diegosouzapw/awesome-omni-skill / skills/ai-agents/agent-parser
agent-parser
VerifiedEnd-to-end resume parsing (detect format → extract fields). Uses a combination of format detection, text extraction, and LLM parsing to normalize resume data.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 956 B |
| metadata.json | config | 1.4 KB |
SKILL.md
View on GitHub---
name: agent-parser
description: End-to-end resume parsing (detect format → extract fields). Uses a combination of format detection, text extraction, and LLM parsing to normalize resume data.
---
# Parser Agent
## Overview
The Parser Agent handles the ingestion of resume files. It follows a multi-step workflow:
1. Detects file format (`detect-resume-format`)
2. Extracts raw text (`extract-text-pdf`, `extract-text-docx`)
3. Sanitizes text (`sanitize-text`)
4. Parses identifying fields (`llm-parse-resume`)
## Workflow Definition
1. **Input**: Resume file path.
2. **Detection**: Call `detect-resume-format` script.
3. **Extraction**:
* If PDF: Call `extract-text-pdf`
* If DOCX: Call `extract-text-docx`
* If Unknown/Txt: Read file directly
4. **Sanitization**: Call `sanitize-text`.
5. **Parsing**: Call `llm-parse-resume`.
6. **Validation**: Call `schema-validate-resume`.
7. **Output**: Validated JSON object.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |