ai-job-agent
AGENTS.md0 starsChanged 3 months agoMITView on GitHub
AI Job Agent is built on the open Agent Skills specification (skills/*/SKILL.md) and standard CLI scripts. When invoked by an AI agent, skills read candidate truth from candidate/, execute deterministic Python helpers in scripts/, run Claim Check QA verification, and write results to output/.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository15 other files it gives its agents.
- .cursor/rules/job-agent.mdcCursor rule
- answer-questionsSkill
- claim-checkSkill
- daily-briefSkill
- find-broad-jobsSkill
- find-consulting-opportunitiesSkill
- find-jobsSkill
- record-outcomeSkill
- refresh-candidate-brandSkill
- research-target-personSkill
- review-search-performanceSkill
- score-fitSkill
- setup-profileSkill
- tailor-resumeSkill
- write-cover-letterSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 22
All skills follow the standard YAML frontmatter contract:
- Very specific: line 31
When invoked by an AI agent, skills read candidate truth from candidate/, execute deterministic Python helpers in scripts/, run Claim Check …
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
Agent Runtime Compatibility Matrix
AI Job Agent is built on the open Agent Skills specification (skills/*/SKILL.md) and standard CLI scripts.
Compatibility Matrix
| Runtime / Agent | Support Level | Discovery Method | Native Scheduling | Notes / Status |
| Standalone Python CLI | Tier 1 (Full) | CLI scripts | OS Task Scheduler / launchd / cron | Zero external dependencies; runs on pure Python 3.10+. |
| Hermes | Tier 1 (Full) | skills/*/SKILL.md + hermes_skills.json | Native Hermes Cron | First-class agent support with local-first tool calling. |
| Claude Code | Tier 1 (Full) | .claude-plugin/plugin.json + skills/ | Via external cron / terminal | Automatic slash commands (/find-jobs, /daily-brief). |
| Cursor | Tier 1 (Full) | .cursor/rules/job-agent.mdc | Via Task Scheduler / terminal | In-editor Composer & Chat integration. |
| Codex / OpenCode | Tier 1 (Full) | .codex-plugin/plugin.json + CLI | Via Task Scheduler / terminal | Full tool invocation and Python script execution. |
| ChatGPT Desktop / Web | Tier 2 (Guided) | File attachments in Projects / Custom GPT | Manual prompt / CLI | Full support via knowledge file uploads; automated scraping requires local Python helper. |
| Gemini / Claude Web | Tier 2 (Guided) | File uploads in Projects | Manual prompt | Grounded scoring and resume tailoring using uploaded profile documents. |
Agent Invocation Standard
All skills follow the standard YAML frontmatter contract:
---
name: skill-name
description: Clear, action-oriented description of capability
user-invocable: true
allowed-tools: Read, Write, RunCommand
---When invoked by an AI agent, skills read candidate truth from candidate/, execute deterministic Python helpers in scripts/, run Claim Check QA verification, and write results to output/.
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.