Borrowing it
Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/skills/copywriting/litmus-test/SKILL.mdgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/litmus-test)<a href="https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/litmus-test"><img src="https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/litmus-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/litmus-test"><img src="https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/litmus-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.00777 |
| Opus 5 | $0.00044 | $0.00388 |
| Sonnet 5 | $0.00017 | $0.00155 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
litmus-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Direction Litmus Test
Apply to ALL ideas before presenting. If an idea fails any question, rework it before showing anyone.
The 5 Questions
-
Would this make a room uncomfortable? If no — it's too soft. Safe ideas don't cut through. Discomfort signals you've said something true.
-
Could a competitor say this? If yes — it's too generic. If your message could appear in a competitor's ad unchanged, it's not a position, it's a category description.
-
Does it lead with outcome or process? If process — rethink. Users don't care how you do it. They care what changes for them. "We use AI" is process. "You get your evenings back" is outcome.
-
Would we say this to someone's face? If no — it's bullshit. Corporate speak fails this test: "leverage synergies," "best-in-class solutions," "stakeholder engagement." If you wouldn't say it to a friend, don't say it to a customer.
-
Can we cut 30% of the words? The answer is always yes. Every first draft has 30% that adds length without meaning. Find it and cut it.
Voice Reference: Authentic Provocateur
The voice that passes the Litmus Test:
- Says what everyone's thinking but no one will voice
- Honest, not harsh
- Simple words, complex ideas
- Short. Punchy. Direct.
Signature patterns:
- "Stop debating and start executing"
- "A strategy given is a strategy forgotten"
- "Ship it now, perfect it never works either — ship it now, fix it fast"
Creative Brief Format
Use this structure when capturing approved creative direction:
The Challenge: [One paragraph reframing the problem — lead with user pain, not company goals]
The Insight: [The uncomfortable truth driving this concept]
The Idea: [Core concept in one sentence — make it uncomfortable]
How It Works: [Specific, not vague — what exactly happens]
Why It's Uncomfortable: [What conventions this challenges]
Why It Works: [Strategic rationale — business case, not aesthetics]
Anti-Generic Rules
- NEVER accept the first framing of a brief — challenge it first
- NEVER propose one safe, consensus option — always show 2–3 directions
- NEVER lead with methodology ("We use a 4-step process...")
- NEVER use: leverage, synergy, best-in-class, solutions, stakeholder engagement, deep dive, circle back
- NEVER hedge with "perhaps" or "it could be argued" — commit or don't say it
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 72 lines · 87 tokens per session scan A aca36026bb42
litmus-test is a skill published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 777 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
video-editing
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
fal-ai-media
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
memstack-content-youtube-script
Use this skill when the user says 'YouTube script', 'video script', 'write script for YouTube', 'YouTube video outline', or is creating scripted content for a YouTube video with hooks, chapters, and CTAs. Do NOT use for TikTok/Reels short-form scripts or webinar presentations.
memstack-marketing-facebook-ad
Use this skill when the user says 'facebook ad', 'FB ad', 'Meta ad', 'Instagram ad', or needs social media ad copy with targeting, creative direction, and A/B test plans for Meta Ads Manager. Do NOT use for Google search ads or organic social content.
memstack-content-tiktok-script
Use this skill when the user says 'TikTok script', 'TikTok video', 'Reels script', 'Shorts script', 'short-form video', or needs timestamped scripts with hooks, visual cues, and captions for 15-60 second videos. Do NOT use for Twitter threads or webinar scripts.