AugmentClaude

BOSS Agent CLI

Local assistant CLI for BOSS job platform with read-only, user-triggered operations.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/skill-can4hou6joeng4/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Use when working with the BOSS Zhipin job platform from your own machine — a local, read-only-first assistant CLI that only acts when you trigger it: no auto-outreach, no bulk operations, no scraping.

What this skill does

BOSS Agent CLI is a local assistant for the BOSS Zhipin job platform, designed for read-only-first workflows that respect platform compliance. It runs only when you trigger it—no automatic outreach, no bulk operations, and no data scraping. All commands output structured JSON, making it easy to parse results and handle errors predictably. The CLI starts safely with simple diagnostic commands and expands into job search or recruiter workflows as needed.

What it does

  • Diagnostic & schema commandsboss doctor, boss schema, and boss status verify setup and document available commands, parameters, and error codes.
  • Job search and filtering — Search for positions by keyword, city, and welfare benefits (e.g., dual weekends, five-point insurance); retrieve detailed job information by security ID.
  • Candidate-side workflow — Shortlist jobs locally via boss shortlist add (submission, messaging, and contact exchange happen on the official platform).
  • Recruiter-side job management — List, publish (online), and unpublish (offline) job postings; candidate search and chat remain on the official platform.
  • Standardized error recovery — All errors return a consistent JSON envelope with error codes, recoverability flags, and recovery actions (e.g., boss login for expired tokens, backoff for rate limits).
  • Compliance-first boundaries — Operations involving personal data or platform relationship writes (e.g., candidate search, chat history) return COMPLIANCE_BLOCKED in low-risk mode.

How to use it

Install via npx skills add can4hou6joeng4/boss-agent-cli for Skills, or uv tool install boss-agent-cli for local use. Start with boss doctor, boss schema, and boss status to verify your setup. For job search, use boss search "keyword" --city <city> --welfare "benefits" and boss detail <security_id>. For recruiters, use boss hr jobs list, boss hr jobs online <job_id>, and boss hr jobs offline <job_id>. Parse only stdout JSON; consult error codes and recovery actions when exit code is 1.

Related skills