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 Orkas-AI/Orkas-Awesome-AgentSkills --skill social-writergit clone --depth 1 https://github.com/Orkas-AI/Orkas-Awesome-AgentSkillsWrote 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/orkas-ai/orkas-awesome-agentskills/social-writer)<a href="https://agentmods.dev/skills/orkas-ai/orkas-awesome-agentskills/social-writer"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/social-writer/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/orkas-ai/orkas-awesome-agentskills/social-writer"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/social-writer.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 | $0.00003 | $0.01463 |
| Opus 5 | $0.00002 | $0.00732 |
| Sonnet 5 | $0.00001 | $0.00293 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade A, and why
social-writer 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Writer
When to Use
Use this skill when the user wants to create, improve, plan, or respond with social media content.
Use for:
- creating Chinese social drafts for Xiaohongshu, WeChat Official Account, Zhihu, Douyin/Kuaishou, Weibo, and similar platforms.
- creating global single posts for X, LinkedIn, Instagram, TikTok, and similar platforms.
- optimizing an existing social draft before posting.
- planning weekly, monthly, or campaign content calendars.
- drafting replies to negative comments, complaints, misunderstandings, and public social issues.
Do not use this skill to operate platform backends, save drafts, click publish, upload media, or perform final legal/public-relations approval.
Choose The Mode
| Mode | Use when | Output |
|---|---|---|
create |
user wants a new post, note, answer, article, caption, or script | platform-native draft |
optimize |
user has an existing draft | score, diagnosis, rewrites, checklist |
calendar |
user wants a week/month/campaign plan | content calendar with topics and production needs |
respond |
user asks how to reply to comments, complaints, or crisis content | risk level, response draft, escalation plan |
Workflow
- Identify platform and mode:
- Chinese platforms: Xiaohongshu, WeChat Official Account, Zhihu, Douyin/Kuaishou, Weibo, Bilibili.
- Global platforms: X, LinkedIn, Instagram, TikTok.
- If no platform is specified, ask for the target platform or produce a platform comparison.
- Confirm content inputs:
- topic, audience, goal, brand voice, source material, product claims, forbidden claims, media availability, and desired action.
- for existing drafts: current title, body, cover/visual description, tags, and performance data if available.
- for calendars: date range, cadence, pillars, key dates, resource constraints, review capacity.
- for responses: original comment/complaint, context, platform, history, support facts, and risk indicators.
- Run a fact and safety pass:
- do not invent personal experience, customer reviews, test results, screenshots, income, health results, legal outcomes, or third-party endorsements.
- mark data, claims, prices, policies, and references that need verification.
- high-risk domains need human review.
- Generate platform-native output:
- Xiaohongshu: title, cover text, hook, short sections, save/comment CTA, 5-10 tags.
- WeChat: title, opening, 3-5 sections, full body, closing, share/follow CTA.
- Zhihu: answer directly, reason carefully, include evidence and caveats, avoid hard-sell tone.
- Douyin/Kuaishou/TikTok: first 1-3 seconds, spoken script, screen text, scene notes, caption, tags.
- Weibo/X: concise point, clear hook, native topic/tag use, low-friction interaction.
- LinkedIn: first two lines, story or insight, transferable lesson, CTA, 3-5 tags if useful.
- Instagram: visual-first caption, save/share CTA, relevant hashtags.
- For
optimize:- score title/first screen, visual/cover, structure, platform fit, interaction/CTA.
- identify the top 3 issues and give concrete rewrites.
- For
calendar:- balance pillars, platform rhythm, key dates, flexible slots, and production capacity.
- create specific topics, not vague labels.
- For
respond:- classify as complaint, fair criticism, misunderstanding, bad-faith attack, coordinated attack, or legal/safety/privacy/regulatory issue.
- rate severity: low, medium, high, critical.
- draft only for human approval; do not publish.
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 · 175 lines · 3 tokens per session scan A 3d4a51b2c38a
social-writer is a skill published in the GitHub repository Orkas-AI/Orkas-Awesome-AgentSkills (13 stars, last pushed 2mo ago), licensed MIT. It adds 3 tokens to every session and 1,463 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
viral-tech-reel-editor
End-to-end viral tech reel production for Instagram Reels and TikTok using 2026 trend grammar — retention-first pacing, punch-ins, 3D cinematic AI-generated shots, motion design graphics, proof b-roll, trending SFX, karaoke captions (Georgian/English), safe-zone layout, and QA-gated 1080x1920 export. This skill should…
implementing-aws-config-rules-for-compliance
Implementing AWS Config rules for continuous compliance monitoring of AWS resources, deploying managed and custom rules aligned to CIS and PCI DSS frameworks, configuring automatic remediation with SSM Automation, and aggregating compliance data across accounts.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.
auto-qa
QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence.