pxb-liepin

pxb-liepin is a skill for Claude Code from dizhouid-lgtm/liepin-ai-loop-recruiting. It costs 152 tokens per session (7,602 once invoked), scanned A, original, MIT.

A Chinese-language workflow for finding and screening job candidates through Liepin, a Chinese recruitment platform, while keeping job descriptions, candidate records, and duplicate checks organized.

In plain words
What is it for?
Use it to search for candidates, review resumes, prepare candidate PDFs, maintain a candidate pool, remove duplicates, and close out a filled or paused role.
Why use it?
It provides a repeatable process for comparing candidates with a job description and prevents the same person from being handled repeatedly.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it to search for candidates, review resumes, prepare candidate PDFs, maintain a candidate pool, remove duplicates, and close out a filled or paused role.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dizhouid-lgtm/liepin-ai-loop-recruiting/pxb-liepin
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add dizhouid-lgtm/liepin-ai-loop-recruiting --skill pxb-liepin
Clone the repo
git clone --depth 1 https://github.com/dizhouid-lgtm/liepin-ai-loop-recruiting

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pxb-liepin

README.md
[![agentmods](https://agentmods.dev/badge/skills/dizhouid-lgtm/liepin-ai-loop-recruiting/pxb-liepin/github.svg)](https://agentmods.dev/skills/dizhouid-lgtm/liepin-ai-loop-recruiting/pxb-liepin)
Your own site
<a href="https://agentmods.dev/skills/dizhouid-lgtm/liepin-ai-loop-recruiting/pxb-liepin"><img src="https://agentmods.dev/badge/skills/dizhouid-lgtm/liepin-ai-loop-recruiting/pxb-liepin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pxb-liepin

Your own site · 80×15
<a href="https://agentmods.dev/skills/dizhouid-lgtm/liepin-ai-loop-recruiting/pxb-liepin"><img src="https://agentmods.dev/badge/skills/dizhouid-lgtm/liepin-ai-loop-recruiting/pxb-liepin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,602 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.07602
Opus 5 $0.00076 $0.03801
Sonnet 5 $0.00030 $0.01520
Haiku 4.5 $0.00015 $0.00760

Measured 12d ago against content hash 06f5bd5f0b3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pxb-liepin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/_csv.mjs, scripts/_liepin.mjs, scripts/dedup.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/pxb-liepin/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pixboom 搜人筛人作业流程

⚠️ 改本 Skill 前先想:这里只放所有岗通用、可复用的作业流程。单一案例/某轮/某岗经验 → 进该岗 JD.md,不进这里。 每岗四件:JD.md(对外 JD + 内部备注表,判断只看它去重台账.csv(resume_id,status,仅去重)· 候选人池.md(确认候选人)· 待定/(简历 PDF 中转)。 路径:命令里 <岗位>\… 相对工作区根(本 CLAUDE.md 所在);脚本全在 .claude/skills/pxb-liepin/scripts/,命令都写全路径,原样可跑。机械活全在脚本、跨 Win/mac;判断在本文 + agent。

全流程:两层循环,主 agent 串行自跑

P. 聊全 JD → 0. 体检+抢锁 → 0.5 登录 → 1. 粗筛 → 2. 精筛 → 3. 够一批没(没够回 1)→ 4. 出 PDF 交用户 → 5. 入池 → 6. 迭代回 0;招满/用户喊停 → 7. 结项复盘。

  • 不派 subagent:单账号单锁串行,subagent 无并行收益、反而启动慢易卡死;主 agent 从头跑到尾。
  • 小循环(1-3,自跑、不打扰用户):搜一页 → 粗筛挑 ~10 → 精筛 → 对口标 待定 → 没攒够回步骤 1,连轮跑到攒够 ~5 个 待定绝不跑一轮就停等用户
  • 大循环(4-6,用户校准 JD):出一批 PDF → 用户复核 → 入池 → 迭代回写 JD(重点是进化关键词)→ 下一批。JD 越调越准、小循环越搜越准。
  • 上下文:脚本只输出窄表。看完做完判断后记住结论即可(待定 的 id=标签、方向感、哪个词有效),别把整页窄表一直留着;轮数多了丢旧轮明细。

状态机(去重台账只此 5 值,全程走 dedup.mjs,绝不手改 CSV)

未精筛(捞回来没细看的干净库存)→ 粗筛不合适(卡片就否)/精筛不合适(细看后否,含用户毙掉的)/待定(细看够格、出了 PDF 等复核)→ 入选(用户拍板要了)。

心跳 + 输出纪律(治"闷头静默"和"过程废话/散问打断")

  • 边跑边报:每跑完一轮先发一行进度再继续,别让用户 10-20 分钟看不到动静。格式:第N轮(词:X):搜A/精筛B/新增待定C,累计 D/目标 E,继续…。心跳是单向,不算打扰。
  • 心跳就那一行:逐人淘汰理由、本轮发现、推理全留你脑子里 + JD 表,别讲给用户
  • 交付干净:出批消息 = 几份可点 PDF + 问为什么,别夹每轮过程、复盘、SKILL 自测。
  • 决策别打断、给推荐、能不问就别问:破例/放宽约束/停搜这类才需用户拍的,优先带推荐先做可逆一步(照推荐先提报、复核可撤),决策点在交付里一句话点出;真要问就攒一处、一次问清、每条附推荐,别过程里东一句西一句、也别没问完就干等。照 JD 能自己判的,别问。

全程红线

① 单账号串行,绝不并发调 liepin。② 反爬宁慢勿封:脚本非零退出即停、别密集连刷(脚本内已带抖动)。③ 原始 JSON 不进上下文(脚本只输出窄表)。④ 隐私:简历只存本地、不外发、不传外部服务。⑤ 只 search/resume,greet(沟通归 HR)。⑥ 只走脚本(search/fetch/pdf/jd-round,已强制无头),除用户手动 liepin login绝不裸敲 liepin(裸调发布版默认有头会弹窗)。全程不该弹任何浏览器窗口;弹了 = 有人裸调或没登录 → 停手排查、别继续刷(可选安全网:装完跑一次 patch-headless.mjs)。

脚本无参运行会打印用法;任一脚本退出码 ≠ 0 = 停手,按报错处置(多半反爬/被踢/未登录)。


P. 开搜前:把 JD + 人员画像聊全(主 agent+用户,不碰 liepin、不抢锁)

搜任何人之前,先把该岗 JD + 人员画像补到能搜的状态——判断全程只看它,补不全 = 瞎搜、多轮返工。在对话里完成。

🟢 怎么聊(最重要):像懂行的猎头跟用人方对齐需求,用人话把"要什么样的人、这种人在哪、什么样的看着像其实不是"聊明白。下面的"三锚/锚一二三"是给你对照的内部清单,不是台词——别把这些词、别"锚一锚二"这样列条目念给客户。自然地问、一次一两点。

Read the full file on GitHub · 211 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 211 lines · 152 tokens per session scan A 06f5bd5f0b3f

Subscribe to this mod's changes

pxb-liepin is a skill published in the GitHub repository dizhouid-lgtm/liepin-ai-loop-recruiting (3 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session and 7,602 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

domain

When you want to brainstorm and check available .com domains for a new project — brand naming, aftermarket pricing (HugeDomains / Afternic / Sedo / Dan), USPTO trademark screening, and social handle availability. Built on Laura Roeder's "work backwards from availability, not from a name you fell in love with"…

coreyhaines31/makerskills · 232 tokens

company-brain

Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…

coreyhaines31/makerskills · 322 tokens

slide-deck

When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…

coreyhaines31/makerskills · 259 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens

session-cleanup

Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation.…

hoangsonww/Claude-Code-Agent-Monitor · 67 tokens

converge

Append-only gap closure and the cadence engine for research theses. Evaluates artifact CURRENT state (never git history, never task checkboxes) against current pins and wrongif falsifiers, then appends a Convergence section to tasks.md re-proposing the gaps. A clean run leaves tasks.md byte-identical. Deterministic…

agentii-ai/agentii-investment-intelligence · 93 tokens