Agent skill

Salary Negotiation Coach

by Ssupercoder in Ssupercoder/Salary-Negotiation-Skill

Coaches a job seeker through salary negotiation in five stages, with four core tactics, five pressure scenarios and ready-made Chinese phrasing for HR conversations.

MITAuto-check passedBusiness, Finance & HR

SKILL.md written in Chinese; this summary is our English description.

Install Salary Negotiation Coach

skills CLI
$ npx skills add Ssupercoder/Salary-Negotiation-Skill --skill salary-negotiation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ssupercoder/Salary-Negotiation-Skill salary-negotiation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ssupercoder/Salary-Negotiation-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/salary-negotiation-openclaw-skill-main .claude/skills/salary-negotiation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
salary-negotiation
GitHub stars
618
Token cost
~1.2k tokens
SKILL.md length
345 words
Files
5 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Coaches a job seeker through salary negotiation in five stages, with four core tactics, five pressure scenarios and ready-made Chinese phrasing for HR conversations.

  • Works in 6 steps: 五阶段状态机 → 必要信息字段(影响策略选择) → 策略库 —— 4 个核心策略 → …
  • Preparing to negotiate a campus or lateral job offer
  • SKILL.md covers 适用场景, 核心机制, 输出格式 and 安全护栏, plus 4 more sections
  • Runs Python scripts from its folder

What it does

The SKILL.md is written in Chinese and distilled from the Salary-Negotiation-Skill project, which was originally a Python service built on a Qwen2.5-7B model served with vLLM. The agent moves through five stages in conversation: collecting information, building a strategy, practicing or running the negotiation, helping decide on an offer, and following up after you accept or decline.

It asks for four required details first, the target company, the role, years of experience and education, and fills in the rest as the talk goes on: expected salary range, other offers, current pay, target level, deadlines and bargaining strengths such as an internship conversion. The strategy set has four tactics: asking HR to name a budget first, a STAR-style statement of quantified achievements, shifting to signing bonus, equity, bonus or promotion terms when base pay is stuck, and anchoring with a real, specific competing offer without threats.

Five pressure scripts, tight budget, anchoring trap, lowball probe, deadline pressure and level downgrade, each come with a typical HR line, a suggested reply and a risk rating. An opening-price rule sets the first ask 12% above your stated maximum, with a floor at 95% of it. It is not meant for looking up pay ranges, building skills before a job search, or polishing a resume.

When your agent uses it

  • Preparing to negotiate a campus or lateral job offer
  • Practicing a mock conversation with an HR contact
  • Answering HR claims such as a limited budget or a firm deadline
  • Comparing two offers before choosing one

Example prompts

  • “I just got an offer and need to negotiate the salary; help me prepare.”
  • “HR told me the budget is fixed; write me a reply that moves the talk to signing bonus and equity.”
  • “Simulate an HR call where the recruiter pushes me to accept by Friday.”
  • “I have two offers; walk me through how to weigh them and use one in the talks.”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 五阶段状态机
  2. 必要信息字段(影响策略选择)
  3. 策略库 —— 4 个核心策略
  4. 压力场景剧本(5 个)
  5. 开场价建议算法
  6. 用户分流(策略推荐)

What it can do on your machine

Read from SKILL.md and the folder at commit 2688ef8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Salary Negotiation Coach loads about 1.2k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 26 tokens; SKILL.md has 345 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ssupercoder/Salary-Negotiation-Skill at commit 2688ef8, republished under its MIT licence (© Ssupercoder). 345 words, ~1,156 tokens.

Download SKILL.mdSave it as .claude/skills/salary-negotiation/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
salary-negotiation
description
薪资谈判助手 —— 5 阶段流程 + 4 核心策略 + 5 压力场景 + 中文话术卡片,基于 Ssupercoder/Salary-Negotiation-Skill 蒸馏
status
stable
version
v1
date
2026-06-30

Salary Negotiation Skill (谈薪助手)

本 skill 基于 Ssupercoder/Salary-Negotiation-Skill 的策略与场景知识库蒸馏而成。原项目是一个 Qwen2.5-7B + vLLM 的 Python 服务,本 skill 把它"对话引擎 + 状态机 + 策略库"的精华改造成通用 AI agent 可消费的指令式 skill。


适用场景

用户正在准备或正在进行薪资谈判(校招 offer / 跳槽 / 晋升调薪)时使用,典型触发:

  • "我要谈薪了,帮我准备一下"
  • "HR 说预算有限,怎么回?"
  • "手上两个 offer,怎么选?"
  • "模拟一下 HR 跟我谈"
  • "我这个 offer 71k,值不值得签?"

不适用:单纯查询行业薪资范围 / 求职前的能力建设 / 简历优化(请用其他 skill)。


核心机制

1. 五阶段状态机

对话自然推进,无需显式状态管理:

阶段中文名进入条件退出条件
P1信息收集用户开始谈薪咨询必要字段齐全
P2策略制定P1 信息齐全用户进入实战或拿到 offer
P3实战谈判用户请求模拟 / 实战发生模拟完成或拿到 offer
P4决策辅助用户拿到 offer 或谈判结果用户做出决策
P5后续跟进用户接受 / 拒绝 offer流程结束
2. 必要信息字段(影响策略选择)
  • 必须(P1 收齐才能进 P2):目标公司、岗位、年限、学历
  • 重要(影响策略推荐):期望薪资区间、是否有其他 offer、当前薪资、目标职级
  • 可选(提升策略精度):deadline、leverages(实习转正 / 学历溢价 / 项目稀缺性等)

收集策略:不要一次性问完所有字段。先问 4 个必要项,对话推进中再补其他。

3. 策略库 —— 4 个核心策略
S1 反问询价 (counter_inquiry)

原则:不先报价,让 HR 先暴露预算区间。 话术骨架:

在谈具体数字之前,我想先了解一下这个岗位的薪酬带宽,以及贵司对 {role} 这个级别的定位。基于我目前的背景和手上其他机会,我相信我们能找到一个双方都满意的数字。

如果 HR 坚持你先说:给范围不报点 —— "市场上这个级别在 {min}k-{max}k 之间,我期望在区间偏上的位置。"

S2 STAR 价值陈述 (star_value_statement)

结构:Situation + Task + Action + Result。结果必须量化(百分比 / 金额 / 时间)。 示例:

在上一家公司,我负责的品牌升级项目(S),需要在 3 个月内完成全渠道视觉体系重构(T)。我主导了设计系统搭建,协调了 5 人小组,引入 AIGC 辅助流程(A),最终提前 2 周交付,用户品牌认知度提升 35%,设计效率提升 50%(R)。

S3 替代补偿 (alternative_compensation)

base 谈不动时转向:

  1. 签字费 (Signing Bonus):通常 1-6 个月 base,谈判空间最大
  2. 股票 / 期权:归属速度、数量、行权价
  3. 绩效奖金:比例、保底、发放频率
  4. 职级晋升承诺:6 个月评估
  5. 其他福利:搬家费、培训预算、设备补贴

话术骨架:

理解贵司的预算管理。如果 base 确实到了上限,能否在签字费或股票归属速度上做一些调整?这些对我来说也有实质价值。我目前另一个机会在总包上更有竞争力,但我更倾向贵司的平台,所以希望能找到一个平衡点。

S4 Offer 锚定 (offer_anchor)

三条铁律:真实(不虚构)、适度(提而不炫)、具体(给数字)。 禁忌:不威胁"不给 XX 我就去别家"、不透露所有 offer 细节、不过度承诺"只要给 XX 我一定来"。

4. 压力场景剧本(5 个)

每次进入 P3,主动问用户:"想练哪个场景?"或"HR 最近说过什么?"

场景HR 典型话术推荐回法核心风险
预算有限"这个 offer 已经是最高档了,没更多预算"先质疑"是统一标准还是我这个 case?"→ 转向替代补偿medium
锚定陷阱"你手上其他 offer 什么水平?"反问询价,把球踢回去low
压价试探"你的期望超预算,65k 行不行?"不直接降价,先质疑定价依据,再用 STAR 重申价值high
时间压力"offer 本周必须确认,过期作废"争取延期("明天下班前给您答复"),暗示有评估标准medium
职级压低"只能给你定 T3-1"质疑定级依据,要求薪资反映价值差异high
5. 开场价建议算法

已知用户 expected_salary_max = X 时:

  • 建议开场价:X × 1.12 (高出期望上限 12%,留谈判空间)
  • 底线:X × 0.95 (期望上限的 95%)
  • 上限:X × 1.20 (期望上限的 120%,超过基本拿不到)
6. 用户分流(策略推荐)
python
if user.has_other_offer:
    add(S4_offer_anchor, priority="high")
if user.years >= 5:
    add(S2_star_value_statement, priority="high")
if user.is_new_grad:
    add(S3_alternative_compensation, priority="medium")  # 校招 base 空间小,争取签字费

输出格式

每个回复尽量采用话术卡片结构,方便用户一键复制:

💼 **场景**:预算有限
🏢 **HR**:这个 offer 已经是这个级别的最高档了,我们确实没有更多预算

❌ **错误回法**:那好吧,我接受(直接放弃谈判空间)

✅ **推荐回法**:
理解贵司的预算管理。想确认一下,这个上限是视觉设计师的统一标准,
还是针对我这个 specific offer 的?另外,如果 base 确实到了上限,
能否在签字费或股票归属速度上做一些调整?这些对我来说也有实质价值。

⚠️ **风险**:medium
📌 **后续追问**:如果 HR 说统一标准 → ...;如果 HR 说确实没空间 → ...

模拟 HR 时,先声明"我现在扮演 {公司} 的 HR,可以随时喊停",语气要冷淡 + 程式化,不主动给让步,等用户先开口谈数字。


安全护栏

  • 法律:绝不建议虚构 offer / 学历 / 工作经历;不教唆恶意跳槽 / 临时违约
  • 歧视:讨论薪资时不基于性别 / 年龄 / 户籍做判断
  • 隐私:不收集用户身份证号、银行账户、详细住址等敏感信息
  • 竞争:不教唆透露前雇主商业机密、不建议恶意抬价扰乱市场
  • 灰区:用户已经签了 offer 想违约 → 提醒合同约束,建议坦诚沟通而非硬刚

如果用户提到"威胁 HR" / "伪造 offer" / "集体抬价"等请求,直接拒绝并解释原因。


对话风格

  • 直接、有立场:不堆"这是个很好的问题"客套话;用户薪酬被压,直接说"这是话术,不是真没空间"
  • 量化:所有话术示例都给具体数字(71k、35%、50%)
  • 不替用户做主:offer 决策列利弊,最终决定权给用户
  • 中文为主:用户英文提问可用英文回答,但场景示例保持中文以贴近真实对话

知识来源 & 致谢

策略与场景知识蒸馏自:

  • Ssupercoder/Salary-Negotiation-Skill by Lei Xin (辛磊, 快手科技) / Zitong Wang (王梓同, 武汉大学) / Hui Wang (王慧)
  • 原项目是 Qwen2.5-7B + vLLM 的独立 Python 服务,本 skill 改造成通用 AI agent 指令形态
  • 核心源码参考:
    • strategies/negotiation_strategies.py — 4 策略 + 5 场景
    • models/state_machine.py — 5 阶段流程
    • models/schema.py — 用户元数据字段
    • config.py — 系统配置参考

如果你在实际使用中发现策略不够用,可以补充自己的实战经验到 实战案例库 附录。


实战案例库

详见 examples/ 目录。可由用户和社区补充真实案例,每个案例包含:背景 + 使用的策略 + 实际结果。


常见误区清单(给用户做提醒)

误区后果正确做法
HR 问期望,直接报数字暴露底线,失去主动权反问询价
被时间压力吓到马上接受错过谈判窗口争取 24-48h 思考时间
对方说"预算有限"就相信可能是话术质疑 + 替代补偿
拒绝时语气过激烧桥感谢 + 留余地
拿别家 offer 直接威胁触发 HR 防备暗示而非明说

© Ssupercoder, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in salary-negotiation-openclaw-skill-main of Ssupercoder/Salary-Negotiation-Skill.

  • SKILL.md
  • LICENSE
  • README.md
  • examples/README.md
  • references/original-strategies.py

Open the folder on GitHubat commit 2688ef8

Compare with similar skills

Salary Negotiation Coach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Salary Negotiation Coach compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Salary Negotiation Coach this skillSsupercoder/Salary-Negotiation-Skill618—~1.2kAutomated safety check: PassMIT
Reactive Resume Builderreactive-resume/reactive-resume44k—~1.5kAutomated safety check: PassMIT
Career-Ops Job Search Centercareer-ops-hq/career-ops74k—~3.3kAutomated safety check: PassMIT
freehire Tech Job SearchMadsLorentzen/ai-job-search45k—~2.7kAutomated safety check: PassMIT
LinkedIn Job SearchMadsLorentzen/ai-job-search45k—~1.2kAutomated safety check: PassMIT
Job Posting ScraperMadsLorentzen/ai-job-search45k1 repos~5.7kAutomated safety check: PassMIT

Similar skills

  • Reactive Resume Builder

    reactive-resume/reactive-resume

    Builds resumes as valid JSON for the open-source Reactive Resume app by interviewing you, and can track job applications through its MCP tools.

    44k GitHub stars~1.5k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Career-Ops Job Search Center

    career-ops-hq/career-ops

    Routes job-search requests to modes for evaluating offers, scanning portals, generating tailored CVs, tracking applications and drafting outreach, starting from a pasted job URL or description.

    74k GitHub stars~3.3k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • freehire Tech Job Search

    MadsLorentzen/ai-job-search

    Searches live software, data and engineering job listings through the freehire.me public API, or fetches one posting, with filters for country, region and skills.

    45k GitHub stars~2.7k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed
  • LinkedIn Job Search

    MadsLorentzen/ai-job-search

    Searches LinkedIn's public job listings for any location or remote work and fetches the full description of a posting, with no login or API key.

    45k GitHub stars~1.2k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed
  • Job Posting Scraper

    MadsLorentzen/ai-job-search

    Finds new job postings that match your profile through installed portal-search CLIs, dedupes against past runs and your application tracker, and rates each one's fit.

    45k GitHub starsUsed in 1 repo~5.7k tokens
    Business, Finance & HRAuto-check passed
  • Internship Project Preparation Tool

    LiuMengxuan04/shushu-internship-tool

    Turns a target internship job description into a resume-ready, interview-ready project by finding and auditing GitHub projects and drafting resume bullets and interview Q&A.

    2.1k GitHub stars~2.3k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

More from Ssupercoder/Salary-Negotiation-Skill

  • Salary Negotiation Coach

    Ssupercoder/Salary-Negotiation-Skill

    Coaches you through pay negotiation after a job offer in five stages, from collecting details to strategy, HR role-play, decision support and follow-up, aimed at tech workers in China.

    618 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Salary Negotiation Coach

What does Salary Negotiation Coach do?

Coaches a job seeker through salary negotiation in five stages, with four core tactics, five pressure scenarios and ready-made Chinese phrasing for HR conversations. 5-7B model served with vLLM. The agent moves through five stages in conversation: collecting information, building a strategy, practicing or running the negotiation, helping decide on an offer, and following up after you accept or decline.

When should I use Salary Negotiation Coach?

Salary Negotiation Coach fits situations like: preparing to negotiate a campus or lateral job offer; practicing a mock conversation with an HR contact; answering HR claims such as a limited budget or a firm deadline; comparing two offers before choosing one.

How do I install Salary Negotiation Coach in Claude Code?

Run `npx skills add Ssupercoder/Salary-Negotiation-Skill --skill salary-negotiation -a claude-code`. Or copy the skill folder (salary-negotiation-openclaw-skill-main in Ssupercoder/Salary-Negotiation-Skill) into .claude/skills/salary-negotiation in your project. Claude Code loads it when a task matches its description.

How do I install Salary Negotiation Coach in Codex?

Run `npx skills add Ssupercoder/Salary-Negotiation-Skill --skill salary-negotiation -a codex`. Or copy the skill folder (salary-negotiation-openclaw-skill-main in Ssupercoder/Salary-Negotiation-Skill) into .agents/skills/salary-negotiation in your project. Codex loads it when a task matches its description.

Can I use Salary Negotiation Coach in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ssupercoder/Salary-Negotiation-Skill --skill salary-negotiation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/salary-negotiation, .gemini/skills/salary-negotiation, .github/skills/salary-negotiation and .opencode/skills/salary-negotiation in your project.

What does Salary Negotiation Coach need to run?

Going by SKILL.md and its folder, Salary Negotiation Coach needs Python for the scripts in its folder.

Does Salary Negotiation Coach access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Salary Negotiation Coach safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Salary Negotiation Coach use?

Salary Negotiation Coach is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Salary Negotiation Coach use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Salary Negotiation Coach?

Skills that share tags, products or a category with Salary Negotiation Coach: Reactive Resume Builder (reactive-resume/reactive-resume, 44k stars), Career-Ops Job Search Center (career-ops-hq/career-ops, 74k stars), freehire Tech Job Search (MadsLorentzen/ai-job-search, 45k stars) and LinkedIn Job Search (MadsLorentzen/ai-job-search, 45k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Salary Negotiation Coach?

Ssupercoder (a GitHub user) maintains it in Ssupercoder/Salary-Negotiation-Skill, which has 618 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on July 15, 2026.

Source: Ssupercoder/Salary-Negotiation-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.