Keyword research

Skill nachoal/my-skills/plugins/claude/my-skills/skills/keyword-research

Run public-safe DataForSEO keyword research, SERP checks, competitor discovery, backlink opportunity analysis, gap analysis, and SEO brief planning. Use when Codex is asked for keyword research, niche validation, search demand, CPC/difficulty data, competitor domains, content gaps, backlink prospects, SEO topic prioritization, or article briefs using DataForSEO credentials.From its SKILL.md

Install

npx -y skills add nachoal/my-skills --skill keyword-research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

reads credentialsReads from 2 credential sources: `DATAFORSEO_LOGIN` and 1 more.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 2 commands, including `python3 scripts/dataforseo_keyword_research.py --help` and 1 more.

SKILL.md

2.7 KB, 567 tokens by cl100k_base, as published. Nobody here has run it

Keyword Research

Use the bundled DataForSEO helper:

python3 scripts/dataforseo_keyword_research.py --help

Start with the smallest paid call that answers the question. Run --dry-run first when the scope or cost is unclear, and pass --yes only after the user asked for live DataForSEO data.

Default Flow

Seed demand: keyword-overview, keyword-ideas, related-keywords, or google-ads-volume.
SERP proof: serp-check for representative commercial terms.
Competitors: competitors from a known domain, or use SERP domains when no seed domain exists.
Competitor keywords: ranked-keywords / research.
Offline analysis: gap-analysis, then briefs only if content planning is requested.
Link building: backlink-opportunities only when outreach/link acquisition is in scope.

Common Commands

python3 scripts/dataforseo_keyword_research.py keyword-overview \
  --keywords "local seo services,seo automation" \
  --location 2840 --language en --dry-run

python3 scripts/dataforseo_keyword_research.py serp-check \
  --keywords "local seo services,seo automation" \
  --location 2840 --language en --yes

python3 scripts/dataforseo_keyword_research.py competitors \
  --target example.com --limit 20 --yes

python3 scripts/dataforseo_keyword_research.py ranked-keywords \
  --target example.com --limit 200 --yes

python3 scripts/dataforseo_keyword_research.py gap-analysis \
  --input dataforseo-results/ranked-keywords-latest.json \
  --min-volume 100 --max-difficulty 40

Rules

Use DATAFORSEO_LOGIN and DATAFORSEO_PASSWORD; never ask for or print secret values.
Keep examples generic unless the user provides a real project, domain, locale, or niche.
Pass locale explicitly for non-US/non-English work, for example Mexico/Spanish: --location 2484 --language es.
Review live SERP results before recommending a content plan.
Treat generated briefs as planning artifacts; do not publish content without a separate content-quality workflow.

Resources

Workflow guide: references/workflow.md
API surface map: references/dataforseo-endpoints.md
Helper script: scripts/dataforseo_keyword_research.py

Read references/workflow.md when choosing command order. Read references/dataforseo-endpoints.md when you need endpoint coverage, payload shape, or cost/safety notes.

What ships with it: 4 files

32.9 KB alongside SKILL.md, 1 of them executable

Gives 0 of the 12 instructions most plan spec skills give in 567 tokens

Counted across 1,360 of the 2,617 authors here whose files we hold, read 2026-09-06

Ask one question at a timein 73 of 1360
Write the spec using the templatein 22 of 1360
Ask clarifying questions if neededin 19 of 1360, across 18 files
Wait for user confirmation before proceedingin 19 of 1360
Save plans to the plans directoryin 17 of 1360, across 13 files
Check for product marketing context firstin 16 of 1360, across 5 files
Read the plan file completelyin 16 of 1360
Order tasks by dependencyin 16 of 1360
Gather context from the conversationin 15 of 1360, across 9 files
Explore the codebase instead of askingin 15 of 1360, across 13 files
Wait for explicit user approvalin 14 of 1360, across 13 files
Quiz the user on the breakdownin 13 of 1360, across 7 files

Said here and by no other author read

Run the smallest paid call first
Run dry run when cost is unclear
Use DATAFORSEO LOGIN and PASSWORD
Pass locale explicitly for non US work
Review live SERP results before planning

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.