# Write Provider Skill

Build a treg provider skill, the endpoint map + mistake map that lets an agent do real...

- Repository: https://github.com/superdesigndev/treg (6950 stars)
- Category: AI and agents
- License: see repository
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add superdesigndev/treg --skill write-provider-skill -g -a claude-code -y`
Codex: `npx skills add superdesigndev/treg --skill write-provider-skill -g -a codex -y`
Cursor: `npx skills add superdesigndev/treg --skill write-provider-skill -g -a cursor -y`
Gemini CLI: `npx skills add superdesigndev/treg --skill write-provider-skill -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add superdesigndev/treg`

## Description

Build a treg provider skill, the endpoint map + mistake map that lets an agent do real work on a platform API through treg's proxy. Use when adding a skill for a connected provider (Google Ads, LinkedIn, Meta Ads, TikTok, X, Instagram, Search Console), or when an existing provider skill needs verifying or extending.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Writing a provider skill

A provider skill is **an MCP server made of documentation**. An MCP server gives a model a tool
list and typed parameters. We can't ship a server per platform, so the skill carries the same
payload as prose: *which endpoints matter, what the parameters really are, and where the API
lies to you.*

The third part is the one MCP can't give you, and it's where nearly all the value is.

## The rule that decides what goes in

> **Document what produces a wrong answer without producing an error.**

Ranked by value to an agent:

| Class | Why it matters | Example |
|---|---|---|
| **Silent wrong answers** | Agent reports confidently false results. Unrecoverable alone. | GA4: incompatible dimension+metric returns `"0"` per row, not an error, reads as "no revenue" |
| **Wrong-shaped errors** | Error doesn't describe the real cause, so retries go sideways | GA4: bad path returns a Google **HTML 404 page**, not JSON, a JSON parse throws something unrelated |
| **Unguessable identifiers** | Agent invents an ID and gets 403/404 forever | GA4 needs `properties/123456789`; GSC needs `sc-domain:x.com` vs `https://x.com/` |
| **Host splits** | Endpoint exists but not on the bound host | GA4 Admin API is `analyticsadmin`, tool is bound to `analyticsdata` → 404 |
| **Capability limits** | Agent attempts work the scope can't do | GA4 connection is `read` only |
| Endpoint list | Findable in official docs |, |

Anything in the bottom row: **link to the docs, don't restate them.** A skill that paraphrases
the API reference is worse than a URL, it goes stale and it's longer.

## Verification protocol, non-negotiable

**Every endpoint and every example body in the skill must have been executed.** Not adapted from
docs, not plausible, run.

```bash
scripts/dev-local.sh up
scripts/dev-local.sh cli connections ls          # confirm health + resource_ref
scripts/dev-local.sh cli call <provider> <path>  # always via /call/, never direct
```

The rest: https://github.com/superdesigndev/treg/blob/HEAD/.agents/skills/write-provider-skill/SKILL.md