跳到正文
cccskills
免费在 GitHub 公开

job-post-writer

Write job posts that make the right person apply -- real role clarity, honest selling points, salary range handling, and requirements pruned to what actually predicts success. Small businesses lose great candidates to bad posts long before the interview. Feeds cowork-hiring-screener and hiring-scorecard downstream.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md3.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Job Post Writer

A job post is an ad competing against every employer in the market, and most read like compliance documents. Write the one the right candidate stops scrolling for -- honest about the work, specific about the money, and stripped of the requirements that filter out people who would have been great. Input: what the role actually does day-to-day (interviewed out of the owner if needed) and what the business can truly offer.

Workflow

  1. Interview for the real job. Not the title -- the Tuesday: what this person does most days, what problem hiring them solves, what the first 90 days look like, who they work with, and what made the last person in the role succeed or fail. If the owner cannot answer these, that gap is finding number one.
  2. Prune the requirements. Sort every requirement into must-have (day-one necessity that cannot be taught in 90 days), trainable, and decoration. Degree requirements, years-of-experience counts, and tool checklists get challenged individually -- every unnecessary must-have shrinks the pool, and shrinks it worst among candidates who take requirements literally. Land on 4-6 real must-haves.
  3. Find the honest sell. Small businesses cannot outbid corporates, but they can offer what corporates cannot: scope ("you'll run the whole kitchen, not station 4"), visibility, schedule reality, speed of growth, no-bureaucracy, the actual humans. Pull the true ones from the interview -- and never write "family atmosphere," "fast-paced," "wear many hats," or "rockstar," which candidates correctly read as understaffed, chaotic, and underpaid.
  4. Handle the money. Push for a posted range: posts with pay get dramatically more applicants, and pay-transparency laws require it in a growing list of states (web-check the user's state). If the owner resists, show the math of what secrecy costs in applicant volume, and at minimum post the benefits and scheduling honestly.
  5. Draft and structure. Title candidates actually search (not "Guest Experience Ninja"), opening two lines that state the role and the strongest sell (that is all most see on the feed), the Tuesday description, the pruned requirements, the pay/benefits block, and an application step that takes under five minutes -- every extra form field sheds good candidates who have options. Output versions sized for the job boards and the one-paragraph social/referral blurb.

Rules

  • The post describes the job that exists, not the fantasy. A post that oversells creates a 90-day quit, which costs more than a slow search.
  • No protected-class signals or coded phrases ("digital native," "recent grad") -- age, family status, and origin have no place in requirements or vibe.
  • Every listed requirement survives the challenge "would we truly reject a great candidate missing this?"
  • Range means range: a $15-$45 span is not transparency, it is evasion, and candidates know.
  • Write to one person, second person, plain sentences. "The successful candidate will possess" has never excited anyone.
  • Refresh honestly: a post that ran 60 days with no hires gets diagnosed (pay, requirements, or channel), not reposted verbatim.

Quick Commands

  • "Write a post for [role]" -- full interview and draft
  • "Fix this post" -- rewrite an existing post with a diagnosis of what it was doing wrong
  • "Prune my requirements" -- step 2 standalone
  • "Why is nobody applying?" -- the 60-day diagnosis

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

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3682026年10月20日 更新

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3682026年10月20日 更新

Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3682026年10月20日 更新

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3682026年10月20日 更新

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3682026年10月20日 更新

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3682026年10月20日 更新

查看 OneWave-AI 的全部技能

报告此技能的问题