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 skills add tuanductran/hr-skills --skill hr-ai-evaluationgit clone --depth 1 https://github.com/tuanductran/hr-skillsWrote 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/tuanductran/hr-skills/hr-ai-evaluation)<a href="https://agentmods.dev/skills/tuanductran/hr-skills/hr-ai-evaluation"><img src="https://agentmods.dev/badge/skills/tuanductran/hr-skills/hr-ai-evaluation/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.
<a href="https://agentmods.dev/skills/tuanductran/hr-skills/hr-ai-evaluation"><img src="https://agentmods.dev/badge/skills/tuanductran/hr-skills/hr-ai-evaluation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00076 | $0.00888 |
| Opus 5 | $0.00038 | $0.00444 |
| Sonnet 5 | $0.00015 | $0.00178 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
hr-ai-evaluation 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI tool evaluation for HR
Evaluate AI tools and vendors being considered for HR use cases — screening, sourcing, chatbots, analytics — against accuracy, bias, transparency, and fit-for-purpose criteria before adoption.
Supported tasks
- Building an AI vendor evaluation framework tailored to HR use cases
- Assessing AI tools for accuracy and reliability claims against real evidence
- Evaluating AI tools for bias risk and disparate impact potential
- Comparing multiple AI vendors for the same HR use case
- Designing a pilot program to test an AI tool before full rollout
- Assessing vendor transparency around model training data and methodology
- Evaluating data privacy and security implications of an AI vendor
- Reviewing AI vendor claims critically rather than taking marketing at face value
- Building evaluation scorecards for AI tool procurement decisions
- Assessing integration feasibility of an AI tool with existing HR systems
- Documenting AI evaluation decisions for audit and compliance purposes
- Re-evaluating existing AI tools periodically as they update or as regulations shift
Key prompts
Building the framework
- "Build an AI vendor evaluation framework for [use case, e.g. resume screening, interview scheduling, chatbot] covering accuracy, bias, transparency, and cost."
- "What questions should we ask an AI vendor about their model's training data and bias testing before considering adoption?"
- "Design an evaluation scorecard to compare multiple AI vendors for [HR use case] on a consistent basis."
- "What red flags in a vendor demo or sales pitch should make us slow down and dig deeper before proceeding?"
Assessing risk
- "What bias risks should we specifically evaluate for an AI tool used in [screening/sourcing/performance assessment]?"
- "Critically assess this vendor's accuracy and fairness claims — what evidence would we need to actually validate them?"
- "What data privacy and security questions should we ask before allowing this AI tool access to employee or candidate data?"
- "What legal or regulatory review should this AI tool go through before we allow it to influence [hiring/performance] decisions?"
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.
- 12d ago First seen · 65 lines · 76 tokens per session scan A ccf9d79476f7
hr-ai-evaluation is a skill published in the GitHub repository tuanductran/hr-skills (57 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 888 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…