CtrlK
BlogDocsLog inGet started
Tessl Logo

irregular-excel-parsing

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

60

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/irregular-excel-parsing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The content is highly actionable with complete, executable pandas code and a clear step sequence, but it loses points for redundancy (a duplicated example function) and the absence of explicit validation feedback loops. Tightening the duplication and adding an error-recovery checkpoint would raise it.

Suggestions

Remove or de-duplicate the 'Complete Example Function' — either reference the Step 1-5 code or keep only one canonical implementation to save tokens and avoid divergence.

Add an explicit validate->fix->retry checkpoint, e.g. 'If no header pattern matches in the first N rows, inspect df_raw.head(20) and adjust patterns before retrying.'

Consider moving the full worked example into a references/ file linked from the body, so the SKILL.md overview stays lean while keeping detail one level deep.

DimensionReasoningScore

Conciseness

The body is mostly code and assumes competence, but the 'Complete Example Function' re-implements a second, divergent version of the header-finding logic already given in Steps 1-4 (different patterns, 15-row cap), which is redundant token spend. This matches anchor 2 ('Mostly efficient but includes some unnecessary explanation or could be tightened'); it does not reach anchor 3 because the duplication wastes context.

2 / 3

Actionability

It provides fully executable, copy-paste-ready pandas code with concrete patterns, column cleaning, duplicate-header handling, and validation logic, matching anchor 3 ('Fully executable code/commands; specific examples; copy-paste ready').

3 / 3

Workflow Clarity

Steps 1-5 are clearly sequenced and Step 5 includes validation/cleaning, but there is no explicit validate->fix->retry feedback loop (e.g. what to do when no header pattern matches beyond a silent fallback), matching anchor 2 ('sequence present but checkpoints missing or implicit'). It stops short of anchor 3, which requires explicit validation checkpoints and error-recovery loops.

2 / 3

Progressive Disclosure

The skill is a single self-contained file with clear sections (When to Use, When NOT to Use, Tips) and no nested references, but it exceeds the ~50-line simple-skill threshold and keeps the duplicated 'Complete Example Function' inline rather than splitting detail out, matching anchor 2 ('Some structure... content that should be separate is inline'). It is not anchor 1 because it is organized, not a monolithic wall of text.

2 / 3

Total

9

/

12

Passed

Description

72%

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 specific and distinct, clearly carving out a niche for problematic Excel structures, but it omits an explicit 'Use when...' trigger clause, which caps its completeness. Replacing the generic 'Handle' with concrete verbs and adding a when-trigger would lift it to top marks.

Suggestions

Add an explicit trigger clause, e.g. 'Use when pandas.read_excel() fails because headers are missing, merged, or not in row 0.'

Replace the generic verb 'Handle' with concrete actions such as 'Detect the header row, clean merged-cell headers, and extract data by index.'

Include file-extension variants (e.g. '.xlsx', '.xls') among the trigger terms for broader natural-language matching.

DimensionReasoningScore

Specificity

The description names a concrete domain ('Excel files with irregular headers, merged cells, and unknown header row positions') and a technique ('pattern-matching and index-based extraction'), but the sole action verb is the generic 'Handle' rather than multiple distinct concrete actions, matching anchor 2 ('Names domain and some actions, but not comprehensive'). It falls short of anchor 3, which expects several specific verbs (e.g. 'Extract... fill... merge').

2 / 3

Completeness

It clearly answers 'what' (handle irregular Excel structures via pattern-matching/index-based extraction) but provides no explicit 'Use when...' trigger clause, so 'when' is only implied. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 2; it cannot reach 3 without an explicit when-trigger.

2 / 3

Trigger Term Quality

It surfaces natural terms a user would actually say — 'Excel files', 'irregular headers', 'merged cells', 'header row positions' — giving good coverage of the problem vocabulary, matching anchor 3. It is not reduced to 2 because, although file extensions like .xlsx/.xls are absent, the core trigger terms are specific and natural rather than generic jargon.

3 / 3

Distinctiveness Conflict Risk

The niche ('irregular headers, merged cells, and unknown header row positions') is specific and distinct from standard Excel skills, making unintended triggering unlikely, matching anchor 3 ('Clear niche with distinct triggers; unlikely to conflict').

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
Reviewed

Table of Contents

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.