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 inklate/social-skills --skill social-repurposegit clone --depth 1 https://github.com/inklate/social-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/inklate/social-skills/social-repurpose)<a href="https://agentmods.dev/skills/inklate/social-skills/social-repurpose"><img src="https://agentmods.dev/badge/skills/inklate/social-skills/social-repurpose/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/inklate/social-skills/social-repurpose"><img src="https://agentmods.dev/badge/skills/inklate/social-skills/social-repurpose.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 | $0.00185 | $0.01529 |
| Opus 5 | $0.00093 | $0.00764 |
| Sonnet 5 | $0.00037 | $0.00306 |
| Haiku 4.5 | $0.00018 | $0.00153 |
Grade A, and why
social-repurpose 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Given one long-form source, extract 5–8 atomic ideas, match each to the format it is strongest in, draft everything, and lay it out as a 7-day content plan.
Context
Read social-context.md (also check .agents/social-context.md) before mining. You need:
- Brand voice: register, person, how spiky the takes are allowed to be
- Audience: what they already know, so drafts do not re-explain basics
## Platforms: which platforms matter, to weight the format mix- Content pillars, if present — ideas that fit a pillar get priority when you must cut
- The Never list: screen mined ideas against it before drafting — spiky mining is exactly what crosses red lines
If the file is missing, offer to run the social-context skill first — but do not block. Ask two or three quick questions inline (Which platforms matter most? Who is the audience? Personal or company voice?) and proceed.
Workflow
- Ingest the full source. Read the whole transcript or post, not the intro. In transcripts, the best material hides in asides, tangents, and answers to the second-to-last question — the parts the author did not know were good.
- Mine 5–8 distinct atomic ideas. Hunt specifically for: quotable one-liners, hard numbers and results, contrarian moments (where the author disagrees with common advice), stories with a turn, and step-by-step fragments that stand alone. Log each as one sentence plus the source excerpt that backs it.
- Deduplicate ruthlessly. Two ideas that would produce the same hook are one idea. If you cannot find five genuinely distinct ideas, say so and deliver fewer, stronger pieces rather than padding.
- Map ideas to formats by strength, not availability:
- Story with a turn → LinkedIn post (LinkedIn rewards narrative + lesson)
- Hard number or surprising result → single X post (the number is the hook)
- Step-by-step or list fragment → Instagram carousel or X thread
- Contrarian take → LinkedIn post or X post, wherever the audience holds the belief being attacked
- Visual or demonstrable moment → short-video beat sheet
- Draft the standard week's mix, adjusted to the platforms in social-context:
- 2 LinkedIn posts from different angles — never two takes on the same idea; each with a fold-surviving hook line and one lesson.
- 1 X thread — 3–7 tweets, first tweet works alone, strongest material in the back half.
- 3 single X posts — each built on one number, quote, or take; no hashtags.
- 1 Instagram carousel outline — cover hook + 6–8 one-idea slides + recap + CTA, slide text ≤25 words.
- 1 short-video script beat sheet — hook ≤3 seconds, 3–5 beats, spoken-word phrasing, on-screen text cues, ≤60 seconds total.
- Make every piece stand alone. No "as I wrote in my blog", no "in this week's episode", no numbering that implies a series. Each draft is written as if the idea occurred to the author this morning. Full context lives inside the draft.
- Run a voice pass. Repurposed content drifts toward summary-voice — flat, third-person, hedged. Rewrite anything that reads like a book report until it sounds like the person in social-context talking. First-person specifics ("we shipped", "I was wrong") are the tell that it worked. Check every quote against the source: verbatim or clearly paraphrased, never a misattributed punch-up.
- Spread the week. Assign each piece a day:
- Lead Monday with the strongest LinkedIn post; put the X thread mid-week when feeds are busiest.
- Never place two pieces derived from the same idea on adjacent days.
- Keep the carousel and the video on different days so the heavier formats do not stack.
- Vary platform day to day — three consecutive X days starves the other channels.
- Sanity-check coverage and constraints. Every atomic idea from step 2 is either used exactly once or explicitly parked in a leftovers list. No idea is used twice in the same week, and no draft exists that does not trace back to a mined idea. Then check each draft against its row in the Quality bar and fix any that misses its format constraint.
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.
- 12d ago First seen · 89 lines · 185 tokens per session scan A c20bc87ff16b
social-repurpose is a skill published in the GitHub repository inklate/social-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session and 1,529 once invoked, about $0.0009 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 2026-08-31.
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…