agentleFS
iamrohithrnairiamrohithrnair/merman/.claude/skills/demo/SKILL.md

demo

Skill42 starsChanged 19 days agoMITView on GitHub

Print the merman demo reply to eyeball every rendering feature after a change. Use after any visual change, when asked for "the demo", "show all features", "visual test", or before a release screenshot.

29 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use pitch, spec and 4 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.
  • ORBWEVASkill

    pitch

    Pitch deck and fundraising skill for founders. Use when user wants to create a pitch deck, prepare for investor meetings, write investor outreach emails, model financials for fundraising, or handle VC objections. Triggers on "pitch deck", "investor", "fundraise", "raise money", "Series A", "seed round", "VC", "angel", or /pitch commands.

    Also in 3 projects that use this

  • 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 5 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

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

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 1

    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:

    every flowchart box and sequence participant in its own color, with matching colors at both ends of the sequence

    line 16

“Common” is measured: kept by at least 6 in 10 of the 27 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

Demo

The visual test. Unit tests prove the tree; this proves the look.

  1. Load the working copy in this session (see live-check step 1). The new version shows only after the turn that made the edit ends.
  2. Print docs/demo.md verbatim as the whole final message of a turn, with nothing before it and no tool call after it. Claude Code condenses text written right before a tool call, so the demo must close the turn.
  3. The person looks at it, or screenshots it on the next turn (live-check step 3). Check:
    • merman in a heavy box on the first line, and Roster with a heavy rule under it
    • the table: yellow header, rules between rows, the right-aligned Size column, colored numbers
    • the four diagrams and the table on one row on a wide terminal, wrapping on a narrow one
    • every flowchart box and sequence participant in its own color, with matching colors at both ends of the sequence
    • a value above each bar, the tallest bar highlighted and the rest muted, labels without quotes, dim gridlines, colored axis numbers
    • the C4 diagram: Shop as a frame around Orders and Ledger, each box with its bold name and bracketed type ([Container: Go]), Payments and [External Software System] all in the comment color, lines numbered 1 to 3 that each start on one box and end in an arrowhead on another, and a legend under it reading 1 Baker → Orders Uses; pointing at a line lights its legend row
    • shell colors: command, flags, the quoted string, &&
    • code blocks with a language header and no frame, and Prism colors in the TypeScript block
    • path, link and inline-code colors, the paths opening their files on click in a terminal that draws hyperlinks while /kick stays unlinked text, the quote bar running down its paragraph and both list rows, and the green Tip alert box
    • accent ⧉ md, ⧉ art and ⧉ html buttons on the table (⧉ html in a local macOS or Linux terminal only), and an accent [ ⧉ copy ] button on every diagram, the list, the shell block, the alert and the quote
    • the timeline figure: drawn line by line with no ── figure header, the caption in the comment color, the ▏───▏ axis and the Provider bar in the diagram color, ✗ and 2 twice in the theme's reddest accent color, the Handler bar and 1 in its greenest, the time labels in its most amber, those three different from each other and from the diagram color, the bars ending on the axis ticks, ⧉ source and ⧉ art above it
    • the Hebrew section: lines read right to left (the first bullet shows eu-west and us-east after the Hebrew, mirrored parentheses), bullets and 1. on the right, the quote bar on the right, the table cells right aligned, and the shell comment reversed while ls -la stays
  4. Fix what looks wrong, then run the demo again.
  5. Keep it current. A new feature adds a line to docs/demo.md and to the checklist above. All data stays invented and neutral.

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.