CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

google-sheets

Analyze and edit connected Google Sheets with range precision. Use when the user wants to create Google Sheets, find a spreadsheet, inspect tabs or ranges, search rows, plan formulas, create or repair charts, clean or restructure tables, write concise summaries, or make explicit cell-range updates.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured instruction-only skill: concrete routing and safety checklists, explicit read order, and exemplary progressive disclosure with a complete, verified reference bundle. The main costs are minor redundancy between the routing and final-answer sections and some meta-commentary that could be trimmed.

Suggestions

Merge the duplicated local-`.xlsx` / final-answer rule (stated in both Default Routing step 2 and the Final Answer Requirement section) into one place to recover a few tokens and remove ambiguity.

Trim 'Canonical Workflow Bias' to a single sentence — the multi-paragraph 'prefer a simple proven workflow' coaching largely restates judgment Claude already applies.

Clarify the Spreadsheets location instruction ('Use/create `ChatGPT` at My Drive root'), which reads as a mangled folder name and is ambiguous as written.

DimensionReasoningScore

Conciseness

The body is mostly lean directives with no concept over-explanation, but it repeats the local-`.xlsx`/final-answer rule in both "Default Routing" and "Final Answer Requirement", and "Canonical Workflow Bias" spends several lines on meta-coaching Claude already knows. Efficient with minor trimmable redundancy — anchor 4, not 3, since padding is a small fraction of the whole.

4 / 5

Actionability

Concrete, executable instruction guidance throughout: named routing branches, a connector checklist ("Resolve and record the spreadsheet id, target sheet names, and `sheetId` values", "use exact visible tab names from metadata, bounded ranges", "Do not guess `Sheet1`"), and a task-to-reference table. A few steps remain high-level ("Gather the required source material"), and write-shape specifics are delegated to references — anchor 4.

4 / 5

Workflow Clarity

Clear sequenced workflows with explicit checkpoints: per-route read order, "verify the output spreadsheet ID differs before writing", "Re-read target cells before writing", and verification against `references/reference-visual-quality.md` before stopping. Not 5 because validation detail for batch/destructive edits is delegated to reference files rather than stated as in-body feedback loops, and the three routing MUSTs are spread across sections.

4 / 5

Progressive Disclosure

The body is a genuine overview that splits all detail into one-level-deep, well-signaled references; all nine files named in the body exist in `references/`, and the Task-to-Reference map plus Required Read Order make navigation easy. Matches the anchor-5 structure exactly.

5 / 5

Total

17

/

20

Passed

Description

92%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.

A strong description: concrete action list, explicit third-person 'Use when...' trigger clause, and a clearly distinct Google Sheets niche. The only weakness is a few missing natural trigger terms around common spreadsheet operations.

DimensionReasoningScore

Specificity

Lists many concrete actions — "Analyze and edit", "create Google Sheets", "inspect tabs or ranges", "search rows", "plan formulas", "create or repair charts", "clean or restructure tables", "make explicit cell-range updates" — with comprehensive coverage of the spreadsheet domain, matching the anchor-5 example. Not 4 because there are no meaningful gaps in the action coverage.

5 / 5

Completeness

Explicitly answers both: what ("Analyze and edit connected Google Sheets with range precision") and when ("Use when the user wants to create Google Sheets, find a spreadsheet, ...") with concrete trigger phrases, mirroring the anchor-5 good example. Not 4 because the 'when' clause is already fully explicit.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "Google Sheets", "spreadsheet", "tabs", "ranges", "rows", "formulas", "charts", "tables" — all phrases users would naturally say. Not 5 because a few common user terms (e.g., sort/filter/format operations, sharing) are missing; not 3 because synonyms and the main product name are all present.

4 / 5

Distinctiveness Conflict Risk

Clear Google Sheets niche with distinct triggers (spreadsheet creation, tab/range inspection, chart repair) and minimal conflict risk with other skills. Not 4 because the domain and trigger terms are unambiguously spreadsheet-specific; the generic "write concise summaries" clause is a minor, non-conflicting inclusion.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/google-drive/skills/google-sheets/SKILL.md

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.