CtrlK
BlogDocsLog inGet started
Tessl Logo

gog-sheets

Google Sheets operations through gog.

57

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/gog-sheets/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%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 an exemplary lean CLI reference: executable safe-start commands with safety guardrails, a compact one-line-per-command table, and disciplined deferral of detail to --help and machine-readable schema output. The only gap is the absence of a post-write validation/feedback step for its destructive and batch commands.

DimensionReasoningScore

Conciseness

Every line is either an executable command, a one-line command purpose, or a safety rule — there is zero explanation of what Google Sheets is or how CLIs work. The file assumes Claude's competence throughout ("Do not guess command syntax" and pointers to --help instead of inline flag documentation), matching anchor 5 ('Lean and efficient; every token earns its place').

5 / 5

Actionability

The 'Safe start' section gives three copy-paste-ready bash commands with real flags, and each bullet is a concrete directive (--account, --readonly, --dry-run, --json --wrap-untrusted). The command table plus "Run gog sheets <command> --help ... and gog schema sheets <command> --json" gives fully executable, machine-verifiable guidance, matching anchor 5.

5 / 5

Workflow Clarity

This is a command-reference skill rather than a multi-step workflow, and it does encode a safe operating sequence: inspect with --readonly first, --dry-run before supported writes, and "Confirm the exact account, object, and mutation before any write or delete" — real checkpoints for the destructive commands it lists (delete-tab, clear, batch-request). It falls short of anchor 5 because there is no post-write verification step or explicit validate-and-retry loop for batch operations, matching anchor 4 ('most checkpoints present; minor validation gaps').

4 / 5

Progressive Disclosure

No bundle files exist; the body is a lean overview that appropriately defers all per-command detail to one level of on-demand material (the clearly signaled sibling `../gog/SKILL.md` for shared rules, `--help` for flags, and `gog schema ... --json` for contracts), with well-organized 'Safe start' and 'Commands' sections. This matches anchor 5 ('Clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation').

5 / 5

Total

19

/

20

Passed

Description

40%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 names a specific domain and tool but stops there: it says only "operations" with no concrete capabilities and no 'when to use' trigger clause. It is functional but well below the quality of the reference good examples, which enumerate actions and explicit use-when phrases.

Suggestions

Enumerate concrete capabilities, e.g. "Read and update ranges, format cells, manage tabs, filters, and charts in Google Sheets via the gog CLI."

Add an explicit trigger clause, e.g. "Use when the user mentions Google Sheets, spreadsheets, tabs, or cell ranges."

Include natural synonyms and file extensions users would say (spreadsheet, .xlsx, tabs, formulas) so the skill triggers on phrasing that never says "Google Sheets".

DimensionReasoningScore

Specificity

The description states "Google Sheets operations through gog", which names the domain clearly but the only action verb is the generic word "operations" — no concrete actions like read, update, format, or create are listed. This matches anchor 2 ('Names the domain but actions are minimal or generic', e.g. 'Processes PDF files'); it is above anchor 1 because the domain is specific rather than abstract, and below anchor 3 because no concrete operation is named.

2 / 5

Completeness

The 'what' is present but vague ("operations through gog") and there is no 'when' clause at all — no 'Use when...' or equivalent trigger guidance, which the guidelines cap at 3. This matches anchor 2 ('Has a vague what and no when'); it cannot be 3 because the what itself is generic, and cannot be 1 because the domain is clearly stated.

2 / 5

Trigger Term Quality

"Google Sheets" is a strong natural phrase users would actually say, but the description omits common synonyms and variations — "spreadsheet", "spreadsheets", "cells", "formulas", or extensions like .xlsx — matching anchor 3 ('Some relevant keywords but missing common variations or synonyms'). Not anchor 4, since keyword coverage is one term plus the internal tool name 'gog', which users would not say.

3 / 5

Distinctiveness Conflict Risk

"Google Sheets operations through gog" carves a clear niche (Sheets via the gog CLI) that is unlikely to trigger for unrelated skills, with only minor overlap risk against closely related skills (generic spreadsheet/xlsx or Google Drive skills). Anchor 5 is not reached because the generic word 'operations' blurs the boundary slightly with sibling gog skills; anchor 3 is too harsh since both the platform and the tool are named.

4 / 5

Total

11

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
openclaw/gogcli
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.