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 agentmods add skills/mikefluff/skills/carousel-buildernpx skills add Mikefluff/skills --skill carousel-buildergit clone --depth 1 https://github.com/Mikefluff/skillsWrote 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/mikefluff/skills/carousel-builder)<a href="https://agentmods.dev/skills/mikefluff/skills/carousel-builder"><img src="https://agentmods.dev/badge/skills/mikefluff/skills/carousel-builder.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.04945 |
| Opus 5 | $0.00043 | $0.02472 |
| Sonnet 5 | $0.00017 | $0.00989 |
| Haiku 4.5 | $0.00009 | $0.00494 |
Grade B, and why
carousel-builder scanned grade B with 1 finding 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 3d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
- Per shot: the slide PNG path as `image_url` + a one-line summary of the slide's overlay text (so the LLM can pick a motion that fits the slide's rhetoric — it must NOT re-describe the text in the output prompt). How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill orchestrates four lower-level skills:
essay-writeorviral-text→ drafts the contentimage-promptstyle anchor + per-slide promptscommon/runnersexecute layer → batch generation via the chosen providercommon/style-library/carousel/→ style anchor (24 bundled styles + user overrides)
Use when the user wants a finished carousel, not just prompts. Without --execute, returns the 8 prompts + captions for manual paste; with --execute, generates and saves the actual PNG slides.
This skill does NOT:
- Compose the slides into a single tall image — Instagram / LinkedIn handle multi-image posts natively.
- Add text overlays via a design tool — text either gets generated INSIDE the image (gpt-image-2 / Ideogram / Imagen) via
--text-mode embedded, or is left to the user's editor (--text-mode overlay). - Generate animated carousels (those are reels — use
reel-builder). - Post to platforms — that is
post-publisher, which takes this skill's output directory as its input.
ROLE
Topic / research → split content into N slides → pick style + model → assemble 8 per-slide prompts (style anchor + slide content + composition hint) → batch execute via image provider (one provider for all slides for consistency) → write slides + captions + manifest → print final paths.
PIPELINE (v2.14.0+ — promptCarousel chain, mirrors figma/app/lib/carousel/promptCarousel/)
- Resolve input — topic OR research brief OR finished post text:
--research <path>: read the brief, extract TL;DR / key facts / suggested angles as the topic.--content-file <path>: user-supplied finished post text. PRESERVE the author's voice — direct quotes + cuts only, no paraphrasing. If the text contains==word==accent markers, those words become accent-color callouts on the relevant slides.--topic "<text>": short topic string. Optionally invokeviral-text(IG/TikTok) oressay-write(LinkedIn) first to produce ~150-220 word post text with==accents==if the topic is rich enough to benefit. For pure promo decks (course invitation / product launch), topic-only is sufficient.
What ships with it
9 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.
- examples/before-after.md 7.0 KB
- references/batch-execute.md 5.9 KB
- references/model-picker.md 6.3 KB
- references/platform-presets.md 4.7 KB
- references/slide-roles.md 13 KB
- references/slide-split.md 7.0 KB
- references/style-resolution.md 6.0 KB
- references/troubleshoot.md 6.7 KB
- scripts/run.py 1.0 KB runs code
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.
- 3d ago First seen · 253 lines · 86 tokens per session scan B 3910b511b8ea
carousel-builder is a skill published in the GitHub repository Mikefluff/skills (18 stars, last pushed 26d ago), licensed MIT. It adds 86 tokens to every session and 4,945 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
humanizer
Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when…
clarity
Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write…
voiceprint
Use when writing an article, newsletter, blog post or long social post that must genuinely be the user's own writing. Triggers on "voiceprint", "write this in my voice", "turn my recording into an article", "cut my transcript down", "make this actually mine", "write from my video". Turns the user's own spoken words…
production-readiness
Review a project for production readiness. Invoked manually by the user via /production-readiness before deploying or preparing a release.
make-plan
Create an implementation plan for any task — feature, refactor, migration, fix — and save it to docs/agents/plans/. Use when the user asks to plan work, write an implementation plan, or prepare a task spec for claude/codex. (Implementing an existing plan is the implement-plan skill, not this one.).
remove-chinese-ai-tics
全面识别、审计和清除简体中文文本中的模型化口癖、套话、句法模板、篇章惯性、客服腔与格式反射，同时保留事实、语体、作者或人物声口。适用于“去 AI 味”“去机器味”“别像 GPT”“删模型口癖”“改自然”“检查套话”、中文成稿润色、创意写作、小说与故事修改、角色对话、创作约束和批量审稿；不用于判断作者身份或承诺绕过 AI 检测。.