excel-outlier-detection-and-highlighting

识别 Excel 中的超限数值与错误单元格并进行高亮标注。

Quality

59%

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 ./skills/sn-da-excel-workflow/capability/excel-cell-coloring/outlier-coloring/SKILL.md

Quality

Content

65%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 content is concrete and mostly executable with good token efficiency, but it lacks validation/verification checkpoints in a batch-and-save workflow, which caps workflow clarity. Inlining all code with no detail-file references keeps progressive disclosure mid-range.

Suggestions

Add explicit validation checkpoints after detection and before saving (e.g., assert exceed_rows/error_cells were populated, verify the saved workbook reopens and highlights are present) to lift workflow clarity above the batch-operation cap.

Define or note the required setup context (how df and wb are obtained, required imports) so the code is truly copy-paste ready.

Move the summary-report generation (Step4) and error-cell scanning (Step2) into reference files with clearly signaled one-level links from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is code-focused with only brief, mostly useful comments and no padding about what Excel/Pandas is, fitting 'efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean 5.	4 / 5
Actionability	All four steps contain real, executable Python using re, pandas, and openpyxl, but the snippets reference undefined context (df, wb) and hardcode assumptions (Sheet3, column indices), leaving minor gaps that prevent a 5.	4 / 5
Workflow Clarity	Step1 through Step4 form a clear sequence, but this batch/destructive workflow (batch cell iteration, highlighting, file saving) has no validation or verification checkpoints; per the rubric this caps workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and all ~110 lines of code are inlined in SKILL.md with only Step headers for structure and a single pointer to a parent workflow; at this length, with content that could be split out and no clearly signaled one-level references, it fits the 'some structure, content that should be separate is inline' anchor.	3 / 5
	Total	14 / 20 Passed

Description

53%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 is specific and names concrete actions within a clear niche, but it omits any 'Use when' trigger guidance, which caps completeness and limits trigger-term quality. Adding an explicit usage trigger and file-extension synonyms would raise it into the 4 range.

Suggestions

Add an explicit 'Use when...' clause naming trigger situations (e.g., 'Use when auditing Excel heat-transfer reports for over-limit values or formula errors').

Include natural synonyms and file extensions users would say, such as .xlsx, 异常值/outlier, and 公式错误/formula errors.

Expand the action list slightly (e.g., 'generate a summary report of over-limit rows') to move specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the Excel domain plus two concrete actions ("识别超限数值与错误单元格" and "高亮标注"), matching the anchor for 1-2 concrete actions but not the comprehensive multi-action coverage of a 4.	3 / 5
Completeness	Has a clear 'what' (detect outliers/errors and highlight them) but no 'when' or 'Use when' trigger clause; per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant domain keywords (Excel, 超限数值, 错误单元格, 高亮) but lacks file extensions (.xlsx), 'Use when' phrasing, and common synonyms like 异常/outlier, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Describes a narrow, distinct capability (Excel outlier detection and error-cell highlighting) with minor overlap risk against sibling Excel sub-skills, but lacks explicit trigger phrases that would lock in a 5.	4 / 5
	Total	13 / 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: OpenSenseNova/SenseNova-Skills
Path: skills/sn-da-excel-workflow/capability/excel-cell-coloring/outlier-coloring/SKILL.md
Commit: 98a8bde

Reviewed: 1 day 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.