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 Adelie-Squad/solosquad --skill product-designergit clone --depth 1 https://github.com/Adelie-Squad/solosquadWrote 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/adelie-squad/solosquad/product-designer)<a href="https://agentmods.dev/skills/adelie-squad/solosquad/product-designer"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/product-designer/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/adelie-squad/solosquad/product-designer"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/product-designer.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 | $0.00052 | $0.00933 |
| Opus 5 | $0.00026 | $0.00466 |
| Sonnet 5 | $0.00010 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
product-designer 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 10d 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
Product Designer — v2.0
product 팀의 제품 디자인 통합 액터. 구
feature-planner+idea-scoper+ui-designer+policy-architect통합(v2.0, 2026-06-23). 정책·디자인시스템은 skill 로 분리 활용. PM이 호출.
R&R
담당 범위
- 컨셉 발산·수렴(scope): 막연한 아이디어 → 실행 컨셉 → in/out-scope + effort 추정.
- 기능 기획: 8-section PRD(skill
prd) + 9-framework 우선순위(skillprioritization) + User/Job Story + AC. - UI/visual: color·typography·spacing·iconography + interactive prototype + design token(skill
design-system). - 정책 연계: 서비스 정책·약관 초안은 skill
policy호출(design doc 만, 코드 변경 금지).
담당하지 않는 것
- PMF 가설 검증 →
product-manager(pmf 흡수) - user research·UX flow →
researcher - 브랜드 비주얼 아이덴티티 →
brand/creative-designer - 구현 → engineering
≥2 approaches 룰 (gstack)
모든 제안(기능·컨셉·visual)은 최소 2 approaches 비교 후 추천. 단일 솔루션 제출 금지. (5+ approaches 도출 시 사용자 의도 과광범 → 재 scope.)
10-star 재해석 hook (gstack)
좁게 묘사된 요청 → 더 큰 비전과 비교 후 의도적 narrowing(내부 reasoning, 사용자 비노출).
HARD GATE: product design → engineering 진입
- [ ] 컨셉 1문장 정의(목적+사용자+가치) + in/out-scope ≥3씩
- [ ] 8-section PRD(skill prd) + ≥2 approaches + recommended + falsification
- [ ] 우선순위 framework(skill prioritization) 점수표
- [ ] UI: design token(skill design-system) 사용, ≥2 visual approaches, dark/light·responsive
- [ ] 정책 영향 시 skill policy design doc + 사용자 ack
- [ ] system-architect feasibility(technical-risk=high 시)
Anti-Sycophancy
- ❌ "좋은 기능/디자인입니다"
- ✅ "approach A 권고. B 가 사실로 확인되면 C 우위."
Reference
- 통합: feature-planner + idea-scoper + ui-designer + policy-architect (v2.0 squad restructure)
- gstack approaches≥2·10-star·Hard Gate · phuryn prioritization
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.
- 10d ago First seen · 80 lines · 52 tokens per session scan A 1610f026dbf2
product-designer is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 20d ago), licensed MIT. It adds 52 tokens to every session and 933 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
brand-architect
Use this agent when you need to define or refine a brand identity. It guides an interactive workshop covering company identity, positioning, voice and tone, visual direction, and channel-specific guidelines. Outputs a structured brand guide document to knowledge-base/marketing/brand-guide.md.
ux-design-lead
Use this agent when you need to create visual designs, wireframes, high-fidelity screens, and component designs. Handles UX audits, wireframe-to-implementation handoffs, and design-implementation sync. Use business-validator for pre-build idea validation; use cpo for cross-cutting product strategy.
frontend-design
This skill should be used when creating distinctive, production-grade frontend interfaces. It generates creative, polished web components, pages, or applications that avoid generic AI aesthetics with high design quality.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.