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 san-npm/skills-ws --skill social-media-growthgit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/social-media-growth)<a href="https://agentmods.dev/skills/san-npm/skills-ws/social-media-growth"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/social-media-growth/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/san-npm/skills-ws/social-media-growth"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/social-media-growth.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 | $0.00070 | $0.04541 |
| Opus 5 | $0.00035 | $0.02270 |
| Sonnet 5 | $0.00014 | $0.00908 |
| Haiku 4.5 | $0.00007 | $0.00454 |
Grade A, and why
social-media-growth 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 5d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Media Growth
Operating guide for organic growth across LinkedIn, X (formerly Twitter), Instagram, TikTok, and YouTube Shorts. Bias toward what you can measure and reproduce, not algorithm folklore.
Sibling skills: paid amplification and channel strategy → marketing-analytics; founder-led pipeline and DMs-to-deals → business-development; editorial systems and repurposing → content-strategy; 1:1 outbound (cold DMs/email) → cold-outreach; creator partnerships → influencer-marketing; sponsored-content disclosure law → affiliate-marketing; positioning and voice → brand-strategy.
Read this first: algorithms change, so verify
Platform ranking systems are opaque, A/B-tested per cohort, and changed often. Most "the algorithm rewards X" advice online is inferred from creator anecdotes, not confirmed, and what worked last quarter may be neutralized today. Treat every tactic below as a hypothesis to validate on your own account, not a law.
Two things are genuinely public and worth grounding on:
- X open-sourced a ranking snapshot (
the-algorithmon GitHub, 2023) — directionally useful, now years stale; do not quote it as current. - Platforms publish creator/transparency docs (LinkedIn Engineering blog, TikTok "For You" explainer, Instagram "Ranking" posts by Adam Mosseri, YouTube Creator Insider). These are marketing-flavored but are the closest thing to primary sources. Cite the doc + the date you read it when you make a claim to a client.
Everything else: measure it.
Verification workflow (run this instead of trusting lore)
- Establish a baseline. Pull 60–90 days of native analytics (LinkedIn → Analytics; X → Premium Analytics / per-post; Instagram → Professional Dashboard + per-post Insights; TikTok → Creator tools → Analytics; YouTube → Studio). Record per-post: impressions, reach, the platform's "watch time"/"dwell" proxy, saves/bookmarks, shares/sends, profile visits, follows-from-post, link clicks. Normalize engagement as a rate (per impression), never raw counts.
- Change ONE variable per test. Hook style, format, length, posting time, link placement, CTA — one at a time. Mixing variables makes results uninterpretable.
- Use a meaningful sample. Single-post wins are noise. Compare ≥7–10 posts per variant, ideally over ≥2 weeks, before concluding. Watch the median, not the one viral outlier (which is usually exogenous, e.g. a large account shared you).
- Separate correlation from cause. "Posts with links got less reach" might mean links suppress reach — or that your link posts are promotional and just less interesting. Hold content type constant when testing a mechanic.
- Re-test quarterly. A tactic that stops working is signal, not failure. Date your playbook ("times/formats validated 2026-Q2") so stale conclusions get retired.
- Beware survivorship bias. "Creator X does Y and blew up" ignores thousands who did Y and didn't. Prefer your own A/B data over screenshots from growth gurus.
What ships with it
1 file 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.
- 5d ago First seen · 222 lines · 70 tokens per session scan A db756bbe48f4
social-media-growth is a skill published in the GitHub repository san-npm/skills-ws (2 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 4,541 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 2026-09-07.
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…