Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add parisgroup-ai/imersao-ia-setup --skill design-auditoriagit clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-setupWrote 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/parisgroup-ai/imersao-ia-setup/design-auditoria)<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/design-auditoria"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/design-auditoria/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/parisgroup-ai/imersao-ia-setup/design-auditoria"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/design-auditoria.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 | $0.00198 | $0.12687 |
| Opus 5 | $0.00099 | $0.06344 |
| Sonnet 5 | $0.00040 | $0.02537 |
| Haiku 4.5 | $0.00020 | $0.01269 |
Grade A, and why
design-auditoria 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 12d 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 — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-auditoria
Audita um produto digital ou interface (landing pública, painel logado, dashboard, fluxo multi-step, app) e entrega documento formal A4 (HTML + PDF) pronto pra stakeholder externo.
Status: v0.6 — calibrado com 6 rodadas reais + 1 revisão crítica + 1 expansão de ferramentas:
- 1ª rodada (v0.2 · 30/04/2026): ToStudy /student/* — área logada, 56 págs A4
- 2ª rodada (v0.3 · 11/05/2026 manhã): ToStudy landing pública /pt-BR — revelou 4 falhas estruturais (protótipo como prosa, prints em apêndice, títulos com jargão, mockup que apaga DS). Viraram R13–R16.
- 3ª rodada (v0.4 · 11/05/2026 tarde): Revalidação da auditoria 1ª rodada · descobri tarde que revalidei em cima do
.mdpreliminar (proposta superseded) em vez do PDF/HTML final (proposta refinada). Custou ~1h refazendo trabalho. Virou R17: ler doc canônico final antes de revalidar, nunca preliminar.- 4ª rodada (v0.5 base · 21/05/2026): ToStudy menu creator portal — 24 itens visíveis · 3 níveis de profundidade · 10 findings + mockup diff-cirúrgico preservando DS terracota. Entregue HTML+PDF.
- 5ª rodada (v0.5 · 22/05/2026): ToStudy jornada student multi-canal (web + CLI + MCP + Mobile) · 27 findings · 5 GH issues abertas em prod (#581–#585). Revelou 2 falhas estruturais (R18+R19) que foram adicionadas à skill mas não tinham sido aplicadas em geração real.
- 6ª rodada (v0.5.1 · 25/05/2026): ToStudy jornada de inscrição em curso (descoberta → catálogo → ficha → checkout → confirmação → primeira aula) · 10 findings (3 P0 críticos) · score 5.4/10. Repetiu violação R18+R19 apesar de existirem na skill. Calibrou R20 (H1 explícito).
- Revisão crítica (v0.5.2 · 25/05/2026 tarde): durante revisão da 6ª rodada, a solicitante identificou 3 falhas estruturais que afetam credibilidade do método: (a) score inflado em pilares onde a evidência era subjetiva (Hierarquia 7.5 reduzida pra 5.5; Performance 6.5 reduzida pra 5.0* — sem Lighthouse formal); (b) auditoria parecia influenciada pelo que o usuário disse na sessão; (c) protótipo §09 não está sendo entregue em auditorias da equipe apesar de R13. Viraram R21 (score falsificável), R22 (independência metodológica anti-viés) e R23 (§09 mockup é gate bloqueante). Score recalibrado da 6ª rodada: 5.4 → 4.8.
- Expansão de ferramentas (v0.6 · 25/05/2026 noite): a solicitante recomendou enriquecer a camada de descoberta de jornada com 4 ferramentas adicionais usadas profissionalmente em UX Research. Retrofit na 6ª rodada validou que adicionam valor concreto, não filler: JTBD expôs barreira emocional dominante (não desistir); Service Blueprint transformou F-01 de bug de UX em bug de arquitetura (rota enrollFree não cria wallet com bonus); Moments of Truth validou objetivamente a priorização (3 P0s atingem 3 dos 4 MoTs); Mental Model Map mostrou que 4 findings compartilham a mesma raiz estrutural. Viraram R24 (JTBD), R25 (Service Blueprint condicional), R26 (MoT) e R27 (Mental Model Map condicional).
Falta 1 rodada em outro tipo de produto (SaaS B2B / e-commerce / app mobile) pra marcar v1.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 519 lines · 198 tokens per session scan A 57f40d990d96
design-auditoria is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 198 tokens to every session and 12,687 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
design-sprint
Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate before we build", "rapid prototype", "test with users", or "should we build this". Also trigger when a team is stuck in endless debate over a high-stakes product…
steve-jobs-design-review
Review designs, products, and features with Steve Jobs' standards: ruthless simplicity, focus, and end-to-end excellence. Use when the user mentions "Steve Jobs review", "design review", "product review", "what would Steve do", "insanely great", "this feels too complicated", "too many features", "product taste"…
web-typography
Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", "typographic scale", or "the text is hard to read". Also trigger when choosing between system…
hooked-ux
Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "habit formation", "engagement loops", "habit zone", or "the manipulation matrix". Also trigger when designing notification or re-engagement strategies, building…