Meta Tags Optimizer

Optimize title tags, meta descriptions, Open Graph, Twitter cards for maximum CTR with A/B variations. 标题优化/元描述/CTR

Security Scan

The skill is an instruction-only SEO/meta-tag generator whose requirements and behavior are consistent with its stated purpose — nothing in the package requests unrelated credentials, installs, or obscure endpoints.

Purpose & Capability

The name/description match the runtime instructions and reference materials: all steps, templates, and output targets are about title tags, meta descriptions, Open Graph/Twitter cards, CTR tips, and A/B recommendations. No unrelated capabilities (cloud access, system administration, or secret handling) are requested.

Instruction Scope

The SKILL.md instructs the agent to read optional repo/state documents when available and to write deliverables and summaries to agent memory paths (memory/content/, memory/hot-cache.md, memory/decisions.md, memory/open-loops.md). Those reads/writes are coherent with a content-generation skill but are worth noting: the skill will persist outputs to the agent's memory and will try to pull CTR/competitor data automatically only if connectors are configured.

Install Mechanism

No install spec or code files are present; this is instruction-only. That minimizes on-disk persistence and arbitrary code execution risk.

Credentials

The skill declares no required environment variables or credentials. It mentions optional Search Console/SEO tool connectors for automatic CTR/competitor pulls — those are optional and would require credentials if enabled, but they are not demanded by the skill itself.

Persistence & Privilege

The skill writes outputs into agent memory on user confirmation and promotes findings to memory caches. This is expected for a content/hand-off skill. It is not marked always:true, and it does not request elevated or cross-skill configuration changes.

Assessment

This skill appears to do exactly what it says: generate optimized meta tags and social tag HTML. Before installing, confirm how your agent handles 'memory/*' writes (will these saved files be visible to other skills or exported?), and be deliberate about enabling any optional connectors (Search Console, SEO tools) — those require separate credentials and will enable external data pulls. Do not paste sensitive credentials or private content into prompts if you do not want them saved to agent memory. If you rely on automatic CTR/competitor pulls, verify which connector implementations will be used and review their required credentials and privacy policies.

Creates title tags, meta descriptions, and social meta tags that improve CTR and sharing quality.

Quick Start

Create meta tags for a page about [topic] targeting [keyword]

Improve these meta tags for better CTR: [current tags]

Skill Contract

Expected output: a ready-to-use metadata package plus the standard handoff summary for memory/content/.

• Reads: the brief, target keywords, entity inputs, quality constraints, and prior decisions from CLAUDE.md and the shared State Model when available.
• Writes: a user-facing metadata deliverable and reusable summary.
• Promotes: approved angles, messaging choices, missing evidence, and publish blockers to memory/hot-cache.md, memory/decisions.md, and memory/open-loops.md.
• Primary next skill: schema-markup-generator when the metadata package is ready for structured-data support.

Handoff Summary

Emit the standard shape from skill-contract.md §Handoff Summary Format.

Data Sources

Optional search console and SEO tool integrations pull CTR data and competitor patterns automatically; otherwise ask for current tags, keywords, and competitors. See CONNECTORS.md.

Instructions

When a user requests meta-tag optimization, run these six steps:

1. Gather Page Information — URL, page type, primary and secondary keywords, audience, CTA, and value proposition.
2. Create Optimized Title Tag — keep it near 50-60 characters, front-load the keyword, and generate three options using the supported title formulas.
3. Write Meta Description — target 150-160 characters, include the keyword and CTA, and generate three options.
4. Create Open Graph, Twitter Card, and Additional Meta Tags — include OG, Twitter, canonical, robots, viewport, author, and article tags as needed.
5. CORE-EEAT Alignment Check — verify C01 (Intent Alignment) and C02 (Direct Answer).
6. Provide CTR Optimization Tips — explain the winning elements, tradeoffs, and A/B test options.

Reference: See references/instructions-detail.md for the compact workflow, formulas, alignment matrix, CTR analysis, and example. See references/meta-tag-code-templates.md for HTML blocks.

Example

Sample outcome: a 55-character title, a 150-160 character description, and a complete OG / Twitter / Article tag block. See the full worked sample in references/instructions-detail.md.

Tips for Success

Front-load keywords, match intent, be specific, test variations, and refresh tags when the SERP changes.

Save Results

On user confirmation, save memory/content/YYYY-MM-DD-<topic>.md and promote key conclusions to memory/hot-cache.md.

Reference Materials

• Instructions Detail — Workflow, formulas, alignment matrix, example
• Meta Tag Formulas — Title and description formulas
• Meta Tag Code Templates — HTML templates
• CTR and Social Reference — CTR patterns and social guidance

Next Best Skill

• Primary: schema-markup-generator — complete the SERP package with structured data.