Job search
Use when someone is job hunting or looking for freelance-to-full-time or contract roles, tracking applications, researching target companies, tailoring CV/cover-letter materials to a specific posting, spotting job-post red flags (ghost jobs, vague pay, overwork signals), and preparing for interviews. Trigger when the user mentions applying to jobs, a job posting, their resume/CV for an application, company research before an interview, or managing an application pipeline. Keeps the user's own voice, not generic AI.From its SKILL.md
npx -y skills add mehtab78/skills --skill job-searchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.3 KB, 600 tokens by cl100k_base, as published. Nobody here has run it
Job search
Help the user run a focused, high-quality search, not a spray of generic applications. The whole approach assumes fewer, better-targeted applications beat volume, because volume burns reputation and time.
Keep state in a workspace
Persist everything in ~/job-search/ so context survives across sessions. See
references/memory-template.md for the files to create and their shape:
~/job-search/
├── memory.md # preferences and target criteria (read this first)
├── applications.md # the live pipeline
├── companies.md # research on target companies
├── materials/ # CV variants, cover letters
└── archive/ # closed-out applications
Principles that shape the work
- Quality over volume. Five tailored applications beat fifty generic ones; each needs company-specific customization.
- Keep the user's voice. Materials must sound like them, not like AI. Ask for a writing sample to match tone, and don't keyword-stuff at the cost of authenticity; recruiters notice, and ATS optimization that reads robotic gets rejected by the human behind it anyway.
- Verify "remote" claims. Check for geographic restrictions, timezone-overlap expectations, and tax/legal fine print before treating a role as truly remote.
- Research before applying. For each target, look at financial health,
recent news, and current-year Glassdoor sentiment. Details in
references/research.md. - Track every application's state in
applications.md: company, role, date, status, next action, contacts, and follow-up reminders.
Reading job-post red flags
| Signal | Likely meaning |
|---|---|
| Posted 3+ months | Ghost job or high turnover |
| "Rockstar / ninja" language | Overwork culture |
| Vague pay ("competitive") | Probably below market |
| "Young, dynamic team" | Possible age bias |
| Recent mass layoffs | Instability |
Adjust to the person
| User | What to prioritize |
|---|---|
| Senior (10+ yrs) | Network activation, discretion, comp negotiation |
| Junior / new grad | Volume-with-quality, entry-friendly companies |
| Career changer | Transferable-skills narrative, bridge roles |
| Urgent need | Speed, temporary options, immediate income |
For interview prep, see references/interviews.md.
Traps to avoid
- Keyword-stuffing to beat ATS at the cost of a human rejecting the robotic text.
- Trusting stale salary data: verify ranges are current.
- "Perfect match" overconfidence: 60% of requirements met still often means a no.
- Networking advice with no warm-intro strategy behind it.
- Long-game "build your brand" advice when the user needs income this month.
What ships with it: 3 files
4.6 KB alongside SKILL.md
references/
- interviews.md1.8 KB
- memory-template.md1.4 KB
- research.md1.4 KB
Gives 0 of the 12 instructions most hr recruiting skills give in 600 tokens
Counted across 356 of the 357 authors here whose files we hold, read 2026-08-07
- Quantify achievements with specific metricsin 14 of 356, across 6 files
- Keep the resume under two pagesin 14 of 356, across 6 files
- Request the full job description if not providedin 12 of 356, across 4 files
- Extract keywords and prioritize job requirementsin 12 of 356, across 4 files
- Stop and ask for clarification if required inputs are missingin 12 of 356, across 5 files
- Map candidate experience to job requirementsin 11 of 356, across 3 files
- Ask if the user wants adjustmentsin 11 of 356, across 3 files
- Provide strengths and gap analysis after the resumein 10 of 356, across 2 files
- Request candidate background details if not providedin 10 of 356, across 2 files
- Format experience bullets as action verb plus resultin 10 of 356, across 2 files
- Ask for missing inputs before startingin 10 of 356, across 9 files
- Use exact job description terminologyin 9 of 356, across 1 file
Said here and by no other author read
- keep state in the workspace directory
- read the preferences file first
- tailor applications to each company
- ask for a writing sample to match tone
- verify remote work claims
- research financial health before applying
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.