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 xiaomaolu/bluue-ai-skills --skill social-content-enginegit clone --depth 1 https://github.com/xiaomaolu/bluue-ai-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/xiaomaolu/bluue-ai-skills/social-content-engine)<a href="https://agentmods.dev/skills/xiaomaolu/bluue-ai-skills/social-content-engine"><img src="https://agentmods.dev/badge/skills/xiaomaolu/bluue-ai-skills/social-content-engine/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/xiaomaolu/bluue-ai-skills/social-content-engine"><img src="https://agentmods.dev/badge/skills/xiaomaolu/bluue-ai-skills/social-content-engine.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 | $0.00129 | $0.01935 |
| Opus 5 | $0.00064 | $0.00967 |
| Sonnet 5 | $0.00026 | $0.00387 |
| Haiku 4.5 | $0.00013 | $0.00194 |
Grade A, and why
social-content-engine 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 11d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Content Engine
Turn a social-content request into a publishable result through a compact internal pipeline. Treat this directory as one installable skill bundle with modular internal capabilities. The user should not need to know or invoke the modules separately.
The central rule is:
The less context the user supplies, the more useful internal work the skill should perform before writing. A short prompt is never a reason to produce generic filler.
Defaults
Unless the user overrides them:
- Task: infer from the request
- Output count: one strongest result
- Output language: resolve with references/multilingual.md
- Platform: infer only when explicit or strongly implied; otherwise use the generic adapter
- Research: only when freshness, factual precision, or requested evidence requires it
- Angle: select one specific angle internally; do not dump many near-duplicates
- Tone: natural, specific, restrained, platform-native
- Personal experience: never invent
- Hashtags: omit unless useful for the destination platform or requested
- CTA: optional; never force one
- Review cycles: maximum 2
- Research retry: maximum 1
- Angle retry: maximum 1
- Writer retry: maximum 2
Supported tasks
Normalize the primary task to one of:
createrewriteoptimizereplycommentaryrepurposesummarizeeducatepromotebrainstormthreadscript
Secondary intents may coexist, such as create + promote or repurpose + translate.
Supported platforms
Read references/platforms.md when a platform-specific result is requested.
Built-in profiles include:
- X / Twitter
- Threads
- TikTok / Douyin / Reels
- YouTube Shorts / long-form
- Xiaohongshu / RED
- Telegram / Discord
- Generic / unknown social platform
If the requested platform is missing, use the generic profile and infer only observable format requirements. Do not pretend to know undocumented platform conventions.
What ships with it
19 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.
- agents/openai.yaml 429 B
- modules/angle-discovery.md 2.5 KB
- modules/context-enrichment.md 2.8 KB
- modules/hook-optimizer.md 1006 B
- modules/platform-adapter.md 2.0 KB
- modules/repurpose.md 1.2 KB
- modules/research.md 3.7 KB
- modules/review.md 2.3 KB
- modules/router.md 3.8 KB
- modules/style-profile.md 1.5 KB
- modules/writer.md 2.8 KB
- README.md 2.7 KB
- references/anti-slop.md 2.2 KB
- references/error-codes.md 1.8 KB
- references/multilingual.md 4.9 KB
- references/platforms.md 4.1 KB
- references/source-policy.md 1.7 KB
- references/state-schema.md 2.4 KB
- references/test-cases.md 3.6 KB
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.
- 11d ago First seen · 251 lines · 129 tokens per session scan A b0b02538fb6f
social-content-engine is a skill published in the GitHub repository xiaomaolu/bluue-ai-skills (6 stars, last pushed 3d ago), licensed MIT. It adds 129 tokens to every session and 1,935 once invoked, about $0.0006 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…