meta-spreadsheet-insight

Turn an Excel workbook into business insight: structured read → trend/anomaly summary → write back to a new 'Insights' sheet → persist KPIs to memory.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./src/opensquilla/skills/exp/meta-spreadsheet-insight/SKILL.md

Quality

Content

72%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 is exceptionally concise and well-structured for a meta-skill, but its actionable detail and workflow robustness are weak: the fallback is high-level, and the destructive append/persist pipeline lacks any validation checkpoint. Per-rubric caps correctly bound actionability and workflow clarity at 3.

Suggestions

Add concrete arguments to the fallback (e.g. the Insights sheet name and the memory path 'memory/spreadsheet-kpi.md') so the LLM-driven path is as executable as the declarative composition.

Insert an explicit validation/verification step before the writeback (e.g. confirm the read returned data, and verify the appended sheet did not corrupt the workbook) to lift workflow clarity above the destructive-operation cap of 3.

Add a brief failure-recovery note (what to do if the read is empty or the summarize output is too long) to establish a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is a lean three-line overview plus a one-line fallback with no padding, no concept explanations, and no over-claiming; every token earns its place and it assumes Claude's competence, matching the score-5 'lean and efficient' anchor.	5 / 5
Actionability	The fallback gives an ordered list of named operations ('xlsx read, summarize, xlsx append, then memory_save') which is more structured than a single vague hint, but it omits concrete arguments, sheet names, and parameters, so it sits between the 'minimal concrete guidance' and 'mostly executable' anchors.	3 / 5
Workflow Clarity	A clearly sequenced dependency graph exists in the frontmatter composition (read -> analyze -> writeback/memorize) and is echoed in the fallback, but there is no validation/verification checkpoint before the destructive sheet-append and memory-write; per the rubric this caps workflow clarity at 3 for a batch/destructive operation.	3 / 5
Progressive Disclosure	The body is well under 50 lines, needs no external references (no bundle files exist), and is organized into a concise overview plus a clearly labeled Fallback section, satisfying the simple-skill exception for a top progressive_disclosure score.	5 / 5
	Total	16 / 20 Passed

Description

58%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 communicates a clear, specific four-step pipeline (read, analyze, writeback, persist) but omits explicit 'Use when' trigger guidance and lacks natural synonym/file-extension terms. It is specific and distinctive yet incomplete on the 'when' dimension.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. 'Use when the user asks to analyze an Excel/spreadsheet file for trends, anomalies, or business insights').

Include common natural terms and synonyms users would say, plus the .xlsx file extension, to improve trigger term coverage.

Ground the actions in concrete terms (e.g. name the xlsx and summarize operations) to push specificity from a strong 4 toward 5.

Dimension	Reasoning	Score
Specificity	The description lays out four concrete sequential actions — 'structured read', 'trend/anomaly summary', 'write back to a new Insights sheet', 'persist KPIs to memory' — giving comprehensive pipeline coverage, though the actions are framed at a slightly abstract level rather than as named tool operations, placing it just below the score-5 anchor.	4 / 5
Completeness	The 'what' is clearly and explicitly stated via the four-step pipeline, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines a missing 'when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant terms like 'Excel workbook', 'spreadsheet', 'KPIs', and 'trend/anomaly', but omits common natural variations users would say (e.g. 'analyze my Excel') and file extensions like .xlsx, so it matches the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The combination of trend/anomaly summarization, writing back to a new Insights sheet, and persisting KPIs to memory carves out a distinct niche with only minor overlap risk against a generic xlsx or summarize skill, fitting the 'mostly distinct' anchor.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/exp/meta-spreadsheet-insight/SKILL.md
Commit: 94ac35e

Reviewed: 4 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.