agentleFS
ChewbaccaRoarsChewbaccaRoars/pathfinder-skills/skills/show-your-work/SKILL.md

show-your-work

Skill2 starsChanged 8 months agoMITView on GitHub

Generates shareable artifacts from what the user built — impact summaries, how-to guides, before/after comparisons, and presentation-ready slides. Use when the user wants to share what they built with their team, manager, or organization.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    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 the user says any of the following, ask which format they want:

    line 138
  2. Distinctive:

    If they're unsure, recommend based on context:

    line 146
  3. Distinctive:

    Always include a "what's next" or "how you can help others" element

    line 157
  4. Distinctive:

    Never include code in leadership-facing outputs unless asked

    line 158

“Common” is measured: kept by at least 6 in 10 of the 3 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Show Your Work

Overview

Building is only half the value. Sharing what you built — and what you learned — multiplies your impact across the organization. This skill turns any build into shareable knowledge.

Keywords: share, present, document, impact, ROI, summary, guide, teach, before after, showcase

Output Formats

1. Impact Summary (for leadership / Slack)

A concise summary designed for people who care about outcomes, not technical details.

Format:

## What I Built: [Name]

**Problem**: [1-2 sentences describing the manual/painful process]
**Solution**: [1-2 sentences describing what was automated/built]

**Impact**:
- Time saved: [X hours/week]
- Before: [how it used to work]
- After: [how it works now]
- People affected: [who benefits]

**What I learned**: [1 sentence about the key insight]

**Want this for your team?** [1 sentence offering to help others do the same]

2. How-to-Replicate Guide (for teammates)

A step-by-step guide someone else could follow to build the same thing or adapt it for their use case.

Format:

## How to Build: [Name]
**Time needed**: ~[X] minutes
**Skill level**: No coding experience needed
**What you'll need**: [Google account, access to X, etc.]

### What This Does
[2-3 sentence plain-English explanation]

### Step-by-Step Setup
[Numbered steps with exact clicks, screenshots descriptions, and what to expect]

### How to Customize It
[Common things someone might want to change, and how]

### Troubleshooting
[Top 3 things that might go wrong and how to fix them]

3. Before/After Comparison

A visual-style comparison that makes the impact tangible.

Format:

## Before vs. After: [Name]

| | Before | After |
|:--|:-------|:------|
| **How it works** | [manual process] | [automated process] |
| **Time per occurrence** | [X minutes/hours] | [X seconds/minutes] |
| **Frequency** | [how often] | [same, but automated] |
| **Error rate** | [manual errors] | [automated accuracy] |
| **Who does it** | [person/team] | [runs automatically] |

**Total time saved per month**: [calculation]
**Total time saved per year**: [calculation]

4. Learning Story (for culture / blog / wiki)

A narrative format that captures not just what was built, but the journey of building it.

Format:

## How I Built [Name] (And What I Learned)

### The Problem
[What was painful and why it mattered]

### The Hypothesis
[What I thought would work and why]

### The Build
[What I actually built — kept simple, no jargon]

### What Broke
[What didn't work the first time — normalized as part of learning]

### What I Learned
[Key insights — technical and non-technical]

### What's Next
[How this could grow or what else it inspired]

5. Presentation Outline (for demos / show-and-tell)

A structured outline for a 5-minute live demo or presentation.

Format:

## Demo: [Name] (5 minutes)

**Slide 1 — The Problem** (30 seconds)
[One sentence about the pain point. Make the audience feel it.]

**Slide 2 — The Idea** (30 seconds)
[What if we could...? State the hypothesis.]

**Live Demo** (2 minutes)
[Run the automation live. Show the input, the process, the output.]

**Slide 3 — The Impact** (1 minute)
[Before/after numbers. Who benefits. Time saved.]

**Slide 4 — What I Learned** (30 seconds)
[One key insight. What surprised you.]

**Close — Call to Action** (30 seconds)
[Who else could use this? How can you help them?]

How to Use

When the user says any of the following, ask which format they want:

  • "Help me share this"
  • "I want to show my team"
  • "How do I present this?"
  • "Write up what I built"
  • "Document this"
  • "Show my work"

If they're unsure, recommend based on context:

  • Sharing in Slack → Impact Summary
  • Helping a teammate do the same → How-to-Replicate Guide
  • Pitching to a manager → Before/After + Presentation Outline
  • Contributing to team culture → Learning Story

Rules

  • Strip all jargon — these artifacts are for non-technical audiences
  • Focus on impact and learning, not technical implementation
  • Make the user the hero of the story — they built this
  • Always include a "what's next" or "how you can help others" element
  • Never include code in leadership-facing outputs unless asked

Tone

  • Proud but humble: "Look what we built" not "Look how smart I am"
  • Impact-focused: numbers, time saved, people helped
  • Inviting: "You could do this too" energy
  • Honest about the journey: include what broke, what was hard

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.