NVIDIA/SkillEvaluator is a framework for checking and evaluating AI-agent skills, which are instruction folders that extend an agent's behavior. Skill authors and agent developers use it to validate quality and security, detect overlap, generate evaluation data, and measure skills through live agent tests. The catalogue entries are skills for running these evaluation workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/nvidia/skillevaluator/text-analyzernpx skills add NVIDIA/SkillEvaluator --skill text-analyzergit clone --depth 1 https://github.com/NVIDIA/SkillEvaluatorWrote 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/nvidia/skillevaluator/text-analyzer)<a href="https://agentmods.dev/skills/nvidia/skillevaluator/text-analyzer"><img src="https://agentmods.dev/badge/skills/nvidia/skillevaluator/text-analyzer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00042 | $0.00408 |
| Opus 5 | $0.00021 | $0.00204 |
| Sonnet 5 | $0.00008 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
text-analyzer 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 5d 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.
What it actually says
Text Analyzer
Analyze text and produce structured statistics.
Purpose
Provide quick text analytics — word counts, line counts, character counts, top frequent words, average word length, and sentence count — for any plain-text input.
Agent Instructions
- Read this SKILL.md to understand capabilities.
- Run
scripts/analyze_text.pywith the appropriate arguments. - Return the analysis results to the user.
Examples
Usage
# Analyze inline text
python scripts/analyze_text.py --text "Your text content here"
# Analyze a file
python scripts/analyze_text.py --file /path/to/file.txt
# JSON output (default is human-readable)
python scripts/analyze_text.py --text "Hello world" --json
Output
The script prints a structured report with:
- Word count — total words
- Line count — total lines
- Character count — total characters (including whitespace)
- Sentence count — estimated sentence count
- Average word length — mean characters per word
- Top 5 words — most frequent words and their counts
Limitations
- Sentence detection uses simple period/question/exclamation splitting; may be inaccurate for abbreviations (e.g., "U.S.A.").
- Non-UTF-8 files will be read with errors replaced.
Troubleshooting
| Problem | Fix |
|---|---|
FileNotFoundError |
Check the --file path exists |
| Empty output | Ensure --text or --file is provided |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 62 lines · 42 tokens per session scan A de75c5f47d71
text-analyzer is a skill published in the GitHub repository NVIDIA/SkillEvaluator (399 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 408 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.
Other skills, from other repositories
skill-authoring
Create, revise, or remove reusable procedural and interactive skills; use memorystore for facts and preferences.
rt7-supply-chain
Red-team an AI agent's skill / plugin / MCP supply chain — can a poisoned skill doc, a malicious MCP server, or a dependency-confused package become persistent executable instruction? Authorized testing of agents you own or are permitted to test.
onboarding-guide
Guides new users through a friendly onboarding experience.
code-reviewer
Reviews code changes and suggests improvements.
deploy-service
Deploy a service to the staging environment via shell commands.
general-assistant
Use when you need help with anything.