跳到正文
cccskills
免费在 GitHub 公开

job-description

Write a performance-based job description. Use when the user says "write a JD", "draft a job posting", "create a job description", "help me post this role", "write requirements for this position", or wants to define what success looks like in a role - even if they don't explicitly say "job description". Also use when a hiring manager says "I need someone who can do X, Y, Z" and needs that translated into a structured posting.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md6.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Overview

Based on Hire With Your Head by Lou Adler. Traditional JDs list requirements (skills, years of experience, degrees) but don't tell candidates what they'll actually do. Performance-based JDs flip the model: define what "great" looks like in 90 days and 1 year, then work backward to what's required. This filters for candidates who can deliver outcomes, not just match keywords.

Workflow

Step 1: Define the Performance Objective

Before writing a single word of the posting, answer: "What does this person need to accomplish in the first 90 days to be considered successful?"

Ask [hiring manager]:

  • "If you hired someone today and they exceeded your expectations at 90 days, what would they have done?"
  • "What's the one outcome that, if missing, would make this hire a failure?"
  • "What does the person in this role own, end-to-end?"

Convert answers into 3-5 measurable performance objectives. Format:

- Within 90 days: [specific deliverable or outcome]
- Within 6 months: [milestone or capability reached]
- Within 12 months: [strategic outcome or ownership expanded]

Step 2: Write the Opening Hook

State the mission of the role, not the list of duties. Candidates skim - the opening determines whether they read further.

Bad: "We are looking for a Senior Engineer to join our growing team." Good: "You'll own the data pipeline that powers every dashboard [your company] ships. In the first 90 days, you'll audit what exists, document what's missing, and ship the first version of the new ingestion layer."

Step 3: Structure the Job Description

# [Role Title] - [Your Company]

## The Role
[2-3 sentence mission. What does this person own? What's the impact?]

## What You'll Do (First 12 Months)
- [90-day outcome]
- [6-month outcome]
- [12-month outcome]
- [Ongoing responsibility 1]
- [Ongoing responsibility 2]

## What We're Looking For
[5-7 bullets. Lead with must-haves, end with nice-to-haves.
Each bullet states a capability, not a credential.
"Built and shipped X" beats "5 years of experience."]

## What We Offer
- Compensation: [$X - $Y base + equity/bonus structure]
- [Benefit 1]
- [Benefit 2]
- [Culture or growth differentiator]

## How to Apply
[Clear next step. Link or instruction. No paragraph of boilerplate.]

Step 4: Write the Requirements Section

Requirements should predict performance. For each requirement, ask: "Can someone without this still achieve the 90-day outcome?" If yes, it's a preference, not a requirement.

Format requirements as:

  • Must-have: Can demonstrate [specific capability] through past examples
  • Strong plus: Experience with [tool or domain] - not required but speeds ramp

Avoid:

  • Years of experience minimums ("5+ years") - use capability statements instead
  • Degree requirements unless genuinely role-critical
  • Vague adjectives ("passionate", "self-starter", "team player")

Step 5: Calibrate on Seniority

Use the scope-ownership matrix to anchor level:

LevelScopeOwnership
Junior / ICDefined tasks within a projectExecutes with guidance
MidFull features or workstreamsOwns deliverable, escalates blockers
SeniorCross-team outcomesOwns outcome and unblocks others
Staff / LeadOrg-level capabilitySets direction, multiplies team

Make sure the performance objectives match the level. A "Senior" JD with junior-level objectives will attract the wrong pool.

Step 6: Review Before Publishing

  • Remove corporate jargon ("synergy", "dynamic", "fast-paced environment")
  • Remove requirements that correlate with demographics, not performance
  • Cut every bullet that isn't load-bearing - shorter JDs get more qualified applicants
  • Add specific signals of the work environment: "We ship weekly", "No dedicated QA team", "You'll be the first in this function"

Anti-Patterns

1. Leading with company bio Bad: "Founded in 2018, [your company] is a mission-driven SaaS company transforming the way teams collaborate..." Good: Lead with the role's mission and impact. Save the company pitch for an "About Us" section at the bottom.

2. Requirements as a wishlist Bad: "5+ years Python, experience with Kafka, Spark, Airflow, dbt, Snowflake, AWS, GCP, and strong communication skills..." Good: 5-7 must-haves that directly predict the ability to hit the 90-day outcome.

3. Duties list masquerading as outcomes Bad: "Responsible for writing code, attending standups, participating in code review, and collaborating with stakeholders." Good: "Own the auth service - design, build, and maintain it. In 90 days, migrate it off the legacy monolith."

4. Vague compensation Bad: "We offer a competitive compensation package." Good: "$140,000 - $170,000 base depending on experience + 0.1-0.25% equity over 4 years."

5. Burying the interesting work Bad: A wall of text where the most compelling work appears in paragraph 4. Good: First 2-3 sentences are the hook. If they're not compelling, the rest won't be read.

Quality Checklist

  • Performance objectives are specific and measurable (not a duties list)
  • Opening 2-3 sentences describe mission and impact, not the company
  • Requirements list is 7 items or fewer, each tied to a performance outcome
  • Compensation range is included
  • No vague adjectives ("passionate", "self-starter", "fast-paced")
  • Seniority level matches the scope and ownership in the objectives
  • JD body is under 600 words (shorter performs better with qualified applicants)
  • Call to action is clear and frictionless

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

中文简介正在准备中。当前显示原文说明。

qa-aman/claude-skills212026年10月19日 更新

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

中文简介正在准备中。当前显示原文说明。

qa-aman/claude-skills212026年10月19日 更新

Design statistically rigorous experiments to test data science hypotheses. Use when the user says "design an A/B test", "run an experiment", "test this hypothesis", "is this difference significant", "how many samples do I need", "randomized controlled trial", "causal inference", "uplift test", "holdout group", "significance test", "power calculation", "avoid p-hacking", or needs to determine whether an observed effect is real before making a product or model decision. For lean build-measure-learn product experiments without the statistics, use experiment-design instead.

中文简介正在准备中。当前显示原文说明。

qa-aman/claude-skills212026年10月19日 更新

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

中文简介正在准备中。当前显示原文说明。

qa-aman/claude-skills212026年10月19日 更新

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

中文简介正在准备中。当前显示原文说明。

qa-aman/claude-skills212026年10月19日 更新

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

中文简介正在准备中。当前显示原文说明。

qa-aman/claude-skills212026年10月19日 更新

查看 qa-aman 的全部技能

报告此技能的问题