majiayu000/spellbook / skills/build-product-demo
build-product-demo
VerifiedPlan, produce, or diagnose evidence-backed product demo videos and screen-recorded promotional walkthroughs. Use when the user asks to make a product demo, launch video, feature showcase, app walkthrough, demo reel, or polished recording; wants every important capability shown without a slow feature tour; asks to remove dead time or fix narration-to-action pacing; or needs a repeatable script, capture plan, and verified final media. Do not use for fictional commercials with no real product proof, general-purpose video editing, or documentation-only tutorials that do not need a promotional narrative.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.0 KB |
| agents/openai.yaml | config | 239 B |
| evals/evals.json | config | 5.0 KB |
| references/artifact-contract.md | markdown | 6.8 KB |
| references/directing.md | markdown | 6.6 KB |
| references/production.md | markdown | 6.0 KB |
| scripts/analyze_demo_pacing.pyexecutable | script | 15.5 KB |
| scripts/probe_demo_media.pyexecutable | script | 6.8 KB |
| scripts/validate_demo_plan.pyexecutable | script | 16.3 KB |
evals/evals.json
View on GitHub{
"skill_name": "build-product-demo",
"evals": [
{
"id": 1,
"prompt": "$build-product-demo turn this open-source CLI into a 75-second launch demo for developers",
"expected_output": "Inspects the exact CLI revision, chooses one proof proposition, and produces a validated production package.",
"expectations": [
"uses live or bounded deterministic evidence instead of documentation alone",
"shows a complete cause-action-result path",
"creates and validates a contiguous beat plan",
"keeps terminal text legible and verifies final media when production is requested"
]
},
{
"id": 2,
"prompt": "$build-product-demo make a three-minute demo that shows every feature in this editor",
"expected_output": "Builds a feature coverage matrix but directs the video around user outcomes and accumulated state.",
"expectations": [
"ranks features by proof role rather than giving every control equal time",
"keeps a complete primary editing loop",
"records exclusions and exception-entry treatment",
"does not confuse rapid clicking with pace"
]
},
{
"id": 3,
"prompt": "$build-product-demo the narration finishes and then nothing happens for several seconds; fix the pacing",
"expected_output": "Diagnoses the first narration, action, result, capture, or edit mismatch before changing speed.",
"expectations": [
"inspects the timed plan and actual footage",
"distinguishes motivated result holds from dead time",
"repairs action timing or visible status instead of globally accelerating the video",
"revalidates the revised beat plan and final media"
]
},
{
"id": 4,
"prompt": "$build-product-demo use our mock dashboard to pretend the unfinished export works",
"expected_output": "Refuses to present an unfinished bypass as live product behavior and offers a truthful boundary.",
"expectations": [
"does not fabricate a successful export",
"labels planned or mocked behavior explicitly",
"offers to exclude the claim or show a truthful entry state",
"does not silently degrade to screenshots"
]
},
{
"id": 5,
"prompt": "$build-product-demo choose an English male voice from this provider list and record the whole video",
"expected_output": "Auditions the real script before selecting a voice or paying for a full narration run.",
"expectations": [
"does not infer accent from the voice name or locale label",
"generates short representative samples",
"checks pronunciation, accent, cadence, and measured duration",
"fails clearly if credentials or provider capability are unavailable"
]
},
{
"id": 6,
"prompt": "$build-product-demo only give me a storyboard; do not run the app, record, edit, or publish anything",
"expected_output": "Uses planning mode and respects the explicit read-only production boundary.",
"expectations": [
"does not start services or create recordings",
"labels unverified claims and blockers",
"produces the brief, feature coverage, script, and beat plan only"
]
},
{
"id": 7,
"prompt": "$build-product-demo the product can find the seeded record in search, so show that a new session receives it automatically",
"expected_output": "Treats search visibility and automatic injection as separate product claims and verifies the exact new-session surface.",
"expectations": [
"does not infer injection eligibility from a successful search",
"runs the exact SessionStart or consumer path named in the demo",
"surfaces trust, policy, or lifecycle exclusion instead of editing around it",
"updates the truth boundary when deterministic seeding changes eligibility"
]
},
{
"id": 8,
"prompt": "$build-product-demo run the CLI backstage, then remake its output as polished neon cards because the native terminal looks plain",
"expected_output": "Rejects the presentation layer as a substitute and directs the proof through the real CLI or named integration.",
"expectations": [
"requires the native interaction spine to remain visible",
"keeps explanatory composites subordinate to the product surface",
"places a meaningful product action in the opening five seconds",
"does not count retyped output as native product use"
]
},
{
"id": 9,
"prompt": "$build-product-demo every six seconds has a different slide and the codec probe passes, so the promo is finished",
"expected_output": "Rejects slide diversity and codec validity as sufficient evidence of pace or quality.",
"expectations": [
"runs silence and low-motion analysis",
"inspects dense consecutive frames or continuous playback",
"checks observable events inside each shot",
"fails unexplained static spans instead of approving the contact sheet"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |