Borrowing it
Nothing to install: this file belongs to ashishpatill/tell-proof. 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/ashishpatill/tell-proof/master/.cursor/skills/tell-taste-verdicts/SKILL.mdgit clone --depth 1 https://github.com/ashishpatill/tell-proofWrote 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/ashishpatill/tell-proof/tell-taste-verdicts)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/tell-taste-verdicts"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-taste-verdicts/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/ashishpatill/tell-proof/tell-taste-verdicts"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-taste-verdicts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00053 | $0.00510 |
| Opus 5.5 | $0.00021 | $0.00204 |
| Sonnet 5.5 | $0.00011 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
tell-taste-verdicts 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 1mo 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.
What it actually says
Tell taste and voice direction
Scope
packages/taste/src/engine.ts— Gemini + deterministic fallbackpackages/taste/src/parse-direction.ts— voice/text direction parsingpackages/taste/src/presets.ts— editorial, precision, warm-minimal, bold-contrast, luxury, brutalist, explainerapps/web/src/app/api/voice/route.ts— browser voice refinement endpoint
Verdict contract
- Verdicts:
generic,drift,intentional,uncertain - Rationale ≤ 3 sentences, critic voice, no apology, no emoji
- Detector
factsare authoritative; reject rationales that contradict them - Reflection loop: draft → validate against facts → refine once → mechanical fallback at confidence 0.5
Voice / art-direction
- Deterministic parser runs first (
parseDirectionPlan) so demo works without keys - Gemini refines when
GEMINI_API_KEYis present - Presets:
editorial,precision,warm-minimal,bold-contrast,luxury,brutalist,explainer - Output:
ArtDirectionwith keywords, token overrides, summary - When adding or steering styles, follow
docs/08_AI_DESIGN_METHODS.md(methods + style playbook). Never put third-party author/site names in keywords or docs.
Path differences
- MCP
tell_diagnosecallsclassifyWithTastewhen key exists - Web
/api/diagnosesubprocess may return deterministic verdicts only - Do not assume Gemini runs on every diagnose path
Testing
- Mock fetch/model responses; never hit live Gemini in tests
- Assert zod validation and fallback when model JSON is invalid or contradictory
DoD
- Every finding gets a valid
TasteVerdict - Brutalist/intentional fixture case can return
intentional - Offline demo works with zero API keys
Related
- Rules:
.cursor/rules/tell-taste-engine.mdc - Agent:
.cursor/agents/taste-engineer.md
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.
- 1mo ago First seen · 51 lines · 53 tokens per session scan A e20edcb8b7d1
tell-taste-verdicts is a skill published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 22d ago), licensed MIT. It adds 53 tokens to every session and 510 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
better-design
Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…
hps-bauhaus
A visual-design fundamentals course for new brand designers — grid, type, color, and the exercises that build the eye. Built as a decision-grade professional training deck for junior designers, new hires.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
wireframe-annotated
An annotated / redline lo-fi wireframe — a desktop landing/marketing page drawn as flat greyboxes inside a browser chrome frame, overlaid with numbered annotation pins (①②③④⑤) in a single accent color, paired with a right-hand SPEC PANEL that lists each numbered pin with a short engineering / UX note. This is the…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component Prismer HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.