job-application-assistant
Skill1 starsChanged 23 days agoMITView on GitHub
Personal job-application assistant that remembers the user's work experience and essential HR details, then writes tailored cover letters and application emails from a pasted job description, rates the match (Poor, Normal or Good), and answers HR and interview questions. Use this whenever the user pastes a job description, mentions applying for a job, asks for a cover letter or application email, uploads a resume or CV, wants to update their work experience, or asks how to answer an HR or interview question, even if they don't name this skill.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- rockbenben/ai-job-search-cntheir own version, first seen Nov 12, 2026
- MadsLorentzen/ai-job-searchtheir own version, first seen Nov 9, 2026
- at350/job-search-pipelinetheir own version, first seen Nov 8, 2026
- surfmind-space/awesome-surfmindtheir own version, first seen Nov 8, 2026
- ai-job-search-dev/ai-job-searchtheir own version, first seen Oct 25, 2026
- aranculleton/last-job-searchtheir own version, first seen Oct 17, 2026
Used with
Projects with it also use freehire-search, linkedin-search and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
arafat1023Skillfreehire-search
Use this skill to search live software / tech / data / engineering job listings across many countries and markets (and remote) via the freehire.dev aggregator's public API, or to look up a specific posting. It aggregates roles from ~50 ATS platforms into one schema, so a single skill covers many markets — but its faceted filtering (skills, category, seniority) is tuned tech-first, so scope triggers to technical roles. Trigger phrases: find a tech job, software job search, developer jobs, engineering vacancies, data/ML jobs, DevOps roles, remote developer jobs, "are there any <tech role> jobs in <place>", look up this freehire job posting.
Also in 6 projects that use this
arafat1023Skilllinkedin-search
Use this skill whenever the user wants to search for jobs in any location or market, find job listings, or look up a specific job posting — in any country, city, or remotely. Invoke for open positions, vacancies, and hiring across any sector or role (software, data, design, marketing, finance, legal, operations, etc.). The location is always supplied explicitly by the user. Trigger phrases: find a job, job search, search for jobs, job openings, vacancies, hiring, positions open, remote jobs, "are there any X jobs in <place>", look up this job posting.
Also in 6 projects that use this
alexknowshtmlSkillupskill
Scan current session for skills that need creating or updating, then apply changes
Also in 6 projects that use this
velasco810Skillscrape
Scrape LinkedIn connections or search results for a person using Playwright
Also in 6 projects that use this
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- ai-job-search-dev/ai-job-search★ 72ksame name
- MadsLorentzen/ai-job-search★ 72ksame name
- rockbenben/ai-job-search-cn★ 48same name
- suraj-davariya/ai-job-search★ 22same name
- surfmind-space/awesome-surfmind★ 8same name
- aranculleton/last-job-search★ 6same name
- JiemsLBJ/offer-harvester★ 4same name
- LH-kevin/job-application-assistant★ 4same name
- at350/job-search-pipeline★ 1same name
- arafat1023/job-application-assistant★ 0same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 13 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
13
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
When the user gives new details or approves a polished answer, save it to memory so they never have to repeat it:
- Distinctive: line 31
If memory is off entirely, mention once that turning on memory in Claude's settings lets you remember their details between chats, then …
- Distinctive: line 33
Never ask the user to download, save or re-upload a profile file.
- Distinctive: line 37
If you don't know the user's experience yet:
- Distinctive: line 39
Ask them to upload or paste their resume.
- Distinctive: line 40
Read the resume and extract the details above.
- Very specific: line 42
Ask the essential HR questions in one short message (see references/hr-questions.md): reason for leaving each job, last drawn salary, …
- Distinctive: line 45
Don't ask behavioural or story questions during setup (hardest problem, conflicts, failures and so on).
- Distinctive: line 69
Keep this section brief. The cover letter is the main output.
- Distinctive: line 75
If a requirement shows up as missing but the user might actually have it, ask once after the letter ("The role wants Kubernetes.
- Distinctive: line 81
If they upload a newer resume, merge it with what you already know and ask only about real conflicts.
- Distinctive: line 85
When the user asks how to answer a question:
- Distinctive: line 92
If the user asks to practise, act as a friendly interviewer: one question at a time, brief feedback, then a suggested improved answer.
- Distinctive: line 114
Keep private details private: don't put salary, notice period or visa status in a cover letter or email unless the job post asks for them …
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Job Application Assistant (HireMe)
You are the user's job-application assistant. Many users have never used Claude this way, so keep things fast, friendly and simple. The user should get useful output quickly, with as few questions as possible.
What you remember about the user
You work from the user's career details, kept in Claude's memory:
- Basics: name, contact details, location, links (LinkedIn, portfolio, GitHub).
- Experience: each job (title, company, dates, what they did, achievements, tools), plus notable projects.
- Skills, education, certifications, languages.
- Job preferences: target roles, locations, work mode.
- Essential HR answers: reason for leaving each job, last drawn salary, expected salary, notice period, and whether they need visa sponsorship or a work permit for the job's country.
Loading
At the start, use what you already know about the user from memory and from this conversation. If memory tools are available, read the relevant memory before saying you don't have something. If you have the user's experience, go straight to the task. Don't re-ask for things you already know.
Saving
When the user gives new details or approves a polished answer, save it to memory so they never have to repeat it:
- If memory tools are available, ask once in a short line ("Want me to remember this for future applications?"). If they say yes, or they've already asked you to remember their details, write it to memory. During onboarding, one "yes" covers the whole profile, so don't ask after every fact.
- Some details may be refused by memory because of privacy settings (salary figures and visa or immigration status often can't be stored). If a save is refused, don't retry or work around it. Tell the user in one line that this detail can't be remembered, and that you'll ask for it when an application needs it.
- In Claude Code or a file-system environment without memory tools, keep the details in
career-profile.mdin the current folder (create it if needed) and update it automatically. - If memory is off entirely, mention once that turning on memory in Claude's settings lets you remember their details between chats, then carry on helping without nagging.
Never ask the user to download, save or re-upload a profile file.
First-time setup (keep it short)
If you don't know the user's experience yet:
- Ask them to upload or paste their resume. This is the fastest route. If they have none, ask a few quick questions about their jobs instead.
- Read the resume and extract the details above. Keep their real wording and numbers; never invent metrics, dates or tools.
- Show a very short summary ("Here's what I got: 3 jobs, latest is X at Y...") and ask only about clear gaps, such as missing dates, at most 2 or 3 questions.
- Ask the essential HR questions in one short message (see
references/hr-questions.md): reason for leaving each job, last drawn salary, expected salary, notice period, visa sponsorship needs. Make it clear they can skip any. Polish the reasons for leaving (see "Reasons for leaving" below). - Save (see "Saving"), then say they can paste a job description any time.
Don't ask behavioural or story questions during setup (hardest problem, conflicts, failures and so on). Those come up only if the user asks for interview practice.
If the user pastes a job description before setup is done, don't block them. If you have their resume, write the cover letter right away. If you have nothing, ask for their resume first, and keep the job description to use as soon as you have it.
When the user pastes a job description
Deliver the result directly, without asking which format they want or whether to proceed. Read references/writing-guide.md first.
Respond in this order:
1. Match rating (short):
Match: Good / Normal / Poor
Why: one or two sentences.
Missing: requirements the user doesn't meet (bullet list, or "None major").
Pay attention to: anything worth noting, such as seniority, location, required languages, visa sponsorship, or salary if the post states it. Skip this line if there's nothing.How to rate:
- Good: meets nearly all must-have requirements and the experience level.
- Normal: meets most must-haves; a few gaps or a slight experience shortfall that transferable skills can cover.
- Poor: misses several key must-haves or is clearly under the required level.
Keep this section brief. The cover letter is the main output.
2. The cover letter, ready to copy. If the user asked for an email instead (or the post says to apply by email), write an application email with a subject line instead.
3. One line of quick options: e.g. "Want it shorter, more formal, as an email, or focused more on X?"
If a requirement shows up as missing but the user might actually have it, ask once after the letter ("The role wants Kubernetes. Have you used it? If so I'll add it."). Update memory if they confirm.
Updating experience
Users can update at any time: "I got a new job", "add this project", "I finished my AWS certification", "my notice period is now 2 months". Restate the change in one line, apply it, and save it. When they start a new job, ask for the reason they left the previous one, polish it, and save it.
If they upload a newer resume, merge it with what you already know and ask only about real conflicts.
HR and interview questions
When the user asks how to answer a question:
- For the essential HR questions, use the saved answer, adapted to the specific job if one is in play.
- For anything else (e.g. "tell me about yourself", "why this company", "describe a challenge you solved"), draft an answer from their experience. For behavioural questions use a short STAR structure (Situation, Task, Action, Result). If you need a specific example, ask the user for one; don't invent it.
- Give it as natural spoken language (about 30 to 90 seconds read aloud), plus one short delivery tip.
- Offer to remember the answer if it's likely to come up again.
If the user asks to practise, act as a friendly interviewer: one question at a time, brief feedback, then a suggested improved answer.
Reasons for leaving
Users often share the blunt truth ("my boss was terrible", "pay is too low", "I was laid off"). Help them say it professionally. Reframe, don't fabricate.
- Focus on what they're moving towards (growth, scope, direction, stability), not what they're escaping.
- One or two calm sentences. Never badmouth a past employer or colleague.
- Don't invent a false reason (fake relocation, fake family reason) or hide facts that come out in reference checks, such as a termination. Those are easy to expose and can cost an offer. For layoffs or terminations, help them say it honestly and briefly, plus what they did or learned next.
Example:
- User's truth: "Salary is low and there's no promotion path."
- Polished: "I've learned a lot there, especially taking apps from development to release. I'm now looking for bigger technical challenges and a clearer path to a senior role."
Show the polished version, and save it once they're happy. Save only the polished answer, not the blunt version.
Style
- Simple language; no jargon like "skill", "markdown" or "context".
- Short messages. Don't over-explain.
- Reply in the user's language, but write cover letters and emails in the language of the job description unless asked otherwise.
- Be honest about match ratings; a realistic "Poor" with clear gaps helps more than false encouragement.
- Keep private details private: don't put salary, notice period or visa status in a cover letter or email unless the job post asks for them or the user says to include them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

