Excel Data Quality Check

Excel/CSV data quality diagnosis & interactive charts — 20+ scan modules, 6-dimension scoring, agent-powered semantic analysis, and any ECharts visualization...

Security Scan

The skill's code, instructions, and requirements are coherent with its stated purpose (local Excel/CSV profiling and chart rendering); nothing in the package or SKILL.md requires unrelated credentials or external services by default.

Purpose & Capability

The name/description (data profiling, scoring, and ECharts rendering) matches the included tools (parser, profiler, scanner, chart_renderer). Node runtime and npm dependencies (xlsx, echarts, sharp) are reasonable and documented in README/SKILL.md. No unrelated credentials, binaries, or config paths are requested.

Instruction Scope

Runtime instructions stay within the declared purpose (present menu on file detection, run local CLI tools to profile/render) but contain some user-experience choices to be aware of: SKILL.md instructs the agent to 'activate whenever the user uploads/mentions' a supported file and to 'present the skill menu immediately', and chart.md Step 2 mandates rendering planned charts immediately ('do NOT ask for confirmation first'). Those are behavioral decisions (privacy/UX) rather than technical inconsistencies, but they could surprise users who expect the agent to wait for an explicit request before operating on uploaded files.

Install Mechanism

No automated install spec in the registry; the SKILL.md instructs a one-time manual 'npm install' to fetch well-known packages (xlsx, echarts, sharp). This is proportionate given the Node code included. There are no downloads from unknown URLs or extract operations in the manifest.

Credentials

The skill declares no required environment variables, no primary credential, and no config paths. The only external delegation (advanced charts) optionally calls an external ChartGen skill that requires its own API key; that is documented and optional.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or system-wide settings in the provided files. It does include instructions to write generated PNG files locally (chart tool) which is expected for chart rendering.

Assessment

This skill appears to be what it claims: a local Excel/CSV profiler and ECharts renderer. Before installing or running it: (1) review the repository and package.json (if present) before running npm install to ensure there are no unexpected install scripts; (2) be aware the skill's instructions tell the agent to present itself automatically when a supported file is uploaded/mentioned and (per chart instructions) to render charts immediately once planned — if you prefer an explicit confirmation step, adjust the skill or avoid using the automatic trigger; (3) advanced/dashboard features delegate to a ChartGen skill which requires an API key and external service — that delegation is optional and only used if you enable/install ChartGen; (4) all processing appears local (no hidden network calls) based on the provided files, but if you have strict data-exfiltration policies, run the tools in an isolated environment or review any omitted files (utils, remaining scanner/scorer code) before use.

Excel Data Helper — Data Quality Diagnosis & Chart Skill

Local Excel/CSV data profiling, quality scanning (20+ modules, 6-dimension scoring, LLM semantic analysis), and chart generation. International locale support: CJK, European, Middle Eastern, Americas.

Supported files: .csv .tsv .xlsx .xls

---

Trigger & Menu

When a supported file is detected, do not auto-process — present this menu first (adapt to the user's language):

📊 Excel Data Helper — Hi, I noticed you shared a data file: <filename>

#	Action	Description
1	Quality Check	Overview, scan, scoring
2	Chart	Any ECharts type: bar, line, pie, scatter, radar, heatmap…
3	Advanced Chart	Dashboard, Gantt, PPT, diagrams
0	Skip	Do nothing for now

Reply 0–3, or describe what you need.

---

Routing & Context

Match user intent and route to the corresponding sub-skill:

• IF user replies 1, or intent is overview / quality check / diagnose / score / problems → follow references/quality-check.md

• IF user replies 2, or intent is chart / plot / visualize / graph → follow references/chart.md

• IF user replies 3, or intent is dashboard / Gantt / PPT / diagram / complex layout → follow references/advanced-chart.md

• IF user replies 0, or intent is skip / later / not now → do nothing, reply: "Got it — file noted. Just let me know when you're ready."

• IF intent is ambiguous or unrelated → ask to clarify, never guess.

Context:

• Short replies (number, "yes", "ok") always refer to the most recent menu or question.
• After Skip (0), context resets — ignore the file unless user re-references it.
• Multiple files — each needs its own explicit choice.

---

Setup

Before first use, install dependencies (one-time):

cd <skill_directory>
npm install

This installs xlsx (SheetJS), echarts, and sharp. All analysis and chart rendering runs locally.

---

Rules

• Respond in the user's language.
• Never auto-process a file — wait for explicit choice.
• Parse tool JSON output; present results in clear, readable format — never expose raw JSON.
• Use absolute file paths from tool output directly for follow-up operations.
• Always include "Excel Data Helper" in the menu header.