Keyword Research

Find high-value SEO keywords: search volume, difficulty, intent classification, topic clusters. 关键词研究/内容选题

Security Scan

The skill is an instruction-only keyword-research workflow that is internally consistent with its description and does not request extra credentials or install anything unusual.

Purpose & Capability

The name/description (keyword research, search volume, difficulty, intent, clusters) match the SKILL.md instructions. The skill explicitly supports working without external tools (asks the user for seeds/metrics) and optionally integrates with SEO tools/search console when available. It does not declare unrelated environment variables or binaries.

Instruction Scope

Instructions are a structured 8-phase research workflow and reference only project docs (CLAUDE.md, state model) and internal memory paths. It also suggests checking live SERPs and optional SEO tool integrations; since no connectors or credentials are declared, the agent will need the user to provide data or use platform connectors. The skill will offer to write results to memory files — users should be aware of persistent storage of research outputs.

Install Mechanism

No install spec and no code files — this is instruction-only, so nothing is downloaded or written to disk during install. This is the lowest-risk install profile.

Credentials

The skill requests no environment variables, credentials, or special config paths. Optional integrations are mentioned but not required; any connector credentials would need to be supplied separately by the user.

Persistence & Privilege

always:false and autonomous invocation not disabled (normal). The skill encourages saving outputs to persistent memory (memory/research/, memory/hot-cache.md). This is expected for research workflows but users should confirm they are comfortable with the agent storing delivered research and decisions in persistent memory.

Scan Findings in Context

[no_code_to_scan] expected: The regex scanner had no code files to analyze because this is an instruction-only skill; the SKILL.md and reference docs are the runtime surface.

Assessment

This skill is a coherent, instruction-only keyword-research workflow and does not install software or ask for credentials by default. Before enabling: 1) Decide whether you want the agent to persist research outputs — the skill will offer to write to memory/research and memory/hot-cache.md. 2) If you want live search volumes or difficulty metrics, be prepared to provide connector credentials (e.g., Ahrefs/SEM/Google Search Console) or raw data, because the skill itself doesn't include connectors or secrets. 3) If you have sensitive project files you do not want read or stored, avoid granting the agent broad file-access or persistent memory consent. Overall the footprint is proportional to its purpose.

Discovers, scores, and clusters keywords for SEO and GEO planning.

Quick Start

Research keywords for [topic/product/service]

What keywords is [competitor URL] ranking for that I should target?

Skill Contract

Expected output: a prioritized keyword brief plus the standard handoff summary for memory/research/.

• Reads: goals, market inputs, tool data, and prior strategy from CLAUDE.md and the shared State Model when available.
• Writes: a user-facing research deliverable and reusable summary.
• Promotes: durable keyword priorities, competitor facts, and strategy decisions to memory/hot-cache.md, memory/decisions.md, and memory/research/.
• Primary next skill: competitor-analysis when the keyword set is ready for market comparison.

Handoff Summary

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

Data Sources

Optional integrations: ~~SEO tool, ~~search console. Without tools, ask for seed keywords, audience, goals, and any known metrics. See CONNECTORS.md.

Instructions

When a user requests keyword research, run eight phases and announce each as [Phase X/8: Name]:

1. Scope — clarify product, audience, business goal, DR, geography, and language.
2. Discover — seed from core, problem, solution, audience, and industry terms.
3. Variations — expand with modifiers and long-tail patterns.
4. Classify — tag by intent (informational, navigational, commercial, transactional).
5. Score — assign difficulty (1-100) and compute Opportunity = (Volume × Intent Value) / Difficulty, with Intent Value 1 / 1 / 2 / 3.
6. GEO-Check — flag AI-answer-friendly queries such as questions, definitions, comparisons, lists, and how-tos.
7. Cluster — group keywords into pillar + cluster topic hubs.
8. Deliver — output an Executive Summary, Quick Wins / Growth / GEO opportunities, Topic Clusters, Content Calendar, and Next Steps.

Quality bar: every recommendation includes at least one specific number. Rewrite generic advice into a concrete keyword + volume + difficulty + reason.

Reference: See references/instructions-detail.md for the full 8-phase templates, expansion patterns, intent table, difficulty tiers, opportunity matrix, GEO indicators, cluster template, actionable-vs-generic examples, and advanced usage.

Example

Example outcome: 150+ keywords analyzed, 23 high-priority opportunities, ~45K/month traffic potential across 3 focus areas. See the full sample in references/example-report.md.

Advanced Usage

Intent mapping, seasonal analysis, competitor gaps, and local keyword workflows live in references/instructions-detail.md.

Tips for Success

Start with seeds, respect intent, cluster tightly, prioritize quick wins, and review quarterly. Full notes live in references/instructions-detail.md.

Save Results

After delivering, offer to save memory/research/keyword-research/YYYY-MM-DD-<topic>.md and promote durable conclusions to memory/hot-cache.md.

Reference Materials

• Instructions Detail — Workflow, scoring, cluster template, advanced usage
• Keyword Intent Taxonomy — Intent signals and content mapping
• Topic Cluster Templates — Pillar and cluster patterns
• Keyword Prioritization Framework — Scoring and prioritization rules
• Example Report — Worked sample

Next Best Skill

Primary: competitor-analysis. Also: content-gap-analysis and serp-analysis.