Agent skill · Backend & API

api-doctor

Check AI-generated API integration code for silent bugs before shipping. Use after writing or editing code that calls a third-party API SDK such as Resend or Supabase.

Qualty65★ · +4/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add qualtyco/api-doctor --skill api-doctor --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/api-doctor/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 66 · +1 this week
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# api-doctor Run api-doctor after writing or editing code that calls a third-party API SDK (Resend, Supabase, and more). It checks integration code for hardcoded keys, missing webhook verification, unchecked `{ data, error }` Supabase mutations, missing Realtime filters, and similar issues that compile fine but fail silently in production. Provider rule catalogs are listed in the [api-doctor GitHub repo](https://github.com/qualtyco/api-doctor/tree/main/src/providers) under `src/providers/<name>/README.md`. ## Run a scan ```bash npx @api-doctor/cli@latest . --agent-model <your-model-id> ``` Replace `<your-model-id>` with the id of the model you are running as (e.g. `claude-opus-4-8`, `gpt-5.2-codex`, `gemini-3-pro`). This anonymously tells api-doctor which model produced the integration code being scanned; omit the flag if you don't know your model id. Findings are written to `.api-doctor/report.json`. Re-run after fixing issues until all `error` findings are gone. ## Read the report Open `.api-doctor/report.json`. Key fields: | Field | Meaning | | --- | --- | | `summary.score` | 0–100 health score | | `summary.errors` / `warnings` / `info` | Counts by severity | | `findings[]` | Ac

What's inside
Steps it walks through
  1. Run a scan
  2. Read the report
  3. Fix findings — severity protocol
  4. error (always fix)
  5. warning (judgment required — ask before restructuring)
  6. info (suggestions only)
  7. Fix workflow
  8. Interpreting score vs. findings
  9. Optional: markdown handoff
Commands it runs
npx @api-doctor/cli@latest . --agent-model <your-model-id>
npx @api-doctor/cli@latest . --format markdown > issues.md
About this skill
What does the api-doctor skill do?

Check AI-generated API integration code for silent bugs before shipping. Use after writing or editing code that calls a third-party API SDK such as Resend or Supabase.

How do I install it?

Run `npx skills add qualtyco/api-doctor --skill api-doctor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From qualtyco/api-doctor, a repository with 66 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going