メニュー
Compute summary statistics for a CSV and write a JSON + markdown report. Use when the user asks to analyze, summarize, profile, or compute metrics for a CSV / tabular dataset.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Test or debug a Claude Code skill/plugin under Claude Cowork's runtime — sandboxed agent, default-deny egress, the can_use_tool permission/question protocol — using the cowork-harness CLI. Use when validating or regression-testing a skill, authoring or debugging a scenario YAML (prompt + scripted answers + assert:), choosing a fidelity tier, scripting AskUserQuestion / tool-permission answers, or asserting artifacts, egress, or sub-agent dispatch. Especially when a harness run no-ops an assertion, fails on an unanswered gate, false-greens, a steered answer never reaches the model, or a web_fetch is unexpectedly denied or gated. Also when iterating or hardening a skill across fixes, or grounding a skill's self-critique against its own run evidence — including a document-analysis skill (cap table, deck, financial model, transcript) that needs an uploaded file attached to be critiqued at all. NOT for generic unit testing (pytest/vitest of your own scripts) or non-Cowork CI. Covers the skill / run / chat / record
Live-lane probe — dispatches one sub-agent that must research with the WebSearch tool.
Live-lane probe — reads an attached uploaded file with the Read tool and quotes its marker line.
Internal harness probe for resume-continuity. Use when asked to run the resume-continuity probe, to load the probe skill, or to retrieve the vault passphrase.
fixture skill A — has a candidate source under scripts/
fixture skill B — sibling of skill-a, must be excluded when the target is skill-a directly
| name | csv-metrics |
| description | Compute summary statistics for a CSV and write a JSON + markdown report. Use when the user asks to analyze, summarize, profile, or compute metrics for a CSV / tabular dataset. |
Profiles a CSV and writes two deliverables: a structured metrics.json and a
human-readable summary.md. The work is done by a bundled producer script
(scripts/metrics.py) — you run it, you don't reimplement it.
The user has a CSV (in uploads/ or a connected project folder) and wants
per-column statistics or a metrics report.
Locate the CSV. Default for this example: uploads/sales.csv.
Run the bundled producer, passing the CSV and the output directory. The
script lives under this skill's scripts/ folder, reachable via
${CLAUDE_PLUGIN_ROOT}:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/csv-metrics/scripts/metrics.py" uploads/sales.csv outputs
It writes outputs/metrics.json and outputs/summary.md and prints a
one-line summary.
Read outputs/summary.md, then reply with a single line that includes the
row count and the path outputs/metrics.json.
pip install, no
network. That is deliberate: under Cowork the agent runs with default-deny
egress and no pypi access, so a skill's producer must be self-contained.outputs/ as write-once for the deliverable: don't delete or rewrite
the files after the producer emits them.