irregular-excel-parsing

Handle Excel files with irregular headers, merged cells, and unknown header row positions using pattern-matching and index-based extraction.

Quality

70%

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/irregular-excel-parsing/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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

The body delivers fully executable, copy-paste-ready guidance in a clear five-step workflow with validation. Its main weakness is conciseness: the 'Complete Example Function' repeats the step code, and there is no explicit feedback loop for header-detection failure.

Suggestions

Remove the duplicated 'Complete Example Function' or replace the per-step snippets with a single canonical function, keeping only the explanatory steps that add new detail.

Add an explicit error-recovery checkpoint after Step 2, e.g. 'If find_header_row returns 0 or an implausible row, inspect df_raw.head(20) and broaden the patterns.'

Consolidate the regex pattern lists (defined twice, slightly differently) into one shared definition to avoid drift between the step and the complete example.

Dimension	Reasoning	Score
Conciseness	Mostly efficient executable code with no over-explanation of basic concepts, but the 'Complete Example Function' duplicates Steps 1-4, adding padding that could be trimmed.	3 / 5
Actionability	Fully executable, copy-paste-ready Python throughout, with a complete end-to-end parse function covering the common case and clearly adjustable patterns.	5 / 5
Workflow Clarity	Clear five-step sequence with validation in Step 5 (dropna, critical-column notna checks), but no explicit error-recovery feedback loop for when header detection misfires.	4 / 5
Progressive Disclosure	Well-organized sections (steps, complete example, when to use/not use, tips) with no external bundle files; minor gap is the inline duplication of the full example rather than splitting it out.	4 / 5
	Total	16 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 clearly conveys a specific niche and methods, but lacks any explicit 'when to use' trigger guidance, which caps completeness. Trigger-term coverage is good but misses common synonyms and the .xlsx extension.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when pandas.read_excel() fails due to merged cells, headers not in row 0, or unknown header row positions.'

Include the .xlsx file extension and the synonym 'spreadsheets' to broaden natural trigger-term coverage.

Tighten the action list toward distinct functional verbs (detect, extract, clean) rather than only naming scenarios handled.

Dimension	Reasoning	Score
Specificity	Enumerates several concrete capabilities (irregular headers, merged cells, unknown header row positions) and concrete methods (pattern-matching, index-based extraction), with only minor gaps in distinct-action coverage.	4 / 5
Completeness	The 'what' is clear (handle irregular Excel files via pattern-matching and index-based extraction) but there is no 'Use when...' trigger clause, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('Excel files', 'headers', 'merged cells', 'header row') but omits synonyms and the .xlsx extension, stopping short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Targets a distinct niche (irregular/merged-cell Excel parsing) unlikely to conflict with generic Excel skills, though the absence of explicit trigger phrases leaves minor overlap risk.	4 / 5
	Total	15 / 20 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/irregular-excel-parsing/SKILL.md
Commit: 3827781

Reviewed: 13 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.