Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Hao0321/claude-skill-social-postnpx agentmods add skills/hao0321/claude-skill-social-post/social-postWrote 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/hao0321/claude-skill-social-post/social-post)<a href="https://agentmods.dev/skills/hao0321/claude-skill-social-post/social-post"><img src="https://agentmods.dev/badge/skills/hao0321/claude-skill-social-post/social-post/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/hao0321/claude-skill-social-post/social-post"><img src="https://agentmods.dev/badge/skills/hao0321/claude-skill-social-post/social-post.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00135 | $0.04530 |
| Opus 5 | $0.00068 | $0.02265 |
| Sonnet 5 | $0.00027 | $0.00906 |
| Haiku 4.5 | $0.00014 | $0.00453 |
Grade A, and why
social-post 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Post
把內容生成、實際發布與成效學習分開。依意圖只讀必要資料，不把整個案例庫一次塞進 context。
P5 執行前先核對 references/chrome-comment-adapter.md 的當前狀態：舊 SDK 的 IG 單則 canary 已完成真實送出及唯讀 recovery 對帳；2026-09-05 當前 CUA 的 Threads 單則 canary 已送出一次並取得原生 own-child 正向觀測，canonical ledger 尚為 needs_reconcile。exact-tab recovery 來源修正已通過 focused tests；當前 Chrome 控制連線無法進行原生檢查，真實唯讀結算尚待恢復連線後完成，未新增 recovery／rotation 事件。當前 CUA 送出只支援 Threads 單則候選，泛用 production 仍關閉。target-only 不代表整篇／回覆串已掃完，semantic UI continuity 不代表實體 document epoch 或持久 node identity。單則實證不代表三平台完整自動回覆完成，也不會自動升級 capability；不得用 fixture 或候選程式存在代替其他真實送出證據。
Session 啟動
P2 預設讀 voice_quick.md；只有 P1 重新學語氣、使用者明確要求深度仿寫，或 quick card 無法裁決時，才完整讀 style_profile.md 或使用者明確指定的 voice Skill。安全與使用者明示 > voice quick／明確指定的 voice Skill > 公式。
路由
| 觸發 | Mode | 必讀 |
|---|---|---|
| 重新規劃、排內容 | P0 Plan | references/phase0_plan.md＋current_brief.md＋scripts/social_data.py comparables compact context＋目標 formula |
| 重新學語氣 | P1 Learn Voice | references/learn_style.md＋style_profile.md |
| 寫一篇、PO、發文 | P2 Draft／Publish | references/generate_and_publish.md＋voice_quick.md＋current_brief.md＋scripts/social_data.py comparables compact context＋單一 formula；確認後才讀平台 ref |
| 把數據訓練進來、記錄成效 | P3 Log Outcome | references/outcome-workflow.md＋data/*.jsonl |
| 比較貼文／集數、找 pattern | P4 Optimize Patterns | references/outcome-workflow.md＋references/evaluation.md＋相關 rules |
| 掃描、草擬、回覆 FB／IG／Threads 留言 | P5 Comment Ops | references/comment-operations.md＋實際操作時的 references/chrome-comment-adapter.md＋scripts/comment_chrome_actuator.mjs＋references/comment-policy.json＋目標平台 ref＋voice_quick.md |
| 查歷史 Case | Legacy Case | references/case_studies.md 索引，再讀單一 references/cases/case-NN.md |
路由前用一句話告知正在做哪個 Mode。單純診斷不需要 Chrome。
Source of truth
| 資料 | Canonical source |
|---|---|
| 貼文／caption／發布條件 | data/posts.jsonl |
| 洞察快照 | data/insight_snapshots.jsonl |
| 帳號期間總覽 | data/account_snapshots.jsonl |
| 跨篇假設與 confound | data/experiments.jsonl |
| 事實修正事件 | data/corrections.jsonl；原始 event 不覆寫 |
| 規則正文 | references/rules/RNN.md；references/rules.md 是索引 |
| 規則生命週期／實驗 backlink | references/rules/metadata.json |
| 規則機器索引 | data/rule_registry.json（生成檔） |
| 舊案例全文 | references/cases/ |
| Chrome 可見留言 observation | data/comment_events.jsonl；私人 append-only ledger |
| Chrome 掃描目標／期限 | data/browser_scan_requests.jsonl；私人 append-only ledger，先建立再掃描 |
| 回覆草稿／permit／送出／對帳 | data/reply_events.jsonl；私人 append-only ledger |
| 留言自動化政策 | references/comment-policy.json |
| 產品能力完成度／外部 canary | 私版 .rd/capability-ledger.json 是唯一 canonical ledger；comment-capabilities.json 只是 hash-bound 生成式公開投影，fixture 與 live 分開 |
What ships with it
60 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.
- .social-post-managed.json 7.6 KB
- agents/openai.yaml 255 B
- comment-capabilities.json 4.7 KB
- content_plan.example.md 2.3 KB
- current_brief.md 1.1 KB
- data/rule_registry.json 2.0 KB
- references/case_studies.md 413 B
- references/cases/case-01.md 417 B
- references/cases/manifest.json 249 B
- references/chrome-comment-adapter.md 37 KB
- references/chrome-comment-runtime.md 6.8 KB
- references/chrome-comment-validation.md 18 KB
- references/comment-operations.md 29 KB
- references/comment-policy.json 1.0 KB
- references/correction-bundle.example.json 311 B
- references/evaluation.md 1.3 KB
- references/facebook.md 1.2 KB
- references/formulas.md 552 B
- references/formulas/F01.md 153 B
- references/formulas/F02.md 145 B
- references/formulas/F03.md 162 B
- references/formulas/F04.md 170 B
- references/formulas/F05.md 176 B
- references/formulas/manifest.json 523 B
- references/generate_and_publish.md 3.6 KB
- references/instagram.md 1.1 KB
- references/learn_style.md 805 B
- references/outcome-bundle.example.json 1.5 KB
- references/outcome-workflow.md 9.0 KB
- references/phase0_plan.md 2.4 KB
- references/rules.md 964 B
- references/rules/manifest.json 1.6 KB
- references/rules/metadata.json 537 B
- references/rules/R01.md 206 B
- references/rules/R02.md 202 B
- references/rules/R03.md 168 B
- references/rules/R04.md 221 B
- references/rules/R05.md 191 B
- references/rules/R06.md 159 B
- references/rules/R07.md 214 B
- references/rules/R08.md 191 B
- references/threads.md 936 B
- references/x.md 1.8 KB
- references/youtube.md 812 B
- scripts/build_rule_registry.py 3.3 KB runs code
- scripts/comment_adapter_fixtures/facebook.html 3.3 KB
- scripts/comment_adapter_fixtures/fixture-runtime.js 6.5 KB runs code
- scripts/comment_adapter_fixtures/instagram.html 3.2 KB
- scripts/comment_adapter_fixtures/threads.html 3.3 KB
- scripts/comment_assistant.py 19 KB runs code
- scripts/comment_authorization.py 9.2 KB runs code
- scripts/comment_browser_action_contract.py 8.6 KB runs code
- scripts/comment_browser_cli.py 25 KB runs code
- scripts/comment_browser_common.py 9.9 KB runs code
- scripts/comment_browser_contract.py 1.7 KB runs code
- scripts/comment_browser_preflight_contract.py 10 KB runs code
- scripts/comment_browser_provenance.py 12 KB runs code
- scripts/comment_browser_result_contract.py 9.1 KB runs code
- scripts/comment_browser_scan_completion.py 6.6 KB runs code
- scripts/comment_browser_scan_contract.py 7.2 KB runs code
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.
- 3d ago Changed · +2 lines 627d832f8fd2
- 5d ago Changed · +2 lines f01921f48cad
- 9d ago First seen · 122 lines · 135 tokens per session scan A d376c86b2af6
social-post is a skill published in the GitHub repository Hao0321/claude-skill-social-post (663 stars, last pushed 3d ago), licensed MIT. It adds 135 tokens to every session and 4,530 once invoked, about $0.0007 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
comfyui
Drive a local ComfyUI install for image, video, and audio generation via its HTTP API. Use WHENEVER generating, rendering, or editing images/video/audio/hero assets with ComfyUI, Z-Image, Ideogram, FLUX, LTX, Wan, or when building, parameterizing, or running ComfyUI workflows. Covers the API client, workflow JSON…
minimax-h3
Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off…
hue
Meta-skill that generates new design language skills. Works on Claude Code and Codex. Use when the user says 'create a design skill', 'generate design language', 'new design system skill', 'design skill inspired by X', 'design skill from this screenshot', '/hue', or 'use hue'. Also triggers for 'remix my design skill'…
dashmotion
Create dark-themed, animated technical diagrams as self-contained HTML+SVG files — flowcharts whose connectors visibly flow, and architecture diagrams where requests travel as light dots through the system (Diagrid/Temporal landing-page style). Use this skill whenever the user asks for a flowchart, workflow, pipeline…
anydesign
Analyze images, websites, and Figma files to extract their design and generate a design.md with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest…
story
Track tickets, issues, and progress for your project. Load project context, manage sessions, guide setup.