excel-debug-extraction

Iteratively debug Excel structure with exploratory scripts before writing extraction logic

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/excel-debug-extraction/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, code-heavy workflow with copy-paste-ready openpyxl snippets and a clear five-step sequence. It loses points for inlining the debug scripts instead of bundling them and for omitting an explicit verification loop on the final extraction output.

Suggestions

Move debug_structure.py / debug_columns.py / debug_rows.py into a scripts/ bundle and reference them from the body to improve progressive disclosure.

Add an explicit validation checkpoint after Step 5, e.g. assert the extracted DataFrame row count and a sample value against the debugged row patterns before finishing.

Trim the repeated "Before writing extraction logic..." preamble from each step header to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable code, but recurring intro lines ("Before writing extraction logic, create a debug script to...") and some commentary Claude could infer (e.g. explaining what row patterns are) could be tightened.	2 / 3
Actionability	Each step ships complete, runnable openpyxl code with concrete imports and real API calls (load_workbook, iter_rows, iter_cols, cell access) — copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced and Step 4 ("Document Findings") acts as a checkpoint, but there is no explicit validate-then-retry feedback loop on the extraction output (e.g. verifying df.head() matches the debugged structure), leaving checkpoints implicit.	2 / 3
Progressive Disclosure	The single file is well-sectioned, but the four full debug scripts are inlined in the body rather than split into a scripts/ bundle, fitting the anchor where content that should be separate is inline.	2 / 3
	Total	9 / 12 Passed

Description

57%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise and scoped to a clear Excel niche, but it reads more as a single-sentence summary than a trigger-rich description. It lacks an explicit "Use when..." clause and broader natural keywords, which limit completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when parsing poorly-structured Excel files, working with unfamiliar .xlsx workbooks, or when initial spreadsheet parsing fails."

Broaden trigger terms to include user-natural phrasings like "spreadsheet", ".xlsx", "workbook", and "parse".

Expand the capability list slightly (e.g. map headers, classify row patterns) to lift specificity from a two-verb summary to multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Names the Excel domain and two concrete actions ("debug Excel structure" and "writing extraction logic"), but the action set is not comprehensive — it stops at two verbs rather than listing the full range of capabilities.	2 / 3
Completeness	The "what" is stated (debug structure, write extraction logic), but the "when" is only implied by the phrase "before writing extraction logic"; there is no explicit "Use when..." trigger clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	"Excel" and "extraction" are relevant keywords, but common variations a user would say ("spreadsheet", ".xlsx", "workbook", "parse") are missing.	2 / 3
Distinctiveness Conflict Risk	The Excel-scoped, debug-first framing carves a clear niche with distinct triggers that are unlikely to fire for PDF, CSV, or general data skills.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/excel-debug-extraction/SKILL.md
Commit: c5a9c4b

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.