mcpbeat

Brighthire

openai/brighthire

Use BrightHire tools when a user asks about BrightHire interview intelligence, calls, candidates, roles, scorecards, transcripts, hiring decisions, or organization-level interview data.

473 tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
4915
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/openai/plugins --skill brighthire

What comes with it

380 bytes besides the instruction
agents/openai.yaml

The instruction itself

1 sections, as written by the author

BrightHire

Use BrightHire tools when the user asks for information stored in BrightHire or asks Codex to reason about interview intelligence from BrightHire data.

Good fits include:

  • Finding calls, interviews, candidates, roles, interviewers, scorecards, or transcripts.
  • Summarizing interview context for a hiring decision.
  • Looking up evidence from BrightHire before answering questions about a candidate or role.
  • Comparing interview feedback, themes, concerns, or evidence across calls.

Before using BrightHire data, identify what entity the user means: candidate, role, organization, call, interviewer, or date range. If the request is ambiguous and multiple BrightHire records may match, ask a concise clarifying question or search broadly and present the likely matches.

Treat BrightHire content as sensitive customer data. Do not expose more candidate, interviewer, or organization information than the user asked for. Prefer concise summaries with links or identifiers when available, and avoid copying long transcript passages unless the user explicitly needs exact evidence.

If a BrightHire tool fails because authentication is missing or expired, tell the user they need to connect or re-authenticate the BrightHire plugin. Do not ask for raw API tokens in chat.

How to use it

Copy the folder

Take openai/brighthire from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.