yao-geo-title-optimizer

yao-geo-title-optimizer is a skill for Claude Code, Codex from yaojingang/yao-geo-skills. It costs 42 tokens per session (1,644 once invoked), scanned A, original, MIT.

A Chinese-language tool for creating and reviewing titles for content that should work well in AI search. It covers articles, pages, FAQs, comparisons, and topic hubs, which are groups of related pages on one subject.

In plain words
What is it for?
It helps generate title options, assess their quality and compliance, and connect each title with an article structure. It is designed for Chinese AI platforms such as DeepSeek, Kimi, Doubao, Yuanbao, and Tongyi Qianwen.
Why use it?
Content teams often need titles that match real user questions, search intent, evidence requirements, and compliance rules at the same time. This turns those considerations into title candidates, scores, and article mappings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps generate title options, assess their quality and compliance, and connect each title with an article structure. It is designed for Chinese AI platforms such as DeepSeek, Kimi, Doubao, Yuanbao, and Tongyi Qianwen.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yaojingang/yao-geo-skills/yao-geo-title-optimizer
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 yaojingang/yao-geo-skills --skill yao-geo-title-optimizer
Clone the repo
git clone --depth 1 https://github.com/yaojingang/yao-geo-skills

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.

agentmods badge for yao-geo-title-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-title-optimizer/github.svg)](https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-title-optimizer)
Your own site
<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-title-optimizer"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-title-optimizer/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.

agentmods 80×15 button for yao-geo-title-optimizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-title-optimizer"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-title-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,644 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01644
Opus 5 $0.00021 $0.00822
Sonnet 5 $0.00008 $0.00329
Haiku 4.5 $0.00004 $0.00164

Measured 13d ago against content hash d2778127ff7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

yao-geo-title-optimizer 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 13d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/collect_yao_geo_title_evidence.py, scripts/render_yao_geo_title_optimizer.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/yao-geo-title-optimizer/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

yao-geo-title-optimizer

Use this skill when the user needs GEO title generation, title optimization, title scoring, title compliance checks, or title-to-article-structure mapping for Chinese content production.

Do not use this skill for plain copyediting, finished article proofreading, brand slogan creation, or generic SEO metadata when the user does not need a GEO title system.

Inputs

  • Core keyword, question set, brand, competitors, target article type, region, and project date.
  • Whether year or month anchors are allowed.
  • Brand knowledge, competitor knowledge, industry dimensions, evidence sources, and compliance banned terms.
  • Target domestic AI platforms, especially DeepSeek, Kimi, Doubao, Yuanbao, and Tongyi Qianwen.
  • Optional real-data inputs: public URLs, local customer documents, exported platform answers, CMS fields, and evidence snapshots produced by scripts/collect_yao_geo_title_evidence.py.

GEO Title Logic

  1. Parse the main entity, user intent, scenario limit, and decision goal.
  2. Select title structures from list, comparison, decision, recommendation, how-to, brand validation, FAQ, and topic-hub types.
  3. Build a systematic analysis layer before writing titles: authoritative references, analysis dimensions, entity-intent matrix, evidence freshness, platform interpretation assumptions, and coverage gaps.
  4. Run real-data readiness checks: public URL reachability, evidence source freshness, unavailable private data, and platform sampling gaps.
  5. Generate varied title candidates that cover decision words, scenario hooks, evaluation dimensions, question wording, and risk-avoidance wording.
  6. Apply brand isolation. Neutral list, comparison, horizontal review, recommendation, and procurement titles must not contain the target brand or competitor names unless the user explicitly asks for branded comparison.
  7. Apply compliance filtering. Do not use unsupported absolute claims or unsupported recency claims such as "best", "latest", "first", "only", "authoritative", "industry standard", "guaranteed inclusion", or equivalent Chinese terms.
  8. Score titles on intent match, entity clarity, differentiation, citation potential, compliance, and freshness.
  9. Map each title to an article structure, evidence blocks, FAQ prompts, platform sampling plan, and publication checks.

Read the full file on GitHub · 136 lines

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.

  1. 13d ago First seen · 136 lines · 42 tokens per session scan A d2778127ff7f

Subscribe to this mod's changes

yao-geo-title-optimizer is a skill published in the GitHub repository yaojingang/yao-geo-skills (742 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,644 once invoked, about $0.0002 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.