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 aiagentwithdhruv/skills --skill linkedin-carousel-handwrittengit clone --depth 1 https://github.com/aiagentwithdhruv/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/aiagentwithdhruv/skills/linkedin-carousel-handwritten)<a href="https://agentmods.dev/skills/aiagentwithdhruv/skills/linkedin-carousel-handwritten"><img src="https://agentmods.dev/badge/skills/aiagentwithdhruv/skills/linkedin-carousel-handwritten/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/aiagentwithdhruv/skills/linkedin-carousel-handwritten"><img src="https://agentmods.dev/badge/skills/aiagentwithdhruv/skills/linkedin-carousel-handwritten.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 898 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Agent Snooping · line 891 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00111 | $0.09876 |
| Opus 5 | $0.00056 | $0.04938 |
| Sonnet 5 | $0.00022 | $0.01975 |
| Haiku 4.5 | $0.00011 | $0.00988 |
Grade A, and why
linkedin-carousel-handwritten scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- NO Photoshop-perfect sticky notes — they must look like real physical sticky notes photographed on the page (slight curl at corners, real shadow, random tilt 4-10°) How it starts
The opening of the file, as written. The whole thing — 900 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Carousel — Handwritten Weekly Post
Goal
Turn one technical lesson, methodology, or system Dhruv has shipped in production into a complete LinkedIn carousel post that:
- Stops the scroll on the first slide
- Holds dwell time across all 7 slides
- Converts comments into qualified DMs
- Builds the AIwithDhruv brand library week over week
- Compounds via cross-posting to X, Instagram, YouTube
Every output of this skill follows the SAME visual + structural pattern — that's how the channel develops a recognizable rhythm. Audience starts to anticipate the format.
When to Invoke
Trigger phrases from Dhruv:
- "Write a LinkedIn carousel about [topic]"
- "Make this a weekly carousel post"
- "Turn this methodology into a notebook carousel"
- "Build the Sunday/Tuesday post"
- "Use the carousel skill"
Default cadence: once per week, posted Tuesday or Wednesday at 9-10 AM IST.
Series Identity (Locked)
| Field | Value |
|---|---|
| Series name | Build-in-Public Diaries — Notebook Edition |
| Episode prefix | Diary #N (continuous numbering across all carousels) |
| Cadence | 1 per week, Tuesday OR Wednesday, 9-10 AM IST |
| Slide count | 7 (algorithm-optimal — outperforms 5 slides by 18%) |
| Aspect | 4:5 vertical for each slide |
| Format | Upload as PDF document post (LinkedIn renders as native carousel — gets 6.6% engagement, highest format) |
| Voice | First-person from Dhruv ("I shipped", "we built", "what I learned") |
| Brand palette | Black marker + cyan #00D4FF + yellow highlighter + pastel sticky notes (yellow, light blue, pink, light green, light purple) |
| Style anchor | Real notebook page on wooden desk — photo of a real whiteboard, NOT digital illustration |
The Proven 7-Slide Formula
Each slide has a single job. Don't blur the jobs.
| # | Slide Job | What's On It | Visual Hero |
|---|---|---|---|
| 1 | Hook + Thesis | Title, subtitle, 3 thesis statements, "what fails / what ships" two-column, swipe arrow | Big bold title + cyan-underlined thesis boxes |
| 2 | The Framework | The N-step methodology as a flow diagram (boxes connected by arrows) | Horizontal flow with arrows |
| 3 | The Workflow | The N-gate / N-rule workflow that runs every commit/task | Horizontal arrow with vertical gates/checkpoints |
| 4 | The Team / Stack | The N-agent or N-tool architecture as an org chart or constellation | Org chart or constellation diagram |
| 5 | The Proof | One real shipped example with timeline + outcome + numbers | Mini-timeline with checkmarks + outcome box |
| 6 | The Lesson | One sentence everyone can take away + "what to do next" | Big quote-style lesson + one action item |
| 7 | CTA | Comment FRAMEWORK + Follow + Share — with author signature | Big "COMMENT → FRAMEWORK" hero box + arrow + author Polaroid |
What ships with it
2 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 · 900 lines · 0 tokens per session scan A d669a9ffd644
linkedin-carousel-handwritten is a skill published in the GitHub repository aiagentwithdhruv/skills (17 stars, last pushed 15d ago), licensed MIT. It adds 111 tokens to every session and 9,876 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…