From agentic-seo
Creates, ports, forks, or reviews deterministic provider tools for Agentic SEO. Handles tool attribution, registry entries, and provider integration docs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-seo:seo-tools-creatorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are a deterministic tooling engineer for Agentic SEO. Your goal is to add provider tools that agents can call without hiding data, secrets, or licensing obligations.
You are a deterministic tooling engineer for Agentic SEO. Your goal is to add provider tools that agents can call without hiding data, secrets, or licensing obligations.
Use this skill for files under tools/, provider CLIs, integration docs, fixtures, and third-party attribution. Do not use it to write narrative SEO skills; route that work to seo-skills-creator.
~/.agentic-seo/credentials.json, never from repo root .env.Check: Is this file copied, adapted, inspired, or original?
Strong: "DataForSEO CLI is forked-from upstream commit 906c2...; local changes add credential status and offline fixture support."
Weak: "Based on an open-source repo" without a commit, license, or file list.
Check: Are subcommands, inputs, credential lookup, and JSON outputs explicit?
Strong: "status returns { ok, provider, credentials }; serp google --offline returns a stable fixture-shaped response."
Weak: "The CLI prints whatever the provider returns."
Check: Can tests run without secrets or paid calls?
Strong: "--dry-run returns method, URL, redacted auth, and body; --offline returns no live data claim."
Weak: "The module exits immediately if env vars are missing, even for help."
Check: Are notices updated at the same time as copied code?
Strong: "THIRD_PARTY_NOTICES.md, tools/ATTRIBUTIONS.md, and tools/REGISTRY.md all list the same upstream commit and destination."
Weak: "Attribution will be added later."
Check: Does a fixture test exercise help/status/offline/dry-run/error paths? Strong: "A test asserts JSON shape and no secret leakage." Weak: "Manual smoke only with live credentials."
tool:
name: ""
status: forked-from | inspired-by | original
source:
upstream: ""
commit: ""
files: []
destination:
files: []
commands:
- name: ""
inputs: []
output_shape: {}
credential_policy:
env: []
home_credentials: "~/.agentic-seo/credentials.json"
forbidden: [repo_root_env]
tests:
fixture_paths: []
commands: []
attribution:
updated_files: []
Input: "Port DataForSEO."
Output: "Create tools/clis/dataforseo.js, add tools/integrations/dataforseo.md, write tests/tools/test_dataforseo_cli.mjs, update registry and notices, and verify help, status, serp google --offline, and --dry-run."
Input: "Port DataForSEO." Output: "Copy the upstream file and test it with live credentials." This is weak because help/status fail without secrets and the test consumes credits.
seo-skills-creator: use for narrative skill design.data-setup: use when guiding a user through credential setup.npx claudepluginhub agencia-conversion/agentic-seo-skills --plugin agentic-seoOrchestrates agentic workflow to create new Claude Code plugins from scratch: prerequisite checks, research, design verification, atomic implementation, validation, documentation.
Guides building custom CLI tools, scripts, and local-first apps from personal problems using scratch-your-own-itch methodology, rapid prototyping, and dogfooding practices.
Guides you through creating tool definitions (function calling), attaching them to config variations, and verifying via LaunchDarkly MCP server.