demo
Skill22 starsChanged 4 days agoMITView on GitHub
The demo skill owns turning a product concept, release artifact, checklist, or named demo into a convincing, self-contained local try-it experience. It stages only missing product context with deterministic, visibly simulated behavior; builds or revises the focal interaction; serves it on loopback; and verifies the exact preview, restart path, and QA result. It triggers when a user asks to build, revise, activate, or use /demo for a realistic local demo or artifact experience. It does not own feature integration into an existing app router, testing an already-running localhost or dist build, comparing prototype directions or state models, converting Markdown into durable HTML, making demo videos, writing sales scripts, explaining mock design, or reviewing bugs without edits.
26 other projects use a version of this.
Adopted by
Most recently taken up by
- yarikleto/claude-teacher-plugintheir own version, first seen Nov 14, 2026
- NahumLitvin/prismantistheir own version, first seen Nov 13, 2026
- serhiileniv/skillstheir own version, first seen Nov 8, 2026
- serhiileniv/ccstheir own version, first seen Nov 8, 2026
- zedarvates/frugal-skillstheir own version, first seen Nov 8, 2026
- mehboobali98/rmine-skillstheir own version, first seen Nov 1, 2026
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.
SentrySkillspec
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 FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 4 projects that use this
SentrySkillreview
Fixture review skill.
Also in 4 projects that use this
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
NVIDIASkillresearch
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
Other versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- NahumLitvin/prismantis★ 426same name
- iamrohithrnair/merman★ 42same name
- yarikleto/claude-teacher-plugin★ 15same name
- calebnewtonusc/Chewbacca★ 8same name
- malinskibeniamin/skills★ 4same name
- nivoset/skills★ 4same name
- pcode-xyz/simple-skills★ 4same name
- developzone5/sanad★ 3same name
- raphaelDkhn/worldbuilder★ 3same name
- fxmartin/claude-code-config★ 2same name
16 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- autoconsultantSkill
- automakeSkill
- consultantSkill
- consultingSkill
- copywritingSkill
- first-principlesSkill
- grilling-fixSkill
- htmlSkill
- midwitSkill
- prototypingSkill
- skill-issueSkill
- voice-modeSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Start a long-lived server for DEMO_DIR on 127.0.0.1 using a free non-common port, record its PID, and record the exact restart command with …
- Distinctive: line 15
Verify the exact preview URL and focal path with browser interaction at relevant viewports when available, or a clearly identified …
- Distinctive: line 20
Run the server as the foreground command of a long-running tool session.
“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.
Files
Demo
Recipe
- Resolve the target and
DEMO_DIRinside the provided demo state root, or expanded~/.demootherwise: revise a named demo in place, demonstrate a named artifact, or identify plausible targets whose differences would materially change the result. - Present any required target question directly—never through
AskUserQuestion—as a clear bold question, necessary context below it, then numbered options whose first option is the recommendation and ends with(Recommended). - Inspect the source and choose its smallest convincing focal experience; use host tools directly, stage missing product or service behavior with deterministic synthetic state, and keep
DemoorSimulatedvisible without credentials, destructive action, or claims of a live backend, model, extension, auth flow, integration, or third party. - Build or revise the one descriptive lowercase-hyphen directory as an accessible responsive local experience, preferring one self-contained
index.htmland adding only assets or files the focal path requires. - Start a long-lived server for
DEMO_DIRon127.0.0.1using a free non-common port, record its PID, and record the exact restart command with the same binding, port, and directory. - Verify the exact preview URL and focal path with browser interaction at relevant viewports when available, or a clearly identified HTTP/source fallback otherwise, and keep the verified server alive through handoff.
- On success reply with exactly five lines labeled
Demo path,Preview,Restart,Real vs staged, andQA; after bounded serve or verification failure reply withNot ready, omit every link, and give the path, restart command, concrete failure, next fix, and QA limitation.
Details
- Run the server as the foreground command of a long-running tool session; do not background or detach it from a shell that will exit, and treat loss of that session as a serving failure rather than reporting its URL.
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
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.

