agentleFS
Andamio-PlatformAndamio-Platform/coach/skills/gather-screenshots/SKILL.md

gather-screenshots

Skill6 starsChanged 8 months agoMITView on GitHub

Generate screenshot capture checklists for Product Demo lessons based on readiness assessment.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After /self-assess-readiness identifies Product Demo SLTs as "Needs Context"

    line 18
  2. Distinctive:

    When the Context Shopping List includes screenshots

    line 19
  3. Distinctive:

    Before building Product Demo lessons

    line 20
  4. Very specific:

    If no course specified, scan courses-in-progress/ and ask which course to generate checklist for.

    line 33
  5. Very specific:

    Read 04-readiness-assessment.md to identify:

    line 37
  6. Very specific:

    Read 00-course.md to get:

    line 44
  7. Very specific:

    Ensure assets/screenshots/ directory exists:

    line 108

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Skill: Gather Screenshots

Description

Generates a structured screenshot capture checklist from a course's readiness assessment. Used during Phase 6 (Gather Context) of the course workflow to prepare assets for Product Demo lessons.

When to Use

  • After /self-assess-readiness identifies Product Demo SLTs as "Needs Context"
  • When the Context Shopping List includes screenshots
  • Before building Product Demo lessons

Invocation

/gather-screenshots                           # Interactive: asks which course
/gather-screenshots andamio-for-contributors  # Specify course

Instructions

1. Identify Course

If no course specified, scan courses-in-progress/ and ask which course to generate checklist for.

2. Read Readiness Assessment

Read 04-readiness-assessment.md to identify:

  • Which SLTs are "Needs Context"
  • Which of those are Product Demo lesson type (cross-reference with 03-lesson-type-classification.md)
  • What specific screenshots are needed (from Gap Analysis sections)

3. Read Course Outline

Read 00-course.md to get:

  • Lesson focus for each SLT (what UI flows to capture)
  • Lesson inputs specified (what screenshots were already anticipated)

4. Generate Checklist

Create assets/screenshots/README.md with:

# Screenshot Capture Checklist: [Course Name]

**Generated from:** `04-readiness-assessment.md`
**Target site:** [primary URL]
**Last updated:** [date]

## Capture Settings

- **Browser:** Chrome or Firefox (consistent across all screenshots)
- **Window width:** 1280px recommended
- **Theme:** Use default theme
- [Any course-specific settings]

## Naming Convention

[slt-number]-[flow-name]-[sequence].png


## Checklist

### SLT [X.Y]: [SLT text]

| # | Filename | What to Show | Status |
|---|----------|--------------|--------|
| 1 | `X.Y-flow-name-01.png` | [specific UI state] | [ ] |
| 2 | `X.Y-flow-name-02.png` | [next UI state] | [ ] |

**Capture notes:**
- [specific guidance for this flow]

---

[Repeat for each Product Demo SLT]

## Summary

| SLT | Screenshots Needed | Captured | Notes |
|-----|-------------------|----------|-------|
| X.Y | [count] | 0 | [brief note] |

**Total:** [n] screenshots

## Capture Session Notes

_Use this space to record observations during capture:_

- Date:
- Tester:
- Environment:
- Observations:

5. Create Directory Structure

Ensure assets/screenshots/ directory exists:

courses-in-progress/[course-slug]/
  assets/
    screenshots/
      README.md  # The checklist
      # Screenshots will be added here

6. Output Summary

After generating, report:

## Screenshot Checklist Generated

**Course:** [name]
**Location:** `assets/screenshots/README.md`

| SLT | Flow | Screenshots |
|-----|------|-------------|
| X.Y | [flow-name] | [count] |

**Total:** [n] screenshots across [m] SLTs

### Capture Tiers

| Tier | SLTs | Prerequisites | Est. Time |
|------|------|---------------|-----------|
| 1: No login | [list] | Just browse | [time] |
| 2: Logged in | [list] | Wallet connected | [time] |
| 3: Async | [list] | Prior actions completed | Later |

**Next step:** Capture Tier 1 screenshots to validate the system.

Naming Convention

Format

[slt]-[flow]-[step].png

Parts

PartFormatExamplePurpose
sltX.Y1.2SLT number
flowkebab-casewallet-connectHuman-readable flow name
step01, 0201Sequence (zero-padded)

Examples

FilenameDescription
1.2-wallet-connect-01.pngFirst step of wallet connection
1.2-wallet-connect-02.pngSecond step
2.1-course-catalog-01.pngCourse catalog overview
3.2-enrollment-03.pngThird step of enrollment

Why This Convention

  1. Sorted by SLT — Files group naturally
  2. Predictable paths — Lessons reference without guessing
  3. Sequence clear — Steps are numbered
  4. Grep-friendly — ls 3.2-* shows all enrollment screenshots

Flow Name Guidelines

Choose flow names that are:

  • Descriptive — wallet-connect not step1
  • Consistent — Same flow = same name across courses
  • Short — 2-3 words max

Common Flow Names

FlowUse For
wallet-connectConnecting wallet to platform
mint-tokenMinting any token/NFT
course-catalogBrowsing course listings
project-catalogBrowsing project listings
enrollmentEnrolling in course/module
submissionSubmitting evidence/assignment
credential-claimClaiming earned credential
project-joinJoining a project
task-commitCommitting to a task

Guidelines

  • One checklist per course — Don't split across files
  • Specific UI states — "Landing page with Connect button" not "homepage"
  • Capture notes matter — Include edge cases, error states, prerequisites
  • Tier by dependencies — Group screenshots by what's required to capture them
  • Update after capture — Check off items, note any issues
  • Flat directory — No subdirectories per SLT (simpler for ~50 files or fewer)

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.