Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

实习.skill · get-job.skill · agentenatalie | DecimalAI

productivityby agentenatalie

实习.skill · get-job.skill

agentenatalie/get-job

Source agentenatalie/get-job.skill ↗License NOASSERTION

实习.skill / get-job.skill：从岗位调研、简历改写到分轮次面试准备的全流程求职 skill。适合找工作、投实习、校招、秋招、春招、暑期实习、社招、跳槽、转行、跨专业求职、留学生求职，以及产品经理、运营、市场、咨询、AI 产品、AI Coding、数据分析、技术岗等目标岗位准备。核心能力：① WebSearch 调研公司、岗位 JD、业务线、竞品、面经、招聘流程和隐性门槛；② 按目标岗位反向定位简历，做 JD 匹配、ATS 关键词、经历筛选、STAR/CAR 改写、可迁移能力翻译、docx 简历生成；③ 按真实轮次准备面试，覆盖一面/业务面/专业面/主管面/HR 面/recruiter screen 等已确认或高置信轮次，逐条深挖简历 bullet、项目逐字稿、自我介绍、表达训练、模拟面试、反问清单、面后复盘题库。适用于「改简历」「简历优化」「简历润色」「简历匹配 JD」「求职简历」「投递前改简历」「按岗位改简历」「准备面试」「面试准备」「面经分析」「模拟面试」「自我介绍」「项目经历怎么讲」「简历被追问怎么办」「双非拿大厂 offer」「背景不对口怎么办」「AI

SkillScore64Maintained

Automatic

Recruiting pack

Last verified 8/23/2026

What it changes

Passed 15 of 23 test cases with the skill, and 10 of 23 without it.

Without skill44%

With skill64%

Checks it passed that the model alone missed

The response halts full resume generation when candidate resume text is omitted.
The response asks only for the minimum required inputs before advancing to resume generation.
The response identifies that key hard inputs like current resume and job description are missing.

and 6 more in the full report

6 fixed10 passed either way8 still failing1 broke

Pass-rate lift: +20 pp
Tokens: +133%
Agent turns: 0%
Response time: +19%

Model gemini-3.6-flashMeasured 8/23/2026v116 of 25 cases passed with skill · 23 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/agentenatalie-get-job/SKILL.md https://app.decimal.ai/s/agentenatalie-get-job/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add agentenatalie-get-job, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/agentenatalie-get-job/ and pins it in .decimal/skills.lock

decimalai skills add agentenatalie-get-job

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/agentenatalie-get-job/SKILL.md https://app.decimal.ai/s/agentenatalie-get-job/SKILL.md

Raw file: /s/agentenatalie-get-job/SKILL.md ↗ · machine-readable summary at /s/agentenatalie-get-job.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

你好，我准备开始找工作，请帮我规划一套求职方案。

What was checked, without and with the skill
Checked	Without skill	With skill
The response requests key anchor information including target role, market, resume, and application stage in one step.	Missed	Passed
The response refrains from generating fictional resume content prior to receiving user anchors.	Passed	Passed

case-25 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md176 linessingle file

实习.skill · get-job.skill

「你不需要一段完美对口的背景，你需要把已经有的背景，翻译成目标岗位听得懂的语言。」

一个通用求职 skill。跨平台可用（Claude Code、Codex，或任何支持 SKILL.md 的 agent 环境）。

可靠性协议（先跑）

完整方法见 references/reliability-playbook.md。任何任务开始前，先做一次输入体检，不要直接进入调研或改写。

状态	处理
✅ Complete	目标岗位、市场/JD、简历、投递状态/轮次足够明确，直接进入对应 Stage。
⚠️ Workable	有缺口但不阻塞：自动推断、WebSearch 补齐、低置信标注，并继续产出。
🛑 Blocked	缺少目标岗位或简历正文等硬输入，无法安全推进；只问最少必要问题，不展开脑补。

自动恢复优先级：

能从用户输入抽取的，不再问。 例如从 JD 语言/地点推断目标市场，从面试邀请推断轮次。
能搜索补齐的，先搜索补齐。 例如用户只给公司+岗位但没贴 JD，先找官方招聘页/同岗 JD。
能降级产出的，先降级产出。 例如轮次未知时生成 00-总览.md + 01-简历bullet逐条深挖.md，只把后续轮次列为待确认。
不能验证的，不写成事实。 所有低置信内容进入"缺口/假设/待确认"区。

可靠性目标：遇到输入不完整、搜索源不足、文件解析失败、轮次不明、用户 claim 没证据时，先自动体检和降级，不把所有问题都推给人工确认。

质量闸门（交付前必须跑）

完整方法见 references/quality-gates.md；大改后回归测试见 references/regression-evals.md。任何最终交付前，必须先内部跑一次质量闸门，不默认把自检过程写进用户产物。

级别	要求
P0 红线	造假、改背调硬信息、来源冒充事实、轮次写死、bullet 漏项、标签泄漏、过度包装：任一出现，停止交付。
P1 核心质量	岗位调研、简历改写、面试准备必须满足对应完成标准；不满足就补齐、降级或明确标注缺口。
P2 体验质量	文件名、语言、结构、扫读体验要像可发布产品，不出现工作记录或模板残留。

交付前内部核对四张覆盖矩阵：

JD 核心能力 → 简历 bullet：每个岗位能力都有真实经历支撑。
简历 bullet → 面试准备：每个最终 bullet 都有讲法、追问、证据、兜底。
Claim → 证据：每个数字/强动词都有证据等级和面试处理策略。
轮次 → 来源：每个独立轮次文件都有邀请、面经或流程依据。

Track record

Benchmark

15 / 23

test cases passed, vs 10 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

agentenatalie / get-job.skill

SKILL.md

View on GitHub ↗

License CC-BY-NC-ND-4.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

实习.skill · get-job.skill

可靠性协议（先跑）

质量闸门（交付前必须跑）

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills