agentleFS
agencia-conversionagencia-conversion/agentic-seo-skills/skills/seo-tools-creator/SKILL.md

seo-tools-creator

Skill51 starsChanged 6 months agoMITView on GitHub

When the user wants to create, port, fork, or review deterministic provider tools for Agentic SEO. Also use when adding tool attribution, registry entries, or provider integration docs.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Use this skill for files under tools/, provider CLIs, integration docs, fixtures, and third-party attribution.

    line 15
  2. Distinctive:

    Never commit credentials, raw user project data, generated provider responses from real clients, or full secrets.

    line 20
  3. Distinctive:

    Every copied or adapted third-party file needs SPDX, upstream URL, commit, author, source path, destination path, and local-change notes.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

SEO Tools Creator

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.

When To Use

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.

Critical Points

  • Skills may call tools; tools never depend on skill prose.
  • Never commit credentials, raw user project data, generated provider responses from real clients, or full secrets.
  • Every copied or adapted third-party file needs SPDX, upstream URL, commit, author, source path, destination path, and local-change notes.
  • CLI output must be stable JSON so tests can compare it.
  • Credentials come from environment variables or ~/.agentic-seo/credentials.json, never from repo root .env.
  • Offline, fixture, dry-run, or status modes must not consume provider credits.

Framework

1. Classify The Source

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.

2. Define The CLI Contract

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."

3. Isolate Credentials And Network Calls

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."

4. Record Attribution

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."

5. Test The Contract

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."

Output Format

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: []

Examples

Example: Strong Port

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."

Example: Weak Port

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.

Related Skills

  • seo-skills-creator: use for narrative skill design.
  • data-setup: use when guiding a user through credential setup.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.