What is skill-seo-quality?

A search-optimisation checker for content published on Chinese social platforms and, optionally, websites or blogs. It reviews whether titles, text, tags, and cover or opening-frame words contain terms people may search for.

Use it to review or improve keywords, tags, titles, and visual text before publishing on platforms such as Xiaohongshu, Douyin, Zhihu, WeChat, Bilibili, and Weibo.

It helps address the problem of content being hard to find through platform search. It also distinguishes search visibility from recommendation-based exposure.

skill-seo-quality — Skill for Claude Code and Codex by ZJU-REAL

Install

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.

Any agent

npx skills add ZJU-REAL/Easel --skill skill-seo-quality

Clone the repo

git clone --depth 1 https://github.com/ZJU-REAL/Easel

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zju-real/easel/skill-seo-quality/github.svg)](https://agentmods.dev/skills/zju-real/easel/skill-seo-quality)

Your own site

<a href="https://agentmods.dev/skills/zju-real/easel/skill-seo-quality"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-seo-quality/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zju-real/easel/skill-seo-quality"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-seo-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,533 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00166	$0.01533
Opus 5	$0.00083	$0.00766
Sonnet 5	$0.00033	$0.00307
Haiku 4.5	$0.00017	$0.00153

Measured 8d ago against content hash 33786d102a1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-seo-quality 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 8d 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.

skills/openclaw/skill-seo-quality/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

平台原生搜索优化

让内容能被平台搜索到、排得靠前。以国内内容平台的站内搜索机制为主体，网页/博客 web SEO 作为可选模式。

定位

国内平台的流量分两条路：推荐流量（算法主动分发）和搜索流量（用户主动搜关键词命中）。多数创作只优化推荐，忽略搜索——而搜索流量精准、长尾、可累积。本 SKILL 专治搜索这条路：让标题、正文、标签、封面文字都踩中用户会搜的词。

推荐流量的钩子/完播/互动优化不在此列，交给 social-content / video-script。

输入

待检查的内容（文件路径、文本、或已发布链接）
目标平台（小红书 / 抖音 / 知乎 / 公众号 / B站 / 微博；缺省时询问或按 Profile）
可选：目标关键词 / 想覆盖的搜索场景、检查侧重（发布前校验 / 关键词补强 / 全面优化）

输出

# 搜索优化报告 — [平台]

## 目标关键词命中盘点
| 关键词/搜索场景 | 出现位置（标题/正文/标签/封面） | 权重 | 状态 |

## 逐项校验（针对该平台的搜索信号）
| 检查项 | 状态 ✅/⚠️/❌ | 说明 | 修改建议 |

## 搜索 vs 推荐取舍诊断
（当前内容偏向哪条流量、是否需要为搜索让渡一部分推荐钩子）

## 整体评级：✅ 可发布 / ⚠️ 需修改 / ❌ 搜索面太窄
## 优先修改项（Top 3，按预期搜索曝光增益排序）

执行步骤

读取内容 — 取全文、标题、标签/话题、封面或首帧文字（视频取标题+简介+字幕关键帧）。
确定平台与目标词 — 无目标词时，从内容主题反推用户可能搜的关键词与长尾词（谁在搜、搜什么、用什么说法）。
加载平台规则 — 读 references/platform-search.md 中对应平台的搜索信号与关键词布局规则。
逐项校验 — 按该平台规则打分：关键词是否前置、密度是否自然、标签是否踩中搜索热词、封面/首帧是否含可搜文字。
诊断流量取舍 — 判断内容当前偏推荐还是搜索，给出为搜索补强而不牺牲可读性的改法。
（可选）网页/博客模式 — 内容是公众号被百度收录的长文、知乎要冲搜索引擎、或独立站/博客时，读 references/web-blog-seo.md 追加 web SEO 校验。
排优先级并写产物 — 选出增益最大的 Top 3，保存到 outputs/<具体主题>/seo-report.md。

平台速览

各平台搜索机制差异很大，详细规则见 references/platform-search.md。核心分歧：

平台	搜索入口	最关键的搜索信号
小红书	站内搜索框	标题+正文关键词、话题标签、封面文字、收藏量
抖音	搜索 + 视频推荐搜索卡位	标题/文案关键词、话题词、完播与互动
知乎	站内搜索 + 百度/谷歌收录	问题匹配、回答质量信号；web SEO 在此适用
公众号	微信搜一搜	标题关键词、原创标、账号权重、被搜历史
B站	站内搜索	标题/tag/简介关键词、播放与完播
微博	话题/超话/热搜	话题词 #、时效性、互动量

适用边界：Meta 描述、Open Graph、URL/Slug、H1/H2 层级、E-E-A-T 这类 web SEO 只对"会被搜索引擎（百度/谷歌）抓取"的内容有效——知乎回答、独立站/博客、被外部收录的公众号文章。纯站内内容（小红书/抖音/B站/微博）不吃这套，别套。

检查原则

关键词前置 — 用户搜索时系统优先匹配靠前的词；标题前段、正文首句放核心词。
说人话的词 — 命中用户真实搜索用语，而非行业黑话或自造词。
密度自然 — 关键词覆盖到位即可，堆砌反而被判低质、限流。
标签是搜索权重不是装饰 — 话题标签直接进搜索索引，选高搜索量且相关的。
封面/首帧可被搜 — 部分平台 OCR 封面文字进索引，封面文案也要含关键词。
搜索与推荐可兼得 — 优先在不牺牲钩子和可读性的前提下补关键词，冲突时按内容目标取舍。

Profile 感知

有 Profile：读 platform 锁定平台规则；读 audience 反推该人群的搜索用语；读账号常用 hashtag_sets 优先复用高权重标签；读 preferences 规避红线词。
无 Profile：询问目标平台与想覆盖的搜索场景，按 references/platform-search.md 通用规则校验，末尾附注"提供账号 Profile 可获得更贴合受众搜索习惯的关键词建议"。

Read the full file on GitHub · 85 lines

Files

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.

Changes

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.

8d ago First seen · 85 lines · 166 tokens per session scan A 33786d102a1b

Subscribe to this mod's changes

skill-seo-quality is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 166 tokens to every session and 1,533 once invoked, about $0.0008 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 2026-09-03.

Marketing and SEO agent agent-skill content-automation content-creation content-generation mcp

python-run

Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.

congchuanling-dot/Cohort · 56 tokens

roadtrip-navigator

Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…

Waybox-AI/roadtrip-skill · 106 tokens

skill-seo-quality