ai-job-search: Command for Claude Code

.claude/commands/upskill.md

upskill is a command for Claude Code from suraj-davariya/ai-job-search. It costs 32 tokens per session (608 once invoked), scanned A, original, MIT.

A career-development command that compares a candidate's skills with job requirements and creates a prioritized learning-gap report.

In plain words
What is it for?
Use it for an aggregate analysis of tracked jobs or a targeted analysis of one job posting, then save a web-sourced learning plan and report.
Why use it?
It shows which skills are missing across tracked jobs or a specific posting, so learning can be focused on the most important gaps.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

This is suraj-davariya/ai-job-search's own configuration. It tells Claude Code how to work on ai-job-search itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-job-search configures →

Reuse

Borrowing it

Nothing to install: this file belongs to suraj-davariya/ai-job-search. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/suraj-davariya/ai-job-search/main/.claude/commands/upskill.md
Clone the repo
git clone --depth 1 https://github.com/suraj-davariya/ai-job-search

Made for: Claude Code.

Wrote 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.

agentmods badge for upskill

README.md
[![agentmods](https://agentmods.dev/badge/commands/suraj-davariya/ai-job-search/upskill/github.svg)](https://agentmods.dev/commands/suraj-davariya/ai-job-search/upskill)
Your own site
<a href="https://agentmods.dev/commands/suraj-davariya/ai-job-search/upskill"><img src="https://agentmods.dev/badge/commands/suraj-davariya/ai-job-search/upskill/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.

agentmods 80×15 button for upskill

Your own site · 80×15
<a href="https://agentmods.dev/commands/suraj-davariya/ai-job-search/upskill"><img src="https://agentmods.dev/badge/commands/suraj-davariya/ai-job-search/upskill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00608
Opus 5 $0.00016 $0.00304
Sonnet 5 $0.00006 $0.00122
Haiku 4.5 $0.00003 $0.00061

Measured 11d ago against content hash 9722521ad48e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

upskill 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 11d ago.

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.

.claude/commands/upskill.md · 46 lines

What it actually says

/upskill — Skill Gap Analysis

Spec: REQ-3001–3011, ARCH-0040 (Career Development), ARCH-0008 Backed by: the career-development Plane-1 skill Used by: the dashboard Upskill surface (reads the upskill/report-*.md files this produces)

Activate the career-development skill and run its full workflow:

  1. Pick the mode (REQ-3001):
    • /upskill (no argument) → aggregate mode — analyze every job in job_search_tracker.csv. If the tracker is empty, say so and suggest targeted mode instead of writing an empty report.
    • /upskill <url> (or pasted posting text) → targeted mode — analyze one posting. If the URL can't be fetched, ask for a paste (DEC-011); never abort.
  2. Load data (REQ-3002, REQ-3003) — candidate profile always; tracker + most recent previous report in aggregate mode; the fetched/pasted posting in targeted mode.
  3. Pass 1 — hard-skill diff (REQ-3004) — required/preferred skills vs. profile, fit-weighted in aggregate mode; generous matching removes skills already held.
  4. Pass 2 — synthesis (REQ-3005) — domain / soft / tooling / credential gaps.
  5. Gap heatmap (REQ-3006, REQ-3011) — Critical/High/Medium/Low table printed first; Low gaps listed but not planned.
  6. Learning plan (REQ-3007) — 2–3 real, web-searched resources per Critical/High gap (and Medium when <5 gaps total), with study direction and time estimate. Never fabricate resources (ARCH-0007).
  7. Study order (REQ-3008) — dependency-aware numbered sequence with total time.
  8. Save the report (REQ-3009, REQ-3010) — always write upskill/report-YYYY-MM-DD.md (aggregate) or upskill/report-YYYY-MM-DD-<company>-<role>.md (targeted), including the since-last delta in aggregate mode.

Full behavior lives in .claude/skills/career-development/SKILL.md.

Changes

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.

  1. 11d ago First seen · 46 lines · 32 tokens per session scan A 9722521ad48e

Subscribe to this mod's changes

upskill is a command published in the GitHub repository suraj-davariya/ai-job-search (22 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 608 once invoked, about $0.0002 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.