job-analyzer
Skill0 starsChanged 6 months agoMITView on GitHub
Analyze saved job listings for fit against the user's profile. Fetches actual job descriptions, rates suitability, and flags criteria the user cares about. Use when the user wants to analyze job listings from HTML, URLs, or structured data.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Rish-Modi/career-agenttheir own version, first seen Jun 3, 2026
- sameergdogg/job-search-skillstheir own version, first seen Mar 5, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- sameergdogg/job-search-skills★ 14same name
- Rish-Modi/career-agent★ 2same name
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.
In this repository3 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Read the user's profile from their resume.
- Distinctive: line 31
If the user has stated preferences in their message (e.g.
- Distinctive: line 49
If the user specifies flags in their message, apply them to every job in the analysis.
- Distinctive: line 54
If no resume has been shared in the conversation, ask for it before proceeding.
- Distinctive: line 67
Use WebFetch on every job URL simultaneously.
- Distinctive: line 95
Not mentioned / not a concern = ✅
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Job Analyzer Skill
Analyze job listings and rate their fit against the user's profile. Always fetch and read the actual job posting — never assess based on title alone.
Getting the user's profile
Read the user's profile from their resume. If they haven't shared one yet, ask:
"Please share your resume — paste the text, attach the file, or drop in the HTML. I'll use it as your profile for the analysis."
Extract from the resume:
- Current role and company
- Key achievements (especially quantified ones)
- Domain background and core skills
- Previous roles and companies
- Education
- Languages and proficiency levels
- Any location or role preferences mentioned
If the user has stated preferences in their message (e.g. "I want to stay in London" or "I'm only looking at senior roles"), combine those with what's in the resume.
Custom flags
Users can also ask the skill to watch out for specific things at analysis time:
"Flag anything that requires French language"
"Note if the role requires a work visa"
"Mark as ❌ any roles that are fully on-site"
Examples of things users commonly flag:
- A specific language being required
- Work authorisation or visa requirements
- Specific tools or tech stacks that are deal-breakers
- Travel or relocation requirements
- Salary or equity mentions
- Remote vs. on-site requirements
If the user specifies flags in their message, apply them to every job in the analysis.
Workflow
Step 1 — Get the resume
If no resume has been shared in the conversation, ask for it before proceeding.
Step 2 — Extract job listings from input
Parse the user's input (HTML, plain text, or URLs) to get:
- Job title
- Company
- Location
- LinkedIn job URL
Step 3 — Check for custom flags
Re-read the user's message for any specific things to watch out for. These will be applied in Step 4.
Step 4 — Fetch all job URLs in parallel
Use WebFetch on every job URL simultaneously. For each job extract:
- Full job description
- Required qualifications
- Preferred qualifications
- Anything matching the user's custom flags
Step 5 — Analyze each job against the profile
For each job assess:
- Domain fit — does the user's background match what the JD asks for? Be honest about gaps.
- Level fit — does the seniority match?
- Location — is it where the user wants to be?
- Custom flags — mark each flagged criterion as ❌ (hard blocker), ⚠️ (worth noting), or ✅ (not mentioned / fine)
- Overall fit — ⭐ to ⭐⭐⭐⭐⭐
Step 6 — Present results
First, a summary table:
| Role | Company | Location | Fit | Flags | Key note |
Then: top 3 picks with 2–3 sentences explaining why each fits or doesn't.
Key Rules
- Always fetch the actual JD — title-based guesses mislead analysis
- Always read the actual resume — don't make up or assume profile details
- Hard blockers (user said "must not") = ❌, mark clearly
- Worth noting (user said "flag" or "note") = ⚠️
- Not mentioned / not a concern = ✅
- Be direct about skill gaps — don't oversell fit to seem encouraging
- Fetch all URLs in parallel to save time
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.

