CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gog-docs

Google Docs through gog. Use for Google Docs text, formatting, tabs, comments, and document exports.

Quality

83%

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

90%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 lean, well-structured CLI-wrapper skill: copy-paste safe-start commands, validation-first sequencing with pre-write safety checkpoints (--readonly, --dry-run, explicit confirmation), a complete one-line-per-command index, and clean delegation of flags and contracts to --help and machine-readable schema output. The only gaps are the absence of a post-write verification loop and a command table that could arguably be split into a separate reference file.

DimensionReasoningScore

Conciseness

The body is lean throughout: a two-line opening ("Use `gog` for Google Docs operations. Read `../gog/SKILL.md` first for shared auth, output, safety, and live-write rules"), three bare safe-start commands, one-line bullets, one line per command, and no explanations of concepts Claude already knows. Every table row delivers command vocabulary Claude cannot obtain without invoking help, so every token earns its place.

5 / 5

Actionability

Fully executable guidance: copy-paste ready commands with flags ("gog --readonly --account user@example.com docs cat DOCUMENT_ID --json --wrap-untrusted"), per-command flag hints (--first, --at-end, --values-json), and explicit syntax lookup ("Run `gog docs <command> --help`... `gog schema docs <command> --json`... Do not guess command syntax"). This matches the copy-paste-ready, common-cases-covered anchor.

5 / 5

Workflow Clarity

The Safe start is a validation-first sequence (auth check → schema → readonly read) with explicit pre-write checkpoints ("--dry-run before supported writes", "Confirm the exact account, object, and mutation before any write or delete"), so the destructive-operation cap of 3 does not apply. However, there is no post-write verification step or error-recovery feedback loop, which keeps it below anchor 5.

4 / 5

Progressive Disclosure

Good structure with clean sections (Safe start, Commands) and one-level-deep delegation of per-command detail to runtime lookups (--help, gog schema --json), appropriate for a CLI wrapper. Minor gaps: the 49-row command table inlines per-command descriptions that could live in a reference file, and the sole file reference (../gog/SKILL.md) points outside the bundle and cannot be verified within it, so it falls short of anchor 5.

4 / 5

Total

18

/

20

Passed

Description

70%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 claims a clear niche (Google Docs via gog) with an explicit 'Use for' trigger clause covering text, formatting, tabs, comments, and exports. Its main weakness is the 'what': capabilities are named as topic nouns rather than concrete actions, underselling the create/edit/delete/insert surface the body actually supports.

Suggestions

Lead with concrete verbs instead of topic nouns, e.g. "Create, edit, format, and export Google Docs; manage text, tables, images, tabs, comments, and suggestions via the gog CLI" so the 'what' is explicit and coverage gaps shrink.

Add natural synonyms and file formats users actually say — "gdoc", ".docx", ".pdf exports", "Google Workspace documents" — to broaden trigger-term coverage.

State the most common operations (create, edit/find-replace, export) explicitly in the first sentence so both 'what' and 'when' are fully concrete.

DimensionReasoningScore

Specificity

The description lists capability areas — "text, formatting, tabs, comments, and document exports" — but as topic nouns rather than concrete actions, and coverage gaps are major (create, edit, delete, tables, images are all unstated despite ~49 commands in the body). It names the domain plus several areas, above anchor 3's '1-2 concrete actions' but with more than the 'minor gaps' anchor 4 allows.

3 / 5

Completeness

Both parts are present: "Google Docs through gog" (what) and an explicit "Use for..." clause enumerating five trigger areas (when). The 'what' is thin — it never states the operations (create/edit/manage) — so it falls short of anchor 5's 'clearly and explicitly answers both', while the explicit trigger clause keeps it above the missing-'when' cap of 3.

4 / 5

Trigger Term Quality

"Google Docs" is the primary natural term and "comments", "tabs", "formatting", and "document exports" are phrases users would naturally say. A few natural synonyms and extensions are missing ("gdoc", ".docx", "Google Workspace"), so it matches anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Google Docs through gog" carves a clear, tool-scoped niche unlikely to trigger for unrelated skills. Minor overlap risk remains with closely related document/Drive/export skills via the generic phrases "document exports" and "text, formatting", matching anchor 4 rather than anchor 5's minimal conflict risk.

4 / 5

Total

15

/

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

Path

.agents/skills/gog-docs/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.