value-check
Skill19 starsChanged 9 days agoMITView on GitHub
Audit copy, campaigns, and UX flows across 13 ethical, trust, organic-fit, and subtlety checks before shipping. Sub-skill: load only when routed from the hook-everything entry skill, not for general writing or editing.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- hook-everythingSkill
- anti-slopSkill
- audience-calibrationSkill
- creative-ideationSkill
- hook-compoundingSkill
- marketing-hooksSkill
- market-intelligenceSkill
- product-hooksSkill
- psychology-mapSkill
- self-reviewSkill
- trust-architectureSkill
- visual-ux-hooksSkill
- writing-hooksSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Run this 13-point audit before delivering any copy, campaign, hook idea, market analysis, or product flow.
- Distinctive: line 37
Check 13 comes from gregruthenbeck's "detone" practice of asking how a piece feels to read for each user segment.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Value, Trust & Subtlety Check (13-Point Gate)
Run this 13-point audit before delivering any copy, campaign, hook idea, market analysis, or product flow. Any NO requires a rewrite before shipping.
Part 1: Ethical & Zero-Scam ("Anti-Scam") Gate
| Check | Question to Verify |
| 1. Payoff >= Promise | After clicking, reading, or completing onboarding, does the user receive immediate utility equal to or greater than what the hook implied? |
| 2. Zero Fabricated Receipts | Are all metrics, latencies, dates, quotes, and citations 100% real (or explicitly marked in brackets for the user to supply)? |
| 3. Upfront Cost Honesty | Are pricing, renewal rules, and data permissions visible before the user invests non-exportable work? |
| 4. Symmetric Exit | Can the user cancel, hibernate, export their raw data, or mute notifications in the same number of clicks it took to join (M26 Regret Regulation)? |
| 5. Vulnerability Guardrail | Does the design avoid exploiting grief, addiction, financial desperation, loneliness, or minors? |
Part 2: Market Fit, Audience Calibration, Compounding & Stylometry Gate
| Check | Question to Verify |
| 6. The Organic Fit Gate | If a live market trend or statistic is included (skills/market-intelligence), is it 100% causally connected to the user's problem with zero forced "news-pegging"? (If it feels forced, delete the trend.) |
| 7. Audience Route Calibration | Does the hook's construal level and proof density match the target audience's ELM processing route (skills/audience-calibration)? |
| 8. Visual & Choice Isolation | Is the layout free of Choice Overload (<= 2 competing actions per viewport) with a clear Von Restorff isolation focus (skills/visual-ux-hooks)? |
| 9. The Second-Look Test | If the user read your internal design notes explaining why this hook chord was engineered this way, would they respect the craft and feel helped - or feel manipulated? |
| 10. The Smell Test | Can a skeptical reader smell "marketing" or "copywriting tricks"? If yes, cut adjective intensity by 40% and add a stronger Trust Damper (skills/trust-architecture). |
| 11. Chord Orthogonality | Did you pair high-tension hooks with trust/autonomy dampers (skills/hook-compounding) and rotate chords across consecutive blocks? |
| 12. 85-Rule Anti-Slop Gate | Does the text score <= 15/100 on tools/slop_scan.py and obey all 85 rules in skills/anti-slop? |
| 13. The Reader-Feeling Check | For each reader segment in skills/audience-calibration (for example, a skimmer and a deep reader), how would it feel to read this? Name any spot that bores, confuses, or talks down to that segment, and rewrite it. |
Decision Rule
- Fail on 2, 3, 4, or 5 requires stopping immediately and removing the deceptive or coercive element.
- Fail on 1, 6, 7, 8, 9, 10, 11, 12, or 13 requires rewriting the chord, stripping the forced trend, injecting a stronger trust lever, or eliminating AI/hype tells until every line passes cleanly.
Check 13 comes from gregruthenbeck's "detone" practice of asking how a piece feels to read for each user segment.
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.