跳到正文
cccskills
免费在 GitHub 公开

local-seo-optimizer

Get a local business found on Google -- audit and optimize the Google Business Profile, local pack ranking factors, review velocity, NAP consistency across directories, and location pages. For businesses whose customers search "near me," this outranks everything else in marketing.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Local SEO Optimizer

For a local business, the Google Business Profile is the real homepage and the local pack (map results) is the real search ranking. This skill audits the three local ranking pillars -- relevance, distance, prominence -- and produces the fix list. Complements seo-optimizer (content/on-page SEO); this is the maps-and-profile layer.

Workflow

  1. Baseline. Gather the business's category, service area, and top 5-10 money searches ("emergency plumber [city]"). Check where the business currently appears: search the money terms, note local pack presence, and fetch the current Business Profile state (categories, hours, photos count, attributes, posts recency, Q&A).
  2. Profile audit. Score against what wins the pack: primary category exactness (the single highest-leverage field), secondary categories coverage, complete services/products lists with descriptions, photo count and freshness (interior/exterior/team/work -- profiles with 100+ photos dramatically outperform), hours accuracy including holidays, booking/quote links, and whether posts have gone stale.
  3. Review engine. Review count, average, velocity vs. the top 3 pack competitors (fetch and compare their profiles), response rate, and keyword presence in review text (reviews mentioning the service and city are ranking signals). Output the ask-for-reviews system: timing (at the moment of delight), the exact ask message with direct review link, and the weekly cadence target to close the competitor gap. Pair with review-response-writer for the response side.
  4. NAP sweep. Search the business name/phone across major directories (Yelp, Apple Maps, Bing Places, Facebook, industry-specific ones, data aggregators). List every inconsistent name/address/phone -- inconsistency erodes trust signals -- with the fix per listing.
  5. Website local layer. Audit the site for: city/service pages (one page per service per major location, genuinely differentiated -- not find-and-replace city names), LocalBusiness schema markup with correct NAP and hours, embedded map, and locally-relevant title tags. Output the page-by-page fix list, with drafts for the highest-value gaps.

Rules

  • Primary category first, always -- it is worth more than everything else on the profile combined.
  • Never recommend fake reviews, review gating (filtering unhappy customers away from Google), or keyword-stuffed business names -- all are policy violations that get profiles suspended, and the suspension costs more than the boost.
  • Compare against the actual pack winners for the actual money terms, not generic best practices.
  • Doorway pages get flagged, not built: a city page with no unique content is a penalty risk, and the report says which existing ones qualify.
  • Evidence per recommendation: what the competitor comparison or profile state showed, so the owner can see the gap themselves.
  • Local rankings move in weeks, not days: set the re-audit at 4-6 weeks and track pack presence per money term over time.

Quick Commands

  • "Audit [business name, city]" -- full workflow
  • "Why is [competitor] outranking me?" -- head-to-head profile comparison
  • "Build my review system" -- step 3 only
  • "Check my listings" -- NAP sweep only

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

查看 OneWave-AI 的全部技能

报告此技能的问题