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 motiful/product-shots --skill product-shots-social-postgit clone --depth 1 https://github.com/motiful/product-shotsWrote 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/motiful/product-shots/product-shots-social-post)<a href="https://agentmods.dev/skills/motiful/product-shots/product-shots-social-post"><img src="https://agentmods.dev/badge/skills/motiful/product-shots/product-shots-social-post/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/motiful/product-shots/product-shots-social-post"><img src="https://agentmods.dev/badge/skills/motiful/product-shots/product-shots-social-post.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 | $0.00157 | $0.02622 |
| Opus 5 | $0.00078 | $0.01311 |
| Sonnet 5 | $0.00031 | $0.00524 |
| Haiku 4.5 | $0.00016 | $0.00262 |
Grade A, and why
product-shots-social-post 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Post
Designs social-platform-native visuals (Feed, Story, Reel, Carousel) across Instagram, TikTok, Facebook, Pinterest, RedNote, LinkedIn, X/Twitter and other social platforms by combining nine canonical formats, seven industry visual-DNA presets, a seven-step workflow, a carousel framework with cross-slide consistency anchoring, and a self-audit gate. The skill produces a design description, optional caption, and self-check score per output.
The format taxonomy (Feed Square 1:1 / Feed Portrait 4:5 / Story 9:16 / Reel Cover 9:16 / Carousel 4:5 / etc.) maps directly across Instagram, TikTok, Facebook, RedNote, and Pinterest — the same aspect ratios are platform-native on all of them. Platform-specific safe-zone tuning lives in references/hard-constraints.md.
Engagement Principles
These rules apply across every Section. Read before acting.
- Lock dimensions first — every request resolves to one of nine formats with explicit width × height and aspect ratio. No format = no work.
- Industry DNA before composition — match the user's industry to one of the seven presets; load its prompt patch + composition + color + lighting + common errors as a single bundle.
- Layered constraint priority — Hard Constraints (Section 0) > Industry Rules (Section 1) > User Preferences > Model defaults. When user color overrides, industry default yields.
- Carousel consistency is per-slide repetition — the consistency anchor is repeated verbatim at the start of every slide's prompt, not declared once.
- Mandatory self-audit before delivery — every output passes the 14-item check (Section 4) and emits the seven-line Self-Check score.
- Banned words are filtered out of generator prompts — platform names / UI terms / screenshot terms / brand-tool names never reach the image model. They are used only for internal format selection and industry matching.
- Match the user's language — respond in English if user writes English, in Chinese if user writes Chinese. Never switch language unprompted.
- Use
<suggestion>for option sets — when proposing platform / format / industry choices, wrap them in<suggestion>tags. Never ask multiple questions at once.
What ships with it
5 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 · 190 lines · 157 tokens per session scan A d6fd76c6e260
product-shots-social-post is a skill published in the GitHub repository motiful/product-shots (48 stars, last pushed 3mo ago), licensed MIT. It adds 157 tokens to every session and 2,622 once invoked, about $0.0008 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
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
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.
kami-deck
A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
fs-editorial-forest
Art-directing a fashion house's annual report — the editorial system, the photography rhythm, and the data spreads. Built as a decision-grade design craft deck for brand stakeholders, exec audience.
html-ppt-zhangzara-stencil-tablet
A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.