/skills/department-synthesizer/SKILL.md

department-synthesizer

Skill11 starsChanged 9 months agoMITView on GitHub

Aggregate multiple interview findings into a department-level synthesis. Identifies cross-interview patterns, quantifies total impact, and categorizes opportunities as Quick Wins or Strategic Initiatives. Use after processing 2+ interviews from the same department with /insight-analyzer.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 3 people in the same department independently describe the same frustration, that's no longer an opinion — it's a validated …

    line 15
  2. Distinctive:

    When I receive the findings, I:

    line 31
  3. Distinctive:

    Before considering a synthesis complete, verify:

    line 206

≈ “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

Department Synthesizer

Takes multiple interview findings documents (from /insight-analyzer) for a single department and synthesizes them into one consolidated view. This is where individual data points become organizational patterns — where "one person complains about scheduling" becomes "scheduling costs this department 800 hours/year."

Why This Matters

Individual interviews are interesting. Synthesis is where the money is.

When 3 people in the same department independently describe the same frustration, that's no longer an opinion — it's a validated organizational problem. This skill does that triangulation for you.

What I Need From You

  1. Department name
  2. 2 or more Interview Findings documents (output from /insight-analyzer)
    • Provide as file paths or paste the content directly
  3. Survey data (optional — if you ran a pre-interview survey)
  4. Any additional context about the department (headcount, budget, strategic importance)

What You'll Get

A Department Synthesis Document — the definitive view of one department's AI opportunities.

Processing Logic

When I receive the findings, I:

  1. Inventory all pain points across all interviews
  2. Triangulate — Flag any pain point mentioned by 2+ people as validated
  3. Aggregate quantification — Sum hours across interviewees, calculate department-wide impact
  4. Identify root causes — Connect surface-level complaints to underlying systemic issues
  5. Categorize opportunities — Quick Wins (2-8 weeks, low complexity) vs Strategic (2-6 months, higher complexity)
  6. Score each opportunity on Impact and Feasibility

Output Format

# Department Synthesis: [Department Name]
**Company:** [Company Name]
**Date:** [Date]
**Interviews Analyzed:** [Number]
**Interviewees:** [Names and roles]

---

## Main Insight

[ONE powerful sentence that captures the core finding for this department.]

Format: "[Department] spends [X hours/year] on [activity] that [impact statement]."

---

## Core Problem

**What's fundamentally broken:**
[2-3 sentence description of the systemic issue — not just symptoms, but the underlying problem]

**Validated by:**
| Source | Evidence |
|--------|----------|
| [Name, Role] | "[Quote or finding]" |
| [Name, Role] | "[Quote or finding]" |
| [Name, Role] | "[Quote or finding]" |

**Confidence Level:** [High (3+ sources) / Medium (2 sources) / Low (1 source + inference)]

---

## Why It's Happening

**Root Cause 1:** [Description]
- Evidence: [What points to this cause]

**Root Cause 2:** [Description]
- Evidence: [What points to this cause]

**Root Cause 3:** [Description]
- Evidence: [What points to this cause]

---

## Quantified Impact

### Time Burden

| Process/Activity | Source | Hours/Week | Hours/Year | People |
|-----------------|--------|------------|------------|--------|
| [Activity 1] | [Who reported it] | [X] | [X × 50] | [N] |
| [Activity 2] | [Who reported it] | [Y] | [Y × 50] | [N] |
| **Total** | | **[Sum]** | **[Sum]** | |

### Cost Estimate

| Category | Annual Hours | Cost at $50/hr | Cost at $75/hr |
|----------|-------------|----------------|----------------|
| Manual processes | [X] | $[Amount] | $[Amount] |
| Rework/errors | [Y] | $[Amount] | $[Amount] |
| Coordination overhead | [Z] | $[Amount] | $[Amount] |
| **Total** | **[Sum]** | **$[Sum]** | **$[Sum]** |

*Note: $50/hr is a conservative estimate for staff time. Adjust based on your actual loaded labor costs.*

### Quality & Risk Impact

- [Error rate or quality issue mentioned]
- [Risk identified (e.g., single point of failure, knowledge loss)]
- [Downstream impact on other departments]

---

## Opportunities

### Quick Wins (2-8 weeks, Low Complexity)

**1. [Opportunity Name]**
| Dimension | Detail |
|-----------|--------|
| **Description** | [What to build or change] |
| **Impact** | [Hours saved/year, $ value] |
| **Complexity** | Low |
| **Dependencies** | [What needs to be true] |
| **Validated by** | [Which interviewees support this] |
| **Why it's a quick win** | [Low technical complexity, data available, champion exists] |

**2. [Opportunity Name]**
...

### Strategic Initiatives (2-6 months, Medium-High Complexity)

**3. [Opportunity Name]**
| Dimension | Detail |
|-----------|--------|
| **Description** | [What to build or change] |
| **Impact** | [Hours saved/year, $ value] |
| **Complexity** | Medium / High |
| **Dependencies** | [What needs to be true — integrations, data, change management] |
| **Validated by** | [Which interviewees support this] |
| **Why it's strategic** | [Requires more investment but delivers transformational value] |

---

## Cross-Interview Patterns Detected

| Pattern | # of Sources | Confidence | Evidence |
|---------|-------------|------------|----------|
| [Pattern name] | [N] | [High/Med/Low] | [Brief evidence summary] |
| [Pattern name] | [N] | [High/Med/Low] | [Brief evidence summary] |

**Patterns appearing in 3+ interviews are high confidence and should be treated as organizational facts, not opinions.**

---

## Implementation Considerations

**Prerequisites:**
- [Data access needed]
- [System integrations required]
- [Stakeholder buy-in needed]

**Risks:**
- [Risk 1] — Mitigation: [How to address]
- [Risk 2] — Mitigation: [How to address]

**Success Factors:**
- [What needs to be true for this to work]
- [Who needs to champion this internally]

**Change Management Notes:**
- [How receptive were interviewees to change?]
- [Any resistance signals to watch for?]

---

## Department Summary Card

| Metric | Value |
|--------|-------|
| Total addressable hours/year | [X] |
| Estimated annual cost | $[Y] |
| Quick win opportunities | [N] |
| Strategic opportunities | [N] |
| Confidence level | [High/Medium/Low] |
| Top priority | [Opportunity name] |

---

## Next Steps

1. Run `/department-synthesizer` for other departments
2. Once all departments are synthesized, run `/priority-ranker` to compare across the organization
3. Use the Main Insight and Key Quotes in your `/executive-briefing`

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

Quality Checklist

Before considering a synthesis complete, verify:

  • Main insight is ONE sentence with specific numbers
  • Core problem validated by 2+ independent sources
  • Impact quantified in both hours AND dollars
  • Every opportunity categorized as Quick Win or Strategic
  • Each opportunity has a complexity rating and dependencies listed
  • Root causes identified (not just symptoms)
  • Cross-interview patterns flagged with evidence counts

Handling Conflicting Information

Sometimes interviewees disagree. When this happens:

  • Note the disagreement explicitly — Don't average conflicting numbers
  • Weight by proximity — The person closest to the work is usually more accurate
  • Flag for follow-up — Disagreements often reveal the most interesting insights
  • Use ranges — "Scheduling takes 5-15 hours/week (estimates vary by role)" is more honest than picking one number

Tips for Best Results

  • Minimum 2 interviews per department. One interview is an anecdote. Two is a data point. Three is a pattern.
  • Include different levels. A manager and a frontline worker from the same department will give you very different perspectives — you need both.
  • Don't cherry-pick. Include all findings, even ones that seem minor. Sometimes the "minor" pain point is actually the biggest time sink when you add it up.

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.