gog-docs

Google Docs operations through gog.

Quality

66%

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 ./.agents/skills/gog-docs/SKILL.md

Quality

Content

68%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 a well-organized, safety-conscious CLI wrapper: executable safe-start commands, explicit account/readonly/dry-run rules, and a complete command catalog with pointers to --help and machine-readable schema contracts instead of guessed syntax. Its main gaps are the absence of a write workflow with post-write validation and the inlining of the full command table in the main file.

Suggestions

Add a short write-workflow example with a validation step, e.g. 'find-range → update → cat (or structure) to verify the edit landed', creating a validate→fix→retry loop for destructive commands.

Move the 48-row command table to a references/ file (e.g. references/commands.md) and keep a curated subset of common commands inline in SKILL.md.

Show one concrete end-to-end example of a supported write using --dry-run first, so the dry-run checkpoint is demonstrated rather than only stated.

Dimension	Reasoning	Score
Conciseness	The body is lean: no explanation of what Google Docs is, a copy-paste safe-start block, and a dense one-line-per-command table. It earns a 4 rather than 5 because the 48-row command table substantially duplicates what 'gog docs --help' and 'gog schema docs' already provide on demand, so some tokens could be trimmed.	4 / 5
Actionability	The safe-start block gives fully executable bash commands ('gog auth list --check --json --no-input', 'gog schema docs --json', 'gog docs cat DOCUMENT_ID --json --wrap-untrusted') and the body directs to '--help' and 'gog schema docs <command> --json' rather than guessing syntax. It is not a 5 because no end-to-end example of an actual write (e.g. find-range → update) is shown — the common edit case has no copy-paste-ready invocation.	4 / 5
Workflow Clarity	A rough sequence exists (auth check → schema → readonly cat) with pre-write checkpoints ('--dry-run before supported writes', 'Confirm the exact account, object, and mutation before any write or delete'), but there is no post-write verification step or validate→fix→retry loop. Since the command set includes destructive operations (clear, delete, sed, write), the missing validation feedback loop caps workflow clarity at 3 per the rubric guidelines.	3 / 5
Progressive Disclosure	Structure is good: well-organized sections, a clearly signaled one-level reference ('Read ../gog/SKILL.md first for shared auth, output, safety, and live-write rules'), and on-demand detail via '--help' and 'gog schema docs --json' instead of inlining flags. It is not a 5 because the full command catalog is inlined in SKILL.md (arguably reference material for a separate file) and the '../gog/SKILL.md' path cannot be verified from within this skill's bundle.	4 / 5
	Total	15 / 20 Passed

Description

48%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 terse and names a distinct niche (Google Docs via the gog CLI), but it lists no concrete capabilities and has no 'Use when...' trigger clause, so a user or model matching on natural language has little to route on. It reads like a bare label rather than a routing description.

Suggestions

Add concrete actions to the description, e.g. 'Create, read, edit, format, and export Google Docs; manage tables, images, comments, and smart chips via the gog CLI.'

Append a trigger clause: 'Use when the user asks to read, edit, format, or export a Google Doc, or mentions Google Docs, gdoc, or document comments.'

Drop or de-emphasize the raw tool name 'gog' in favor of natural user vocabulary (Google Docs, Google document), keeping the tool name in the body.

Dimension	Reasoning	Score
Specificity	The description only says 'Google Docs operations through gog' — it names the domain (Google Docs) and the tool, but lists zero concrete actions (no create, edit, format, export, or comment operations). This matches the anchor 'Names the domain but actions are minimal or generic' ("Processes PDF files"); it cannot be a 3 because not even 1-2 concrete actions are stated.	2 / 5
Completeness	There is a clear 'what' (Google Docs operations via gog) but no 'when' — no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is clear and specific rather than vague.	3 / 5
Trigger Term Quality	'Google Docs' is a natural phrase users would say, but 'gog' is internal tool jargon and common variations are missing ("Google document", ".gdoc", "Docs", "edit a Google Doc"). This sits at the anchor 'Some relevant keywords but missing common variations or synonyms' ("Works with PDF files") — below 4 because keyword coverage is thin, above 2 because the key domain term is present and natural.	3 / 5
Distinctiveness Conflict Risk	Naming the specific service (Google Docs) and the specific tool (gog) carves out a clear niche with minimal conflict risk against generic document skills. Not a 5 because sibling gog skills (sheets, slides, drive) likely exist and, without any trigger phrases or action list, this terse description does not fully distinguish itself from them.	4 / 5
	Total	12 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: openclaw/gogcli
Path: .agents/skills/gog-docs/SKILL.md
Commit: 414e2ff

Reviewed: 3 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.