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 khasky/awesome-agent-skills --skill awesome-content-repurposegit clone --depth 1 https://github.com/khasky/awesome-agent-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/khasky/awesome-agent-skills/awesome-content-repurpose)<a href="https://agentmods.dev/skills/khasky/awesome-agent-skills/awesome-content-repurpose"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-content-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/khasky/awesome-agent-skills/awesome-content-repurpose"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-content-repurpose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 37 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00173 | $0.12583 |
| Opus 5 | $0.00086 | $0.06291 |
| Sonnet 5 | $0.00035 | $0.02517 |
| Haiku 4.5 | $0.00017 | $0.01258 |
Grade A, and why
awesome-content-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 today.
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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Repurpose
One text in, one post per platform out, each written to that platform's register rather than trimmed to its cap. Then the posts are filed, and publishing them is one more step the user chooses.
The rule that makes this skill different from writing posts from scratch: the source is the boundary. A repurposed post may sharpen, cut and reframe, but it may not add a claim, a number or an implication the source does not carry, and it may not invert the source's point by compressing it. The text arrives settled — where it came from and whether it may be published are the user's business, decided before this runs.
This skill owns the repurposing craft and orchestrates the rest. Two of its own reference files carry what every run is checked against, and both are read before a line is written:
references/authored-style.md— the register, as countable patterns: the seven opening shapes that work, the five that are banned, how much first person a run may carry, and the paragraph-shape rules that keep a post from turning into a stack of one-line fragments.references/platform-specs.md— the 26-file output contract, the hard character caps, and the depth band each platform's version is written to.scripts/gate.mjs(Node 18+, no dependencies) — the mechanical gate: every check a script can settle, in one pass, with--self-testproving each check fires before it is trusted to pass anything. Phase 5 runs it first and the judgment passes only on what survives.
Two files persist across runs in the runtime's scratch root, beside the per-run repurpose/<slug>/ folders and never in the invocation directory: repurpose/defaults.md (the interview answers from the last run) and repurpose/platform-cache.md (the last live platform check, dated). Both are the agent's own temporary files; when the runtime wipes them the run simply asks in full again.
It reuses the rest by reference rather than by restating:
references/platforms.md(ships withawesome-content-campaign) — the canonical slug table: target detail per platform, media requirements, and which genre file governs each.references/genre-micro-post.md,references/genre-long-article.md,references/genre-community-post.md(same skill) — the register each genre demands.awesome-content-graphics— the whole image stage when a post needs a picture and none exists: the look inputs, the offline HTML/CSS renders, the headline gate and the pick gate. Nothing about making graphics is reimplemented here, including the chart craft it takes fromdataviz.awesome-humanize-en,awesome-document-style,awesome-slop-audit— loaded only under--deep-audit. The part of their catalogs that applies to a feed post is written out as the Phase 4 checklist, so an ordinary run reads nine lines instead of three skills.awesome-content-voice— the author's voice, when a profile exists.awesome-content-publisher— everything about publishing: bridge, login, ledger, pacing, read-back.awesome-translate-ru-en— whenever the output language differs from the source, in either direction.
What ships with it
3 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.
- today Changed · +50 lines · +26 tokens per session 90c0557215e5
- 2d ago Changed 4cd22a98fa74
- 3d ago Changed a527970a2eb3
- 4d ago Changed · -65 tokens per session 87f87a7d7bef
- 7d ago Changed · +112 lines a7f8757771c0
- 11d ago First seen · 153 lines · 212 tokens per session scan A 733454cbe91b
awesome-content-repurpose is a skill published in the GitHub repository khasky/awesome-agent-skills (8 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 12,583 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
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
9router-web-fetch
Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
9router-web-search
Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.