google-slides-automation

Lightweight Google Slides integration with standalone OAuth authentication. No MCP server required. Full read/write access.

Quality

68%

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-slides-automation/SKILL.md

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

Quality

Content

76%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-organized, and highly actionable, with concrete commands for every operation and clear output documentation. The main gaps are the absence of validation/verification steps for the destructive and batch operations, and the referenced scripts not being present in the bundle to confirm executability.

Suggestions

Add verification checkpoints for risky operations: after replace-text or batch-update, instruct to re-run get-text to confirm the change; before delete-slide, instruct to run get-metadata and confirm the slide ID.

Ship the referenced scripts (scripts/auth.py, scripts/slides.py) in the bundle, or note where they come from, so the documented commands are actually executable.

Consider moving the JSON output-format examples for find and get-metadata into a short reference file, keeping SKILL.md focused on the command catalog.

Dimension	Reasoning	Score
Conciseness	The body is pure operational content — setup commands, read/write command examples, a layout catalog, ID format notes, and token storage specifics — with no explanation of concepts Claude already knows. The only trimmable token is the opening line, which repeats the frontmatter description verbatim; that is not enough to drop below anchor 5 ('Lean and efficient; every token earns its place').	5 / 5
Actionability	Every operation has a copy-paste-ready command with realistic arguments and flags, and output formats are shown as concrete JSON — this approaches anchor 5. It scores 4 rather than 5 because the referenced files (scripts/auth.py, scripts/slides.py) are not present in the bundle, so the commands as shipped cannot actually be executed, and there are no examples of reading/validating output before or after batch-update.	4 / 5
Workflow Clarity	The setup-then-use sequence is clear (login via scripts/auth.py, commands auto-authenticate), and delete-slide has a soft checkpoint ('use get-metadata to find IDs'). However destructive and batch operations (delete-slide, replace-text, batch-update) have no validation or verification steps — e.g. no 'run get-text to confirm the replacement' — which caps workflow clarity at 3 per the rubric's destructive/batch guideline.	3 / 5
Progressive Disclosure	A single well-sectioned file with clear headers (setup, read, write, layouts, ID format, output, tokens) and no nested references, which suits a skill of this size. It is not 5 because the inline JSON output examples and full layout catalog could live in a reference file, and the body references scripts/ paths without the bundle providing those files to verify structure against.	4 / 5
	Total	16 / 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 concise and names a distinct niche, but it describes the capability generically ('Full read/write access') with no concrete actions and no 'Use when...' trigger guidance. It reads more like a feature tagline than a routing description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions Google Slides, Google Workspace presentations, or wants to create, read, or edit slide decks.'

Replace 'Full read/write access' with the concrete operations the skill supports: create presentations, add/delete slides, extract slide text, find-and-replace across slides, batch updates.

Include natural synonyms users would say ('presentations', 'slide decks', 'slides') so the skill triggers on phrasing beyond the exact term 'Google Slides'.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Google Slides integration") but the only action language is the generic "Full read/write access" — no concrete operations like create presentation, extract text, or find-and-replace are listed. This matches anchor 2 ('Names the domain but actions are minimal or generic'), not anchor 3, which requires 1-2 concrete named actions.	2 / 5
Completeness	The 'what' is present but shallow ("integration ... Full read/write access") and the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' (Google Slides, read/write, OAuth) is clearly stated rather than vague.	3 / 5
Trigger Term Quality	"Google Slides" is the one strong natural keyword a user would say, but common variations are missing: "presentations", "slide deck", "slides", "Google Workspace". Matches anchor 3 ('Some relevant keywords but missing common variations or synonyms'); not 4 because several natural phrasings users would actually say are absent.	3 / 5
Distinctiveness Conflict Risk	"Google Slides" carves a clear niche distinct from generic presentation/pptx skills, and "No MCP server required" explicitly disambiguates from MCP-based Slides integrations. It is not 5 because without any 'Use when' trigger phrases, a user asking generally about 'presentations' or 'slides' could route to a pptx skill instead.	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: 17 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: 6 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.