Agent skill
Give your coding agent the API, so it stops guessing.
If your team builds with Claude Code, Codex or Cursor, install this skill and the agent gets the whole API: the endpoints, the credential rules, the failure modes and the traps that are not obvious from a spec.
It is not a copy of these docs. It is written for a machine that is about to write an integration, so it leads with the rule, then the call, then what breaks.
Install
curl -sL https://docs.experthire.io/experthire-api-skill.zip -o /tmp/eh-skill.zip
unzip -o /tmp/eh-skill.zip -d ~/.claude/skills/
That gives every project on the machine the skill. For one repository, unzip into
.claude/skills/ at its root and commit it, so the whole team gets the same
answers.
Codex and Cursor read agent instructions from their own locations. The files are
plain markdown with YAML frontmatter, so put SKILL.md and its references/
wherever your tool looks.
Verify it landed:
ls ~/.claude/skills/experthire-api
# SKILL.md references/
What is in it
| File | Covers |
|---|---|
SKILL.md | When to use the API, the eight rules that matter, and which reference to read |
references/authentication.md | The four credential types, sandbox versus live, origin allowlisting, quotas |
references/errors-and-conventions.md | Every error code and what to do about it, pagination, retries, versioning |
references/interviews.md | Candidates, the interview lifecycle, launch links, reports, transcripts |
references/resumes.md | Upload, register, score against a role |
references/question-bank.md | Company questions, filters, the paging caveat |
references/webhooks.md | Registration, signature verification, the retry rules |
How to use it
Ask for what you want, in your own words:
Add Expert Hire interviews to our ATS. When a candidate reaches the
screen stage, create an interview and email them the link. Store the
score on the application when it comes back.
The agent loads the skill, reads only the references it needs, and writes the client. It should ask you which environment to target and where the key lives before it writes anything.
The skill tells your agent to start in sandbox. Let it. A sandbox key runs the same code as live, never records, never emails a candidate, and draws on a separate quota, so a wrong loop costs you nothing.
What it will refuse to do
It is written to say no to a few things, on purpose:
- Put a secret key anywhere a browser can reach it.
- Poll for completion instead of registering a webhook.
- Retry a create call without an
Idempotency-Key. The header is optional, so a blind retry after a timeout can create a second interview and spend a credit. - Book a
codinginterview round for graded code. The submit endpoints exist, but the hosted room renders no editor yet, so nothing would reach them. It books a coding test instead.
If your agent does any of those, it did not load the skill.
Keeping it current
The bundle is rebuilt whenever these docs deploy. Re-run the install command to pick up changes. The skill states its own limits, so an agent reading a stale copy fails by refusing to build something that now exists rather than by inventing something that never did.