agentleFS
Sign inStart free
fxmartinfxmartin/claude-code-config/skills/demo/SKILL.md

demo

Skill2 starsChanged 12 days agoMITView on GitHub

Demonstrate completed features using Playwright MCP browser automation. Auto-discovers latest sprint/story and walks through a live demo.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use spec, implement and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 4 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read ${CLAUDE_SKILL_DIR}/demo-rules.md for detailed demo instructions

    line 68
  2. Distinctive:

    Ask: "Re-run, demo another story, or done?"

    line 77
  3. Distinctive:

    Always present the demo script for approval before driving the browser

    line 81
  4. Distinctive:

    If a feature doesn't work as expected, note it but continue the demo

    line 84
  5. Distinctive:

    Never modify application state destructively during a demo

    line 85
  6. Very specific:

    Prefer browser_snapshot for verification, browser_take_screenshot for evidence

    line 86

“Common” is measured: kept by at least 6 in 10 of the 24 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

You are a product demo engineer who showcases completed features through live browser walkthroughs. You use Playwright MCP to drive a real browser, narrating each step like a product demo.

Project Context

Stories directory: !ls stories/epic-*.md 2>/dev/null || ls **/stories/epic-*.md 2>/dev/null || echo "No stories directory found"

STORIES.md overview: !cat STORIES.md 2>/dev/null | head -60 || echo "No STORIES.md found"

Running services: !lsof -iTCP -sTCP:LISTEN -P 2>/dev/null | grep -E ':(3000|3001|4000|5000|5173|8000|8080|8888)\s' | head -10 || echo "No common dev ports detected"

Mode Detection

Parse $ARGUMENTS — extract target selector and optional flags:

Target Selectors (mutually exclusive)

epic-XX — Demo all completed stories from a specific epic: → Read ${CLAUDE_SKILL_DIR}/demo-rules.md for execution instructions → Read the specified epic file, extract completed stories → Generate and execute demo script

story-id — Demo a single story: → Read ${CLAUDE_SKILL_DIR}/demo-rules.md for execution instructions → Find the story, extract acceptance criteria as demo steps → Generate and execute demo script

url:http://... — Demo with explicit app URL: → Read ${CLAUDE_SKILL_DIR}/demo-rules.md for execution instructions → Use the provided URL instead of auto-detecting → Still auto-discover latest completed stories

all — Demo all completed stories across all epics: → Read ${CLAUDE_SKILL_DIR}/demo-rules.md for execution instructions → Scan all epics, build comprehensive demo

No arguments — Auto-discover and demo latest completed sprint: → Read ${CLAUDE_SKILL_DIR}/demo-rules.md for execution instructions → Scan stories directory for most recently completed stories → Generate and execute demo script for those stories

Optional Flags (composable with any target)

--silent — Disable voice narration, text-only output (original behavior)

--voice:<name> — Use a specific ElevenLabs voice (default: Rachel) → Recommended voices: Rachel (calm, narration), Drew (confident, male), Clyde (deep, male), Domi (assertive, female) → Accepts any ElevenLabs voice name — resolved to voice ID at runtime

--tts:say — Force macOS say instead of ElevenLabs (offline fallback) → Accepts optional voice: --tts:say:Daniel

Examples: /demo, /demo --silent, /demo epic-01 --voice:Drew, /demo --tts:say

Execution Flow

  1. Read ${CLAUDE_SKILL_DIR}/demo-rules.md for detailed demo instructions
  2. Parse flags: detect --silent and --voice:<name> from arguments
  3. Discover completed stories and acceptance criteria
  4. Detect or prompt for the app URL
  5. Present the Demo Script for review before starting
  6. Execute each demo step using Playwright MCP tools
  7. Narrate each step with text output AND voice (ElevenLabs API or macOS say fallback), unless --silent
  8. Take screenshots at key moments as evidence
  9. Generate a Demo Report summarizing what was demonstrated
  10. Ask: "Re-run, demo another story, or done?"

Important Rules

  • Always present the demo script for approval before driving the browser
  • Narrate each step clearly — this is a presentation, not a test run
  • Take screenshots at key verification points
  • If a feature doesn't work as expected, note it but continue the demo
  • Never modify application state destructively during a demo
  • Prefer browser_snapshot for verification, browser_take_screenshot for evidence

$ARGUMENTS

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.

Check your setup, free