mcpField
S
serp-keyword-harvester

serp-keyword-harvester

github.com/sergekostenchukMarketing & growth3249 installsUpdated 18w ago
Repository

About serp-keyword-harvester

serp-keyword-harvester is a skill for collecting and normalizing search-demand evidence for pre-design work. It supports local inputs and approved external sources, then hands structured data to semantic-core-builder.

Key features

  1. 01Plan keywords, locales, and sources
  2. 02Normalize local keyword data
  3. 03Use approved external SERP sources
  4. 04Audit existing harvest reports
  5. 05Label source status and provenance

Use cases

  1. 01Prepare keyword evidence before site design
  2. 02Normalize exported CSVs and site text
  3. 03Review an existing keyword-harvest report

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sergekostenchuk/ui-ux-agent-skill-system --skill serp-keyword-harvester

After installing, type/serp-keyword-harvesterin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
assets/
keyword-harvest.schema.json
openserp-settings.example.json
references/
keyword-harvest-contract.md
openserp-setup.md

Details

From the project README

SERP Keyword Harvester

This skill prepares raw search-demand evidence for the pre-design pipeline. It does not decide final site architecture or source/proxy policy; serp-source-configurator owns setup gates and this skill hands structured inputs to semantic-core-builder.

Operating Modes

  • plan: define seed keywords, locales, sources, approvals, and fallback.
  • harvest-local: normalize user-provided keywords, exported CSVs, existing site text, or local reports.
  • harvest-external: use approved SERP/autocomplete APIs or tools; approval required before network calls.
  • audit: review an existing reports/keyword-harvest.json.

Required Workflow

  1. Read references/keyword-harvest-contract.md.
  2. If OpenSERP, AKE, proxy, API keys, engine checkboxes, source settings, or paid-proxy limits are mentioned, route setup to serp-source-configurator first and consume its redacted reports/serp-source-config.json handoff.
  3. If OpenSERP is already approved/configured, read references/openserp-setup.md and use assets/openserp-settings.example.json only as a redacted contract, not as a credential store.
  4. Confirm privacy and approval mode:
    • local inputs and user-provided public facts: allowed;
    • external SERP/API/crawling: explicit approval required;
    • private/authenticated sources: explicit approval plus data-handling note.
  5. Collect or normalize seed keywords, market/locale, project type, and source provenance.
  6. Write or update reports/keyword-harvest.json using assets/keyword-harvest.schema.json as the field contract.
  7. Label every data group as Ran, Skipped, Planned, or Manual.
  8. Hand off to semantic-core-builder; do not invent missing SERP evidence.

Safety Rules

  • Do not scrape or call external services without approval.
  • Do not store API keys, cookies, private URLs, recovery codes, or .env values in reports.
  • Treat OpenSERP as optional-cloud / external-network: no call without explicit approval, configured credentials, query scope, source config, and a data-transfer note.
  • Do not decide proxy provider, paid budget, or engine selection inside this skill when it is not already explicit; use serp-source-configurator.
  • If search APIs return 429/503 or are unavailable, mark the source Skipped and continue with local/user-provided inputs.

Handoff Shape

Mode:
Locale/market:
Seed keywords:
Sources used:
Sources skipped:
Source config:
Output path:
Privacy/approval note:
Next skill: semantic-core-builder

Validation

When editing this skill, run:

python3 $CODEX_HOME/skills/.system/skill-creator/scripts/quick_validate.py $CODEX_HOME/skills/serp-keyword-harvester
python3 $CODEX_HOME/skills/senior-skill-architect/scripts/lint_production_skill.py $CODEX_HOME/skills/serp-keyword-harvester

Comments

Markdown supported