菜单
Visual + structural verification of HTML benchmark/validation reports using the Claude-in-Chrome extension. Opens the report in a browser, takes screenshots, checks key DOM elements, and produces a PASS/FAIL verdict. Generic by default; module-specific check lists extend the base set.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/vamseeachanta/workspace-hub --skill html-report-verify命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | html-report-verify |
| description | Visual + structural verification of HTML benchmark/validation reports using the Claude-in-Chrome extension. Opens the report in a browser, takes screenshots, checks key DOM elements, and produces a PASS/FAIL verdict. Generic by default; module-specific check lists extend the base set. |
| type | reference |
| version | 1.0.0 |
| category | development |
| last_updated | "2026-02-19T00:00:00.000Z" |
| tools | ["Bash","Task","mcp__claude-in-chrome__tabs_context_mcp","mcp__claude-in-chrome__tabs_create_mcp","mcp__claude-in-chrome__navigate","mcp__claude-in-chrome__computer","mcp__claude-in-chrome__read_page","mcp__claude-in-chrome__javascript_tool","mcp__claude-in-chrome__find","mcp__claude-in-chrome__read_console_messages"] |
| related_skills | ["verification-loop","webapp-testing"] |
| tags | ["html","reporting","verification","chrome","visual-qa","benchmark","orcawave"] |
| platforms | ["windows","linux","macos"] |
Opens an HTML report in Chrome (via local HTTP server for local files) and performs layered verification: console errors → DOM structure → visual scan → module-specific checks.
/html-report-verify <path-or-url> [--module <name>]
Examples:
/html-report-verify docs/modules/orcawave/L00_validation_wamit/3.2/benchmark/benchmark_report.html --module orcawave-qtf
/html-report-verify http://localhost:8974/3.1/benchmark/benchmark_report.html
If a local path is given, start a Python HTTP server in the parent directory on
a free port (default 8974). Use uv run python -m http.server so the uv
environment is active. For background tool launches, explicitly cd into the
intended server root inside the command (for example cd /path/to/repo && python -m http.server 8974) rather than relying only on the tool's workdir; a wrong server root produces misleading 404s even when the file exists. Kill the server after verification is complete.
For a user asking only for a clickable HTML review link, do the minimal hyperlink path instead of full visual QA: start or reuse a local server from the artifact's parent directory, move to the next free port if the default is occupied, verify the exact URL returns 200 OK with curl -I/HEAD, then return a concise Markdown hyperlink plus artifact path and verification status. Do not present an unverified server-start URL as review-ready.
mcp__claude-in-chrome__navigatemcp__claude-in-chrome__read_console_messages for JS errors (onlyErrors: true)Run via mcp__claude-in-chrome__javascript_tool:
For static local collateral where browser/MCP verification is unnecessary or unavailable, use Python stdlib html.parser for basic title/link/content checks instead of depending on BeautifulSoup; many worktree/agent environments do not have bs4 installed.
| Check | Selector / Test | Pass Condition |
|---|
| Title present | document.title | Non-empty string |
| H1/H2 headings | querySelectorAll('h1,h2').length | ≥ 1 |
| Navigation bar | querySelector('.nav-bar, nav, [class*="nav"]') | Not null |
| Plotly charts rendered | querySelectorAll('.js-plotly-plot, .plotly-graph-div').length | ≥ 1 |
| No broken images | [...querySelectorAll('img')].every(i => i.complete && i.naturalWidth > 0) | True |
| No empty script errors | Check console | Zero JS exceptions |
window.scrollTo(0, document.body.scrollHeight))When a report visualizes generated sweep data (speed × heading × angle, cases × phases, benchmarks, etc.), do not stop at DOM rendering. Cross-check the rendered controls and embedded/chart data against the source artifact (.csv, .json, manifest, or generator summary):
When a generator emits an HTML/PDF report plus CSV/JSON/provenance/manifest artifacts, verify the bundle before summarizing success:
html.parser for title, headings, expected section labels, schematic captions, and provenance/caveat text.--module orcawave-qtf| Check | Test | Pass Condition |
|---|---|---|
| QTF section exists | document.getElementById('qtf-analysis') | Not null |
| QTF heading | querySelector('#qtf-analysis h2')?.textContent | Contains "QTF Analysis" |
| Figure cards | querySelectorAll('#qtf-analysis .qtf-figure').length | ≥ 1 |
| Figure titles (h3) | querySelectorAll('#qtf-analysis h3').length | Matches figure count |
| Reference images | querySelectorAll('#qtf-analysis img[src^="data:image"]').length | ≥ 1 (if screenshots available) |
| Plotly in QTF section | querySelectorAll('#qtf-analysis .plotly-graph-div').length | ≥ 1 |
| OrcaWave label | Text search for "OrcaWave Output" | Present |
| Reference label | Text search for "Reference (WAMIT paper)" | Present |
Scroll into #qtf-analysis and take a screenshot to capture side-by-side layout.
--module benchmark-correlation| Check | Test | Pass Condition |
|---|---|---|
| Consensus table | querySelector('table') | Not null |
| DOF sections | querySelectorAll('[id^="dof-"]').length | ≥ 1 |
| Correlation values | Text contains r= | ≥ 1 match |
| Pass/Fail badges | Elements with green/red color styling | Present |
Produce a structured report:
HTML Report Verification — <filename>
======================================
URL : http://localhost:8974/...
Module checks: orcawave-qtf
Layer 1 (Load) : PASS
Layer 2 (DOM) : PASS [3 h2, 12 Plotly divs, 0 broken images]
Layer 3 (Visual) : PASS [screenshots attached]
Layer 4 (Module: QTF) : PASS [2 figures, 2 reference images]
OVERALL: ✅ PASS
If any layer fails, list the specific failing check and what was found vs expected.
references/parameter-sweep-report-review.md for the data-contract + interaction checklist for generated engineering parameter-sweep chart reports.references/engineering-report-artifact-verification.md for manifest/HTML/PDF/CSV/JSON verification when an engineering report generator emits a multi-artifact bundle.references/client-review-export-closeout.md for locating an existing HTML report with tolerant spelling/condition-token search, producing PDF/DOCX client-review copies, verifying URLs/content, and closing out issue-scoped follow-up artifacts.mcp__claude-in-chrome__tabs_context_mcp first to get a valid tab IDmcp__claude-in-chrome__tabs_create_mcp for a fresh tab (don't reuse report tab)pkill -f "http.server 8974" (Linux/macOS) or taskkill (Windows)uv run python -m http.server (not python3)Add a new --module <name> block to Layer 4. The module check function receives
the tab ID and runs additional javascript_tool calls + screenshots tailored to
that report's specific sections.
When verifying, note (but do not fail on) these visual quality signals:
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.