Test Writing Workflow
iOfficeAI/AionUi
Sets the test-writing workflow for the repository: risk-first scenario lists, behavior-focused Vitest tests, a full run before each commit and a coverage target.
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…
Install Show And Tell Video Slate
$ npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ericosiu/ai-marketing-skills show-and-tell-video-slate --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/show-and-tell-video-slate .claude/skills/show-and-tell-video-slate && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "show-and-tell-video-slate" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/show-and-tell-video-slate into .claude/skills/show-and-tell-video-slate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "show-and-tell-video-slate", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ericosiu/ai-marketing-skills/tree/main/show-and-tell-video-slateType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ericosiu/ai-marketing-skills show-and-tell-video-slate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/show-and-tell-video-slate .agents/skills/show-and-tell-video-slate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "show-and-tell-video-slate" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/show-and-tell-video-slate into .agents/skills/show-and-tell-video-slate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "show-and-tell-video-slate", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ericosiu/ai-marketing-skills show-and-tell-video-slate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/show-and-tell-video-slate .cursor/skills/show-and-tell-video-slate && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "show-and-tell-video-slate" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/show-and-tell-video-slate into .cursor/skills/show-and-tell-video-slate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "show-and-tell-video-slate", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ericosiu/ai-marketing-skills.git --path show-and-tell-video-slate--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ericosiu/ai-marketing-skills show-and-tell-video-slate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/show-and-tell-video-slate .gemini/skills/show-and-tell-video-slate && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "show-and-tell-video-slate" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/show-and-tell-video-slate into .gemini/skills/show-and-tell-video-slate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "show-and-tell-video-slate", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ericosiu/ai-marketing-skills show-and-tell-video-slateInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/show-and-tell-video-slate .github/skills/show-and-tell-video-slate && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "show-and-tell-video-slate" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/show-and-tell-video-slate into .github/skills/show-and-tell-video-slate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "show-and-tell-video-slate", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ericosiu/ai-marketing-skills show-and-tell-video-slate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/show-and-tell-video-slate .opencode/skills/show-and-tell-video-slate && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "show-and-tell-video-slate" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/show-and-tell-video-slate into .opencode/skills/show-and-tell-video-slate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "show-and-tell-video-slate", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
show-and-tell-video-slate- GitHub stars
- 3.6k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 732 words
- Files
- 8 (incl. scripts, references)
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
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…
- Works in 3 steps: money created; → money saved; → productive capacity created.
- Deciding what to film
- SKILL.md covers Preamble, Set the scope, Inventory filmable evidence and Apply the show-and-tell gate, plus 6 more sections
- Runs Python scripts from its folder; calls python3
What it does
Show And Tell Video Slate is an agent skill from ericosiu/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.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `README.md`, `agents/openai.yaml` and `references/output-contract.md`).
It sits in Testing & QA, covering Quality gates. The repository describes itself as: Open-source AI marketing skills — growth experiments, sales pipeline, content ops, outbound, SEO, and finance automation. The licence is MIT.
When your agent uses it
- Deciding what to film
- Creating show-and-tell business videos
- Combining thin topics into complete episodes
- Requiring packaging concepts to clear explicit quality gates
Example prompts
- “/show-and-tell-video-slate”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- money created;
- money saved;
- productive capacity created.
What it can do on your machine
Read from SKILL.md and the folder at commit 8088e1a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Show And Tell Video Slate loads about 1.5k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 732 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from ericosiu/ai-marketing-skills at commit 8088e1a, republished under its MIT licence (© ericosiu). 732 words, ~1,546 tokens.
Download SKILL.mdSave it as
.claude/skills/show-and-tell-video-slate/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- show-and-tell-video-slate
- description
- 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.
Show-and-Tell Video Slate
Turn real work into videos whose opening promise is repaid by a visible artifact, workflow, result, or before/after.
Preamble
From the repository root, run the privacy-preserving version check and telemetry initializer when available:
python3 telemetry/version_check.py 2>/dev/null || true
python3 telemetry/telemetry_init.py 2>/dev/null || trueRemote telemetry is opt-in. Never log content, URLs, paths, credentials, names, business data, or proof artifacts.
Set the scope
State the authorized sources, owner, channel, viewer, runtime, deliverable, and stop condition. Keep source systems read-only. Never search unrelated accounts, repositories, conversations, or credentials.
Ask the user to rank these outcomes when not already known:
- money created;
- money saved;
- productive capacity created.
Load any supplied creator voice guide before writing titles or hooks. Reject packages that violate it even if their numeric scores pass.
Inventory filmable evidence
Inspect only supplied or authorized builds, repositories, demos, agent runs, dashboards, analytics, and workflow outputs. For every candidate record:
- viewer and business outcome;
- visible artifact and demonstration path;
- claim status: achieved, estimate, anecdote, forecast, target, or plan;
- proof pointer, freshness, and privacy limits;
- mechanism, lesson, and viewer action;
- missing pickup, capture, redaction, or validation.
Do not upgrade remembered results into verified evidence. Label provisional candidates.
Apply the show-and-tell gate
Read references/selection-rubric.md. Reject or repair a candidate unless:
- the first 30 seconds can show a real outcome, build, screen, output, or physical artifact;
- the demonstration explains or proves the package;
- one promise can sustain 15 minutes without padding;
- the viewer receives a usable mechanism or decision;
- the ending resolves the opening promise completely.
Framework-only topics must use real case studies. Product walkthroughs must lead with the viewer outcome rather than a feature list.
Combine carefully
Combine ideas only when they share one mechanism, viewer, and payoff. Examples include sales and recruiting workflows that use the same outreach loop, multiple cost controls inside one audit system, or a demonstrated content result paired with the loop that produced it.
Do not combine unrelated proof points merely to reach the runtime. Route thin ideas to shorter formats.
Build an exact 15-minute spine
Use 900 seconds unless the user overrides it:
0:00-0:30show the outcome and promise;0:30-2:00establish the stakes and baseline;2:00-5:00show what was built;5:00-10:00demonstrate how it works;10:00-13:00show receipts, limitations, and lessons;13:00-15:00give the implementation path and close the promise.
Show full SKILL.md (348 more words)Show less
Score and package
Use the nine episode lenses in references/selection-rubric.md. Require a 90+ average, with Demoability and Payoff Integrity each at least 90.
Create exactly three materially different packages:
- verdict or contrarian conclusion;
- specific proof or transformation;
- decision utility or implementation framework.
Require every package to score at least 9.0/10 with no dimension below 8.5. Use zero to four thumbnail words and no more than three major visual groups. Prefer the real artifact, result screen, dashboard, output, or physical prop over an abstract metaphor.
After the slate passes, use content-eval for deeper panel review, video-content-engine for the production plan, and shortform-idea-grill for complete short-form derivatives when those skills are installed. Use a compatible thumbnail-packaging skill when available. Keep achieved results distinct from plans and forecasts.
Validate
Read references/output-contract.md, save the structured slate as JSON, and run:
python3 scripts/evaluate_slate.py slate.json --output slate-eval.json
python3 scripts/evaluate_slate.py slate.json --validate-onlyThe validator checks runtime, artifact evidence, claim proof, episode scores, packaging lanes, thumbnail word count, component budget, and package score floors.
Deliver
Return the ranked slate, combination decisions, exact run of show, first-30-second promise, proof and pickup ledger, three packages per episode, evaluation readback, winning package, and shoot order.
Separate ready from repair. A strong package never overrides missing proof. Do not render, publish, schedule, upload, or change a live asset without explicit approval.
Lifecycle
- Tracked state: keep run evidence, slate JSON, evaluation reports, and decisions in a user-selected private runtime folder, not in the skill.
- Success test: at least one episode passes the episode and show-and-tell gates, every surfaced package passes deterministic validation, and every achieved claim has a proof pointer.
- Repeat trigger: run when choosing a recording slate, after a meaningful build ships, or when new first-party results arrive. Do not schedule by default.
- Learning writeback: store user corrections, failed proof checks, and post-publication performance evidence in the private runtime folder.
- Promotion: validate after one real build produces a passing slate and a complete recording. Treat as production-ready after three useful slates and at least two measured content readbacks.
- Retirement: archive if three consecutive runs add no differentiated ready episode or another workflow absorbs the complete process.
© ericosiu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (scripts, references) in show-and-tell-video-slate of ericosiu/ai-marketing-skills.
- SKILL.md
- README.md
- agents/openai.yaml
- references/output-contract.md
- references/selection-rubric.md
- requirements.txt
- scripts/evaluate_slate.py
- tests/test_evaluate_slate.py
Open the folder on GitHubat commit 8088e1a
Compare with similar skills
Show And Tell Video Slate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Show And Tell Video Slate this skillericosiu/ai-marketing-skills | 3.6k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Test Writing WorkflowiOfficeAI/AionUi | 33k | 1 repos | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| SoloPi AI Controlalipay/SoloPi | 6.3k | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | |
| Quality Scandiegosouzapw/OmniRoute | 75k | — | ~748 | Automated safety check: Pass | MIT | |
| Test GuardamElnagdy/guard-skills | 1.3k | 2 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Triage Sonarqubenetdata/netdata | 81k | — | ~2.8k | Automated safety check: Notes | GPL-3.0 |
Similar skills
SoloPi AI Control
alipay/SoloPi
Drives Android devices through SoloPi's typed command line to record, replay and verify app behavior, with device pools and signed on-device decision models.
Quality Scan
diegosouzapw/OmniRoute
Runs a scoped, read-only quality scan on a repository candidate and reports exact evidence, failures and frozen debt, without treating a static scan as release acceptance.
Test Guard
amElnagdy/guard-skills
Reviews newly written or edited tests against nine rules that cut test bloat, such as mock-heavy checks and near-duplicate cases, before they are committed.
Triage Sonarqube
netdata/netdata
Inspect, review, or apply authorized triage decisions to SonarCloud issues and security hotspots; also review the Sonar helpers.
Cherry Studio Regression Tests
CherryHQ/cherry-studio
Runs Cherry Studio's critical-path regression suite as deterministic Playwright E2E tests through a GitHub workflow on macOS and Windows runners.
More from ericosiu/ai-marketing-skills
All 21 skills in this repoExpert Panel
ericosiu/ai-marketing-skills
Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts.
Cold Outbound Optimizer
ericosiu/ai-marketing-skills
Design, analyze, and optimize cold outbound email campaigns for Instantly.
Finance Ops
ericosiu/ai-marketing-skills
AI-powered financial analysis suite. An agent skill from ericosiu/ai-marketing-skills.
Leveling Up Content Engine
ericosiu/ai-marketing-skills
Diagnose and transform any authorized video URL, upload, recording, transcript, podcast, interview, presentation, screen recording, webinar, ad, or published video into the strongest justified…
Net New Video Editor
ericosiu/ai-marketing-skills
Turn newly recorded talking-head footage into review-ready vertical video drafts with an explicit edit plan, deterministic FFmpeg rendering, captions, hook cards, audio normalization, and visual QA.
Packaging Youtube Thumbnails
ericosiu/ai-marketing-skills
A skill your agent uses when a user supplies new video content or a channel and wants on-brand YouTube titles, thumbnail concepts, rendered variants, A/B packaging, identity profiling, precise…
Related
Categories
Questions about Show And Tell Video Slate
What does Show And Tell Video Slate do?
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…. Show And Tell Video Slate is an agent skill from ericosiu/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.
When should I use Show And Tell Video Slate?
Show And Tell Video Slate fits situations like: deciding what to film; creating show-and-tell business videos; combining thin topics into complete episodes; requiring packaging concepts to clear explicit quality gates.
How do I install Show And Tell Video Slate in Claude Code?
Run `npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a claude-code`. Or copy the skill folder (show-and-tell-video-slate in ericosiu/ai-marketing-skills) into .claude/skills/show-and-tell-video-slate in your project. Claude Code loads it when a task matches its description.
How do I install Show And Tell Video Slate in Codex?
Run `npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a codex`. Or copy the skill folder (show-and-tell-video-slate in ericosiu/ai-marketing-skills) into .agents/skills/show-and-tell-video-slate in your project. Codex loads it when a task matches its description.
Can I use Show And Tell Video Slate in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ericosiu/ai-marketing-skills --skill show-and-tell-video-slate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/show-and-tell-video-slate, .gemini/skills/show-and-tell-video-slate, .github/skills/show-and-tell-video-slate and .opencode/skills/show-and-tell-video-slate in your project.
What does Show And Tell Video Slate need to run?
Going by SKILL.md and its folder, Show And Tell Video Slate needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Show And Tell Video Slate access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Show And Tell Video Slate safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Show And Tell Video Slate use?
Show And Tell Video Slate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Show And Tell Video Slate use?
About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 784 tokens, read only when the agent opens those files.
What are the alternatives to Show And Tell Video Slate?
Skills that share tags, products or a category with Show And Tell Video Slate: Test Writing Workflow (iOfficeAI/AionUi, 33k stars), SoloPi AI Control (alipay/SoloPi, 6.3k stars), Quality Scan (diegosouzapw/OmniRoute, 75k stars) and Test Guard (amElnagdy/guard-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Show And Tell Video Slate?
ericosiu (a GitHub user) maintains it in ericosiu/ai-marketing-skills, which has 3,620 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 22, 2026.
Source: ericosiu/ai-marketing-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.