Agent skill

Auto Job Apply Assistant

by sharzoy in sharzoy/auto-job-apply

Scores how well your résumé matches a job posting on an A to C scale, writes a per-job application packet, and only submits after you explicitly confirm.

MITAuto-check passedBusiness, Finance & HR

Install Auto Job Apply Assistant

skills CLI
$ npx skills add sharzoy/auto-job-apply --skill auto-job-apply -a claude-code

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

GitHub CLI
$ gh skill install sharzoy/auto-job-apply auto-job-apply --agent claude-code

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

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

Facts

Skill name
auto-job-apply
GitHub stars
169
Token cost
~440 tokens
SKILL.md length
114 words
Files
26 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Scores how well your résumé matches a job posting on an A to C scale, writes a per-job application packet, and only submits after you explicitly confirm.

  • Works in 4 steps: profile.md from profile.template.md → Optional config.yaml → Always read resume before writing → …
  • Scoring how well a job posting matches your résumé before applying
  • SKILL.md covers Prerequisites, Output rule, Workflow and Safety
  • Generating a written application packet with HR-style feedback

What it does

Checks a job description against your profile for hard requirements first: any single unmet hard requirement caps the match score at 79, so it can never reach grade A, and two or more unmet requirements cap it at 59, grade C, regardless of how well the rest of the skills line up. Each scored job gets a single text packet saved under a grade-specific folder, named by date, company and role.

The packet includes a summary card with the grade, star rating and either a recommendation reason or a flagged reason to skip, a hard-requirements check, an HR-perspective read of the application, and concrete résumé wording suggestions. A grade or C-listed job is shown separately and never queued for one-click submission by default, and nothing is sent until you type an explicit approval phrase; the skill is told never to invent experience or leave secrets in committed files.

When your agent uses it

  • Scoring how well a job posting matches your résumé before applying
  • Generating a written application packet with HR-style feedback
  • Deciding which of several job matches to prioritize for submission
  • Getting résumé wording suggestions tailored to a specific job posting

Example prompts

  • “帮我把这个JD和我的简历做个匹配打分。”
  • “Generate application packets for all the A and B grade jobs in my queue.”
  • “帮我一键投递所有评分为A档的职位。”

Requirements

  • A profile.md file describing your background
  • Your résumé, read before each packet is written

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. profile.md from profile.template.md
  2. Optional config.yaml
  3. Always read resume before writing
  4. applications/log.md

What it can do on your machine

Read from SKILL.md and the folder at commit 035bf09. 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 1 file in scripts/, 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

Auto Job Apply Assistant loads about 440 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 114 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~440

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); the scripts in this folder are not scanned.

SKILL.md

The full file from sharzoy/auto-job-apply at commit 035bf09, republished under its MIT licence (© sharzoy). 114 words, ~440 tokens.

Download SKILL.mdSave it as .claude/skills/auto-job-apply/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.
name
auto-job-apply
description
Job apply skill: ABC match grades (A90–100 / B60–89 / C<60), hard-requirement anti-misjudgment caps, unified .txt packets in packets/A|B|C, HR simulation, resume wording tips, greetings, submit only after confirm. Use for 投简历, 自动投递, 打招呼, 一键投递, Boss, 前程无忧, JD匹配.

Auto Job Apply

Never submit until the user explicitly confirms.

Docs: README.md · docs/scoring.md · reference.md

Prerequisites

  1. profile.md from profile.template.md
  2. Optional config.yaml
  3. Always read resume before writing
  4. applications/log.md

Output rule

One .txt per job under grade folder:

text
applications/packets/A|B|C/<date>-<company>-<role-slug>.txt

Template: templates/packet.txt
Must include top 摘要卡(等级/星级/推荐原因或🚫原因/硬性核对)+ 一~六 + 七 HR视角 + 八 简历修改建议 + 九 投递备注.

Workflow

- [ ] 1. Ingest JD
- [ ] 2. Hard-requirement check → scorecard → A/B/C (docs/scoring.md)
- [ ] 3. Write packet into packets/{A|B|C}/
- [ ] 4. Dry-run
- [ ] 5. Confirm (A→B priority; C default skip)
- [ ] 6. Submit
- [ ] 7. Log (include grade)
Score → Grade
GradeScoreAction
A90–100优先投;简历建议「无需改」
B60–89可投;先包装表述(八)
C<60不推荐;写🚫原因;默认不进一键投递

防误判: 任 1 项 JD 硬性未过 → 分封顶 79(不能 A);≥2 项 → 封顶 59(C)。技能再像也不能强行 A。

Batch priority

Show/submit order: A high→low, then B high→low. C listed separately.

Approve phrases: 确认投递 / 一键投递 / 强制投递 …
Not approve: 先别投 / 跳过

Safety

  • No invented experience
  • No submit without confirm
  • No secrets in committed files

© sharzoy, 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 25 other files (scripts) in the repository root of sharzoy/auto-job-apply.

  • SKILL.md
  • .gitignore
  • GITHUB_RELEASE.md
  • LICENSE
  • README.md
  • applications/jobs/.gitkeep
  • applications/log.example.md
  • applications/packets/.gitkeep
  • config.example.yaml
  • docs/scoring.md
  • examples/sample-jd.txt
  • examples/sample-packet.txt
  • examples/sample-scorecard-hardfail-C.json
  • examples/sample-scorecard.json
  • profile.template.md
  • prompts
  • … and 10 more

Open the folder on GitHubat commit 035bf09

Compare with similar skills

Auto Job Apply Assistant 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.

Auto Job Apply Assistant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Auto Job Apply Assistant this skillsharzoy/auto-job-apply169—~440Automated safety check: PassMIT
Career-Ops Job Search Centercareer-ops-hq/career-ops74k—~3.6kAutomated safety check: PassMIT
Reactive Resume Builderreactive-resume/reactive-resume44k—~2kAutomated safety check: PassMIT
Internship Project Preparation ToolLiuMengxuan04/shushu-internship-tool2.1k—~2.3kAutomated safety check: PassCustom licence
Offer Negotiationreactive-resume/reactive-resume44k—~10kAutomated safety check: PassMIT
Job Application AssistantMadsLorentzen/ai-job-search45k—~1.2kAutomated safety check: NotesMIT

Similar skills

  • 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~3.6k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • 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~2k tokensUpdated yesterday
    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
  • Offer Negotiation

    reactive-resume/reactive-resume

    Evaluates and negotiates job offers. An agent skill from reactive-resume/reactive-resume.

    44k GitHub stars~10k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Job Application Assistant

    MadsLorentzen/ai-job-search

    Evaluates job postings against your profile, then tailors a LaTeX CV and cover letter and prepares interview answers for the roles you pursue.

    45k GitHub stars~1.2k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check: notes
  • Backend and Agent Project Selector

    lishuangqiang/backend-agent-resume-scout

    Finds backend or AI agent projects on GitHub that are worth putting on a resume, checks them against local source and writes a Markdown resume package.

    350 GitHub stars~1.4k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

Questions about Auto Job Apply Assistant

What does Auto Job Apply Assistant do?

Scores how well your résumé matches a job posting on an A to C scale, writes a per-job application packet, and only submits after you explicitly confirm. Checks a job description against your profile for hard requirements first: any single unmet hard requirement caps the match score at 79, so it can never reach grade A, and two or more unmet requirements cap it at 59, grade C, regardless of how well the rest of the skills line up. Each scored job gets a single text packet saved under a grade-specific folder, named by date, company and role.

When should I use Auto Job Apply Assistant?

Auto Job Apply Assistant fits situations like: scoring how well a job posting matches your résumé before applying; generating a written application packet with HR-style feedback; deciding which of several job matches to prioritize for submission; getting résumé wording suggestions tailored to a specific job posting.

How do I install Auto Job Apply Assistant in Claude Code?

Run `npx skills add sharzoy/auto-job-apply --skill auto-job-apply -a claude-code`. Or copy the skill folder (the sharzoy/auto-job-apply repository) into .claude/skills/auto-job-apply in your project. Claude Code loads it when a task matches its description.

How do I install Auto Job Apply Assistant in Codex?

Run `npx skills add sharzoy/auto-job-apply --skill auto-job-apply -a codex`. Or copy the skill folder (the sharzoy/auto-job-apply repository) into .agents/skills/auto-job-apply in your project. Codex loads it when a task matches its description.

Can I use Auto Job Apply Assistant 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 sharzoy/auto-job-apply --skill auto-job-apply -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-job-apply, .gemini/skills/auto-job-apply, .github/skills/auto-job-apply and .opencode/skills/auto-job-apply in your project.

What does Auto Job Apply Assistant need to run?

SKILL.md names no scripts, command-line tools or credentials: Auto Job Apply Assistant is instructions for the agent only. Our summary lists: A profile.md file describing your background; Your résumé, read before each packet is written.

Does Auto Job Apply Assistant 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 Auto Job Apply Assistant 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Auto Job Apply Assistant use?

Auto Job Apply Assistant 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 Auto Job Apply Assistant use?

About 440 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Auto Job Apply Assistant?

Skills that share tags, products or a category with Auto Job Apply Assistant: Career-Ops Job Search Center (career-ops-hq/career-ops, 74k stars), Reactive Resume Builder (reactive-resume/reactive-resume, 44k stars), Internship Project Preparation Tool (LiuMengxuan04/shushu-internship-tool, 2.1k stars) and Offer Negotiation (reactive-resume/reactive-resume, 44k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Auto Job Apply Assistant?

sharzoy (a GitHub user) maintains it in sharzoy/auto-job-apply, which has 169 GitHub stars. The repository was last updated on August 18, 2026.

Source: sharzoy/auto-job-apply on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.