Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/galiprandi/job-seekernpx agentmods add skills/galiprandi/job-seeker/profileWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/galiprandi/job-seeker/profile)<a href="https://agentmods.dev/skills/galiprandi/job-seeker/profile"><img src="https://agentmods.dev/badge/skills/galiprandi/job-seeker/profile/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/galiprandi/job-seeker/profile"><img src="https://agentmods.dev/badge/skills/galiprandi/job-seeker/profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 145 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 223 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.03014 |
| Opus 5 | $0.00013 | $0.01507 |
| Sonnet 5 | $0.00005 | $0.00603 |
| Haiku 4.5 | $0.00003 | $0.00301 |
Grade A, and why
profile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Profile
Pre-flight
- Load active preferences (see
memoryskill):node scripts/db.js "SELECT category, key, value, confidence, source FROM preferences WHERE user_id = <user_id> AND status = 'active' ORDER BY category, key" - Load existing profile if present:
node scripts/db.js "SELECT data->'profile' AS profile, data->'job_preferences' AS job_preferences, data->'style_profile' AS style_profile FROM users WHERE id = <user_id>" - If profile exists, validate changes before overwriting
Flow overview
Step 1: CV analysis → extract experience, sector, profile, inferred seniority
Step 2: Gap questionnaire → only what the CV doesn't clarify (adaptive to inferred profile)
Step 3: Current situation + expectations → employment status, urgency, salary, work mode, availability
Step 4: Strategy → targets, sources, aggressiveness (informed by everything above)
Step 5: Polish suggestion → align CV and LinkedIn profile to the job target to maximize matches
Step 1: CV analysis
Ask user for CV (URL or PDF). Extract:
- Full name and title/profession
- Professional summary (elevator pitch)
- Work experience (company, role, period, achievements, team size, reporting line if applicable)
- Core competencies and tools (tech stack, software, methodologies, equipment, whatever is relevant to the field)
- Soft skills (leadership, communication, etc.)
- Certifications and courses
- Education (degrees, institutions)
- Languages and proficiency level
- Quantifiable achievements (metrics, impact)
- Notable projects or relevant work samples
Step 1b: Inferred profile
From the CV data, infer:
| Signal from CV | Inferred field | Used for |
|---|---|---|
| Years of experience, previous roles | career_stage (intern, junior, mid, senior, staff, principal, director+) |
Which questionnaire blocks to show, seniority filtering |
| Team size managed, titles with Lead/Manager/Head | has_management (bool) |
Whether to show management-related questions |
| Core competencies and tools | core_skills |
Step 2 gap questions on skill preferences |
| Industries of previous employers | industry_history |
Step 2 gap questions on industry preferences |
| Company sizes (startup vs corporate) | company_size_history |
Step 2 gap questions on company size |
| Sector or functional area | sector |
Step 2 gap questions, platform tiering |
| Languages and publications/conferences | visibility_level |
Outreach tone, referral strategy |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 985ec9121324
- 12d ago First seen · 244 lines · 25 tokens per session scan A 637aef872e76
profile is a skill published in the GitHub repository galiprandi/job-seeker (26 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 3,014 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Application Form Filler
Fill out job application form fields with context-aware, tailored answers drawn from the candidate's CV and the job description.
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.
decision-heuristics
A set of heuristics for making difficult personal decisions such as changing jobs, buying a home, moving, forming a partnership, or getting married. It is intended for major choices, not everyday decisions.
productize-yourself
A Chinese-language coaching framework for finding a distinctive career, side business, or freelance direction. It combines personal strengths that are hard to teach with ways to turn them into repeatable products or content.
principal-agent
A Chinese-language guide based on the principal-agent idea: the person who owns a decision or its result may have different incentives from someone acting on another person's behalf. It applies this lens to jobs, companies, and partnerships.