SEO Prospect

What it does

When your agent uses it

• Tasks that involve Link building
• Tasks that involve Local SEO

Example prompts

• “<niche <city”
• “/seo-prospect”

Requirements

• Pre-approved tools (allowed-tools): Bash, Write

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Parse login: and password: from their message.
2. 2Write them to ~/.claude/skills/seo/.env
3. 3chmod 600 ~/.claude/skills/seo/.env
4. 4Run a verification call: ~/.claude/skills/seo/scripts/keyword_research.py volume "test"
5. 5If verification succeeds: tell the user "✅ Credentials verified. Running your command now..." and proceed.
6. 6If status 40104 — Please verify your account: tell the user to verify their account at https://app.dataforseo.com/, then say "continue" to…
7. 7If any other auth error: ask them to double-check the API password from https://app.dataforseo.com/api-access.

What it can do on your machine

Read from SKILL.md and the folder at commit 67ac4f0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Write

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • dataforseo.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • DATAFORSEO_PASSWORD

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

SEO Prospect loads about 1.5k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 445 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~100

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:29

  2. Write them to `~/.claude/skills/seo/.env`:

• NoteMentions a .env fileSKILL.md:34

  3. `chmod 600 ~/.claude/skills/seo/.env`

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Write

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zubair-trabzada/dataforseo-claude at commit 67ac4f0, republished under its MIT licence (© zubair-trabzada). 445 words, ~1,452 tokens.

name

seo-prospect

description

Find local-business SEO prospects in a single command. Searches Google for "<niche> <city>", filters out aggregators (Yelp, Yellow Pages, Angi), enriches each remaining domain with DataForSEO Labs domain overview, On-Page technical audit, and Backlinks summary in parallel, then ranks the businesses by a closeability score (0-100) — highest scores are the easiest to land as SEO clients.

allowed-tools

Bash, Write

~/.claude/skills/seo/scripts/preflight.sh

login: their_email@example.com
password: their_api_password_here

~/.claude/skills/seo/scripts/prospect_finder.py find \
    --niche "<niche>" \
    --city "<city + state>" \
    --limit 30 \
    --out ~/.claude/skills/seo/output/<niche>-<city-slug>-prospects.json

🎯 SEO Prospect Search — <niche> in <city>

📡 Powered by DataForSEO API · <N> live calls · ~$<Y> charged
   ↳ SERP, Labs, On-Page, and Backlinks endpoints

Found <X> non-aggregator businesses. Scored by closeability:

Rank | Domain               | Pos | Closeability | Traffic/mo | Issues | Backlinks
-----|----------------------|-----|--------------|------------|--------|----------
 1   | acmeplumbing.com     | 14  | 87/100       | 240        | 5      | 23
 2   | bayareaplumbers.com  | 22  | 82/100       | 180        | 4      | 41
 ...

🥇 Top pick: acmeplumbing.com

  Why it's a great target:
  • Ranks #14 for "<niche> <city>" — page 2, will respond to a pitch that says "let's move you to page 1"
  • Specific issues found: missing meta descriptions, no H1 on the homepage,
    duplicate title tags across service pages
  • Only 23 referring domains — small, hungry, likely no SEO agency on retainer
  • Estimated 240 monthly visits — they have revenue but room to grow

  Next step: run /seo audit acmeplumbing.com to generate the full PDF,
  then /seo email acmeplumbing.com to draft the cold email.

─────────────────────────────────────────────────────────
📡 Data source: DataForSEO API (https://dataforseo.com)
   Endpoints fired in this prospect search:
   • SERP google/organic/live/advanced  → candidate discovery
   • Labs domain_rank_overview          → traffic + keyword footprint
   • On-Page instant_pages              → technical issue surface
   • Backlinks summary                  → authority + size signal

   Saved: ~/.claude/skills/seo/output/<file>.json
   Next: /seo audit <domain>  to deep-dive on any single prospect.
─────────────────────────────────────────────────────────

© zubair-trabzada, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/seo-prospect of zubair-trabzada/dataforseo-claude.

Open the folder on GitHubat commit 67ac4f0