Tooluck logoTooluck
SKILL.md

show-and-tell-video-slate

Agent skill fromericosiu/ai-marketing-skills

Turn authorized current builds, workflows, dashboards, analytics, and completed work into proof-led founder videos, then rank and combine the strongest filmable artifacts into exact 15-minute long-form slates with strict title and thumbnail evaluation. Use when deciding what to film, creating show-and-tell business videos, combining thin topics into complete episodes, or requiring packaging concepts to clear explicit quality gates.

How to install show-and-tell-video-slate

install show-and-tell-video-slate
# install the ai-marketing-skills pack with the skills CLI
npx skills add ericosiu/ai-marketing-skills

# or add only this skill to Claude Code: copy the folder

show-and-tell-video-slate/

# into

~/.claude/skills/show-and-tell-video-slate/ (all projects)

.claude/skills/show-and-tell-video-slate/ (one project)

show-and-tell-video-slate/SKILL.md

MITFull file
1# Show-and-Tell Video Slate
2
3Turn real work into videos whose opening promise is repaid by a visible artifact, workflow, result, or before/after.
4
5## Preamble
6
7From the repository root, run the privacy-preserving version check and telemetry initializer when available:
8
9```bash
10python3 telemetry/version_check.py 2>/dev/null || true
11python3 telemetry/telemetry_init.py 2>/dev/null || true
12```
13
14Remote telemetry is opt-in. Never log content, URLs, paths, credentials, names, business data, or proof artifacts.
15
16## Set the scope
17
18State the authorized sources, owner, channel, viewer, runtime, deliverable, and stop condition. Keep source systems read-only. Never search unrelated accounts, repositories, conversations, or credentials.
19
20Ask the user to rank these outcomes when not already known:
21
221. money created;
232. money saved;
243. productive capacity created.
25
26Load any supplied creator voice guide before writing titles or hooks. Reject packages that violate it even if their numeric scores pass.
27
28## Inventory filmable evidence
29
30Inspect only supplied or authorized builds, repositories, demos, agent runs, dashboards, analytics, and workflow outputs. For every candidate record:
31
32- viewer and business outcome;
33- visible artifact and demonstration path;
34- claim status: achieved, estimate, anecdote, forecast, target, or plan;
35- proof pointer, freshness, and privacy limits;
36- mechanism, lesson, and viewer action;
37- missing pickup, capture, redaction, or validation.
38…

Excerpt shown under the repository's MIT license.

More skills in ai-marketing-skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates