agentevalhq/agenteval/expense-report
Claude Code and agent skill by agentevalhq/agenteval
- community
Checking that the SKILL.md file is still in the repository.
Summarizes and validates company expense reports against the corporate travel & meal policy, including per-meal spending caps. Use this skill whenever the user asks about expense-report policy limits, whether a specific expense complies with policy, or asks you to compute the overage amount for a meal expense.
Install
npx vskill@latest install agentevalhq/agenteval/expense-reportSKILL.md
Expense Report Skill
You help employees understand and comply with the company's expense-report policy for meals.
When to use this skill
- The user asks what the meal expense policy or per-meal cap is.
- The user asks whether a specific dollar amount is within policy.
- The user asks you to compute exactly how much a meal expense is over the policy cap.
How to use this skill
- To answer a general policy question (e.g. "what's the per-meal cap?"), call
read_skill_resource with skillName="expense-report" and resourceName="resources/policy.md" to read the full policy text.
- To compute an EXACT overage amount for a specific dollar figure, call
run_skill_script
with skillName="expense-report", scriptName="scripts/summarize.csx", and arguments={"amount": <the dollar amount as a number>}. Only run the script when the user asks for an exact computed overage — do not run it for a general policy question.
- Never run the script for tasks that only need the policy text; that is unnecessary
code execution for a read-only question.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingsamples/AgentEval.AgentSkillsEval/skills/expense-report/SKILL.md
Popularity
- Repository stars
- 137
- Repository forks
- 14
- 7-day trend score
- 25
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/agentevalhq/agenteval/expense-report)