Agent skill

Treg

by superdesigndev in superdesigndev/treg

People and company enrichment, AEO and SEO, ads, social, web scraping, image and video generation through the treg connector.

Custom licenceAuto-check passedMarketing & SEO

Install Treg

skills CLI
$ npx skills add superdesigndev/treg --skill treg -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install superdesigndev/treg treg --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/superdesigndev/treg.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/treg .claude/skills/treg && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
treg
GitHub stars
4.5k
Token cost
~642 tokens
SKILL.md length
350 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Custom licence

At a glance

People and company enrichment, AEO and SEO, ads, social, web scraping, image and video generation through the treg connector.

  • Works in 4 steps: catalog_search with the task in plain… → catalog_get the endpoint you picked.… → call(endpoint_id, params). If a call's… → …
  • A task needs external
  • SKILL.md covers Flow and When something goes wrong
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Treg is an agent skill from superdesigndev/treg. People and company enrichment, AEO and SEO, ads, social, web scraping, image and video generation through the treg connector. Use when a task needs external or live data; search the catalog by the task, check the endpoint, then call it.

Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Web scraping, AI search optimization and AI video generation. The repository describes itself as: OpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn.

When your agent uses it

  • A task needs external
  • Search the catalog by the task
  • Check the endpoint

Example prompts

  • “/treg”

Workflow steps

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

  1. catalog_search with the task in plain words, not a vendor name. Read verdict: strong means
  2. catalog_get the endpoint you picked. When several providers do the same job, compare their
  3. call(endpoint_id, params). If a call's answer never arrived (timeout, dropped connection),
  4. Nothing fits: catalog_request one sentence saying what is missing, then tell the human.

What it can do on your machine

Read from SKILL.md and the folder at commit e609803. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    Links to these hosts (documentation or services it may open):

    • treg.to

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Treg loads about 642 tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 350 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~642

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 350 words (~642 tokens).

“treg is connected as an MCP connector. Use its tools; there is nothing to install and no API key to ask the human for - treg adds the provider credential on its server.”

— opening of SKILL.md by superdesigndev, Custom licence
name
treg

Read the full SKILL.md on GitHub

Files

Just SKILL.md in plugin/skills/treg of superdesigndev/treg.

Open the folder on GitHubat commit e609803

Compare with similar skills

Treg next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Treg compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Treg this skillsuperdesigndev/treg4.5k—~642Automated safety check: PassCustom licence
Nuxt Geo Best Practicesvinayakkulkarni/nxui212—~1.9kAutomated safety check: PassMIT
Geo Measureyaojingang/GEOHub164—~348Automated safety check: PassAGPL-3.0
AI Search Visibility Auditdavepoon/buildwithclaude3.6k—~2.4kAutomated safety check: PassMIT
SEO DataforseoAgriciDaniel/codex-seo7872 repos~4.6kAutomated safety check: PassMIT
Aptos Explorer LLM SEOaptos-labs/explorer124—~835Automated safety check: PassNone

Similar skills

  • Nuxt Geo Best Practices

    vinayakkulkarni/nxui

    Nuxt GEO (Generative Engine Optimization) guidelines for getting cited by ChatGPT, Perplexity, Claude, Google AI Overviews, and Gemini.

    212 GitHub stars~1.9k tokensUpdated today
    Marketing & SEOAuto-check passed
  • Geo Measure

    yaojingang/GEOHub

    Measure GEO visibility from an approved, file-backed engine observation bundle.

    164 GitHub stars~348 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • AI Search Visibility Audit

    davepoon/buildwithclaude

    Audit whether a website can be found, crawled, and cited by AI answer engines such as ChatGPT Search, Perplexity, Google AI Overviews, and Microsoft Copilot.

    3.6k GitHub stars~2.4k tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • SEO Dataforseo

    AgriciDaniel/codex-seo

    Live SEO data via DataForSEO MCP server. An agent skill from AgriciDaniel/codex-seo.

    787 GitHub starsUsed in 2 repos~4.6k tokens
    Marketing & SEOAuto-check passed
  • Aptos Explorer LLM SEO

    aptos-labs/explorer

    Keeps Aptos Explorer discoverable for LLMs, crawlers, and SEO when routes, tabs, or page metadata change.

    124 GitHub stars~835 tokensUpdated today
    Marketing & SEOAuto-check passed
  • Aeo Visibility

    textura-agency/next16-claude-starter

    Answer Engine Optimisation — make the site citable by ChatGPT, Claude, Perplexity, Gemini and AI Overviews.

    132 GitHub stars~1.4k tokensUpdated today
    Marketing & SEOAuto-check: notes

More from superdesigndev/treg

All 12 skills in this repo
  • Add OAuth Provider

    superdesigndev/treg

    Add a provider to treg's OAuth registry (the ones treg holds its own approved app for).

    4.5k GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Dev Local

    superdesigndev/treg

    One-command local dev stack for tools-registry. An agent skill from superdesigndev/treg.

    4.5k GitHub stars~623 tokensUpdated today
    Auto-check passed
  • Google Ads

    superdesigndev/treg

    Traps when running Google Ads through treg — the API requirements and cleanup semantics that cost round-trips or money.

    4.5k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Google Analytics

    superdesigndev/treg

    Traps to avoid when querying Google Analytics 4 through treg — cases where the GA4 Data API returns a confident wrong answer instead of an error.

    4.5k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Google Search Console

    superdesigndev/treg

    Traps to avoid when querying Google Search Console through treg — cases where the API returns a confident wrong answer instead of an error, especially around totals and recent-date trends.

    4.5k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Jev Memory

    superdesigndev/treg

    A skill your agent uses when the user wants Claude Code to remember their preferences across sessions, asks for a memory mod or memory harness for Claude Code, mentions the Jev memory classifier or…

    4.5k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Questions about Treg

What does Treg do?

People and company enrichment, AEO and SEO, ads, social, web scraping, image and video generation through the treg connector. Treg is an agent skill from superdesigndev/treg. People and company enrichment, AEO and SEO, ads, social, web scraping, image and video generation through the treg connector.

When should I use Treg?

Treg fits situations like: A task needs external; search the catalog by the task; check the endpoint.

How do I install Treg in Claude Code?

Run `npx skills add superdesigndev/treg --skill treg -a claude-code`. Or copy the skill folder (plugin/skills/treg in superdesigndev/treg) into .claude/skills/treg in your project. Claude Code loads it when a task matches its description.

How do I install Treg in Codex?

Run `npx skills add superdesigndev/treg --skill treg -a codex`. Or copy the skill folder (plugin/skills/treg in superdesigndev/treg) into .agents/skills/treg in your project. Codex loads it when a task matches its description.

Can I use Treg in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add superdesigndev/treg --skill treg -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/treg, .gemini/skills/treg, .github/skills/treg and .opencode/skills/treg in your project.

What does Treg need to run?

SKILL.md names no scripts, command-line tools or credentials: Treg is instructions for the agent only.

Does Treg access the network?

SKILL.md names 1 domain. As links in the text: treg.to. This is read from the text; nothing was executed.

Is Treg safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Treg use?

Treg has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Treg use?

About 642 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Treg?

Skills that share tags, products or a category with Treg: Nuxt Geo Best Practices (vinayakkulkarni/nxui, 212 stars), Geo Measure (yaojingang/GEOHub, 164 stars), AI Search Visibility Audit (davepoon/buildwithclaude, 3.6k stars) and SEO Dataforseo (AgriciDaniel/codex-seo, 787 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Treg?

superdesigndev (a GitHub organization) maintains it in superdesigndev/treg, which has 4,540 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

Source: superdesigndev/treg on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.