agent data_extraction tool_instruction risk: low

ELV PDF Symbol Counter Skill

The prompt defines the 'pdfcount' skill for PDF type detection (vector vs scanned), a 6-step workflow from file organization to discrepancy report, visual symbol tables per ELV sys…

PROMPT

---
name: pdfcount
description: Key sections:

PDF Type detection — Vector vs Scanned, different extraction strategy for each
Step-by-step workflow — 6 steps from file organization to discrepancy report
Visual symbol table — per ELV system (CCTV, FAS, ACS, PA, SC, IPTV, etc.)
Best practices — legend-first, one device type at a time, grid method, typical floor check
Confidence rating — High / Medium / Low per drawing
---

# My Skill

Describe what this skill does and how the agent should use it.

## Instructions

- Step 1: ...
- Step 2: ...

REQUIRED CONTEXT

skill name and description
key sections for PDF analysis

EXPECTED OUTPUT

Format

markdown

Constraints

use headings and bullet points
include step-by-step instructions

SUCCESS CRITERIA

Describe what this skill does.
Describe how the agent should use it.

CAVEATS

Missing context

Full 6-step workflow details
Criteria for PDF type detection (vector vs scanned strategies)
Examples or details for visual symbol tables per ELV system
Best practices implementation details
Confidence rating criteria
Input/output formats for the skill

Ambiguities

Incomplete instructions with placeholders like '- Step 1: ...'
Unclear what exactly 'pdfcount' skill accomplishes beyond bullet points
'# My Skill' header lacks actual description

QUALITY

OVERALL: 0.50
CLARITY: 0.65
SPECIFICITY: 0.40
REUSABILITY: 0.60
COMPLETENESS: 0.30

IMPROVEMENT SUGGESTIONS

Replace placeholders in Instructions with complete step-by-step content
Add a detailed paragraph under '# My Skill' describing the skill's purpose and usage
Expand key sections in description into actionable guidelines
Include examples of symbol tables, workflows, and confidence ratings
Specify expected inputs (e.g., PDF files) and outputs (e.g., discrepancy report format)

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.