SenseNova Excel Data Analysis Workflow
Six-step Excel pipeline: count, gate, clean, filter, aggregate, export
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 4c54132
Task: on a real generated .xlsx (2 sheets, 12,000 rows, 400 missing values in '得分', 300 contaminated values in '部门', column named '是否通 过' with a space) count rows per sheet, clean data, calculate the proportion passed by department, and export the result. Baseline run without skill crashed with KeyError: 'Column not found: 是否通过' — exactly on the trap warned about in the skill's Key rules section ('Column names may contain spaces'); after manual fix, it ran but exported a file with 400 uncleansed NaN. Skill run exported 0 NaN and correctly hit the 10k-gate (12,003 rows → 10k–100k band → Parquet cache). Fair counter-argument: at this size, optimization turned out to be pessimization — 5.8 s and peak 57.4 MB vs. 2.9 s and 20.6 MB for naive pandas, meaning the Parquet roundtrip at the lower bound of its own band only hinders. Main reason for setup verdict: the skill is written for the SenseNova host sandbox and contains non-portable paths (/mnt/data/result.xlsx, fonts /mnt/afs_agents/SimHei.ttf, links like 'sandbox:'), and the ≥100k rows branch requires the neighboring skill sn-da-large-file-analysis, which is NOT installed by the installation command — it needs to be copied separately. Stage 0 clean: body (288 lines) and 40 capability files read, no network or exfiltration.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 3/5
- Triggers reliably 4/5
- Output vs. baseline 7/10
- Docs & honesty 3/5
What SenseNova Excel Data Analysis Workflow does
Orchestrates multi-sheet Excel analysis as six steps — row counting without full load, a large-file Parquet gate, schema inspection, cleaning, filtering and export — backed by 40 capability sub-skills. Triggers on requests to analyze, clean, pivot, chart or export .xlsx/.xls/.csv data.
How to install SenseNova Excel Data Analysis Workflow
git clone https://github.com/OpenSenseNova/SenseNova-Skills.git
mkdir -p ~/.claude/skills
cp -r SenseNova-Skills/skills/sn-da-excel-workflow ~/.claude/skills/sn-da-excel-workflow
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger SenseNova Excel Data Analysis Workflow
-
/sn-da-excel-workflowSix-step Excel pipeline: count, gate, clean, filter, aggregate, export
It also activates on plain-language prompts like these:
-
Clean this messy Excel file and export the pass rate by department -
Count rows across both sheets before we process this huge spreadsheet -
Filter and aggregate this xlsx data without loading the whole file into memory
Frequently asked questions
- Is the SenseNova Excel Data Analysis Workflow skill free?
- Yes. The skill itself is free from OpenSenseNova/SenseNova-Skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does SenseNova Excel Data Analysis Workflow work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Task: on a real generated .xlsx (2 sheets, 12,000 rows, 400 missing values in '得分', 300 contaminated values in '部门', column named '是否通 过' with a space) count rows per sheet, clean data, calculate the proportion passed by department, and export the result. Baseline run without skill crashed with KeyError: 'Column not found: 是否通过' — exactly on the trap warned about in the skill's Key rules section ('Column names may contain spaces'); after manual fix, it ran but exported a file with 400 uncleansed NaN. Skill run exported 0 NaN and correctly hit the 10k-gate (12,003 rows → 10k–100k band → Parquet cache). Fair counter-argument: at this size, optimization turned out to be pessimization — 5.8 s and peak 57.4 MB vs. 2.9 s and 20.6 MB for naive pandas, meaning the Parquet roundtrip at the lower bound of its own band only hinders. Main reason for setup verdict: the skill is written for the SenseNova host sandbox and contains non-portable paths (/mnt/data/result.xlsx, fonts /mnt/afs_agents/SimHei.ttf, links like 'sandbox:'), and the ≥100k rows branch requires the neighboring skill sn-da-large-file-analysis, which is NOT installed by the installation command — it needs to be copied separately. Stage 0 clean: body (288 lines) and 40 capability files read, no network or exfiltration.
- What is the SenseNova Excel Data Analysis Workflow SkillProof Score?
- 6.8/10 — installs cleanly 3/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 3/5.
- How do I install SenseNova Excel Data Analysis Workflow?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use SenseNova Excel Data Analysis Workflow with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.