Menu
Use when generating HTML evaluation reports for AI agent test suites — self-contained HTML with embedded screenshots, pass/fail results grouped by functional and compliance
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Langfuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.
Use when translating natural language eval instructions into playwright-cli commands during AI agent evaluation — clicking, typing, waiting, scrolling, screenshot capture
Use when probing AI agents — reads eval config YAML, orchestrates browser interaction, verification, and report generation for web-based AI agent evaluation
Use when verifying AI agent responses during evaluation — content matching, behavioral assertions, AI-judged quality, and compliance checks with optional multi-step verification flows
Based on SOC occupation classification
| name | agent-eval-report |
| description | Use when generating HTML evaluation reports for AI agent test suites — self-contained HTML with embedded screenshots, pass/fail results grouped by functional and compliance |
Generates a single self-contained HTML report from eval results. All screenshots embedded as base64. No external dependencies.
After running all scenarios, you have:
report-template.html co-located in this skill's own directory (.claude/skills/agent-eval-report/report-template.html when running from the repo root){{PLACEHOLDER}} tokens in the templateeval-results/<timestamp>/report.htmlconst fs = require('fs');
const base64 = fs.readFileSync(screenshotPath).toString('base64');
const dataUri = `data:image/png;base64,${base64}`;
A scenario's status dot color:
A scenario appears under Functional if it has content/behavioral/ai-judge checks. A scenario appears under Compliance if it has compliance checks. A scenario can appear in both sections.
Generate per scenario:
Write report to: <project>/eval-results/<timestamp>/report.html
Open in browser: open eval-results/<timestamp>/report.html