google-docs-automation

Lightweight Google Docs integration with standalone OAuth authentication. No MCP server required.

Quality

64%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/google-docs-automation/SKILL.md

The canonical home for this skill is google-docs in sanjay3290/ai-skills

Quality

Content

65%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 lean, well-sectioned, and provides concrete commands with realistic examples, but it references script files absent from the bundle and offers no verification step around the destructive replace-text operation. Including the scripts and adding a verify step would raise both actionability and workflow clarity.

Suggestions

Ship the referenced `scripts/auth.py` and `scripts/docs.py` in the skill bundle (or remove the commands) — every documented operation currently fails because the scripts do not exist.

Add a validation step around destructive edits, e.g. "Run `get-text` first to confirm the target text exists, and again after `replace-text` to verify the change."

Trim the Token Management section to one or two lines (where tokens are stored and that they auto-refresh); the per-OS keyring enumeration is unnecessary detail.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven ("All operations via `scripts/docs.py`. Auto-authenticates on first use if not logged in."), but the per-OS keyring enumeration ("macOS: Keychain", "Windows Credential Locker", "Linux: Secret Service API") and the "Service name" line are details Claude does not need. Minor trimmable content keeps it below the lean 5 anchor.	4 / 5
Actionability	Commands are concrete with realistic arguments (real document ID, full URL, quoted content strings), but every command depends on `scripts/auth.py` and `scripts/docs.py`, which are not present in the skill bundle, so the guidance is not fully executable as shipped. Not 3 because the command forms, arguments, and examples are otherwise precise and copy-paste shaped.	4 / 5
Workflow Clarity	Single-command operations are unambiguous and setup/auth is clearly sequenced, but `replace-text` destructively modifies user documents and no validation step is given (e.g., `get-text` to verify before/after). Per the guidelines, destructive operations without validation cap workflow clarity at 3. Not 2 because the command set and first-time setup flow are clearly laid out.	3 / 5
Progressive Disclosure	Sections are well-organized and the skill is appropriately self-contained for its size, but the only external references (`scripts/auth.py`, `scripts/docs.py`) point to files that do not exist in the bundle (no scripts/ directory), breaking navigation to the referenced material. This fits the 3 anchor (structure present, references not resolvable) rather than 4.	3 / 5
	Total	14 / 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 states a clear niche and auth model but names no concrete operations and omits any "Use when..." trigger guidance, capping completeness. Adding action verbs and a trigger clause would move it toward the strong examples.

Suggestions

Enumerate the concrete operations in the description, e.g. "Create, find, read, append, and edit text in Google Docs via a lightweight CLI."

Add an explicit trigger clause: "Use when the user asks to work with Google Docs, wants to create or edit shared documents, or mentions docs.google.com links."

Drop "standalone" and lead with user-facing capabilities rather than implementation details (OAuth, MCP) that don't aid trigger matching.

Dimension	Reasoning	Score
Specificity	"Google Docs integration" names the domain but lists no concrete actions (no create, find, append, or replace operations are mentioned), matching the anchor for minimal/generic actions. It is not 1 because the domain is explicitly stated, and not 3 because no concrete capability is enumerated.	2 / 5
Completeness	The "what" is reasonably clear ("Lightweight Google Docs integration with standalone OAuth authentication. No MCP server required."), but there is no "Use when..." trigger clause, so the "when" is entirely absent — capped at 3 per the guidelines. Not 4 because the when-clause is missing outright, not 2 because the what is domain-specific rather than vague.	3 / 5
Trigger Term Quality	"Google Docs" is a natural phrase users would say, but "standalone OAuth authentication" and "MCP server" skew technical and common variations like "document", "docs", or "edit" are missing. Some relevant keywords exist, but coverage of natural synonyms is incomplete.	3 / 5
Distinctiveness Conflict Risk	Google Docs is a clear, distinct niche unlikely to trigger for unrelated skills; only minor overlap risk with other Google/Drive-oriented skills exists. Not 5 because the absence of explicit trigger phrases weakens distinct routing compared to the 5-anchor examples.	4 / 5
	Total	12 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/google-docs-automation/SKILL.md
Commit: 64adc55

Reviewed: 9 minutes 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.