google-slides-review

Use this skill at the end of a Google Slides deck-creation flow run by the same agent in the current session, before reporting the finished URL to the user. Catches the failure modes a creating agent reliably misses — surviving placeholder text, unswapped template imagery, layout overflow, hidden-original leaks. Trigger when the parent google-slides workflow reaches Step 9 / QA, or when the user asks "is this deck ready?" / "QA my deck" about a deck this agent itself just edited. Do NOT trigger for reviewing decks the agent did not create — without the Step 5 pre-fill snapshot the leak check silently degrades and the result is misleading.

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a high-quality, highly actionable skill that provides precise, executable guidance for a complex multi-agent QA workflow. Its greatest strength is the specificity of the sub-agent prompts — complete with exact tool calls, output schemas, and anti-patterns to detect. The main weakness is length: the three full sub-agent prompts make the file long, though this is partially justified by the need for literal prompt text, and the progressive disclosure could be improved by splitting prompts into referenced files.

Suggestions

Consider moving the three sub-agent prompts into separate reference files (e.g., `references/visual-review-prompt.md`) and referencing them from the main skill, reducing the SKILL.md to a concise orchestration overview.

Trim the introductory paragraph — the description of creator bias is repeated in both the intro and workflow step 5; consolidate to one mention.

Dimension	Reasoning	Score
Conciseness	The skill is fairly long but most content earns its place — the sub-agent prompts are necessarily detailed and specific. However, there's some redundancy (e.g., the bias explanation is repeated in both the intro and workflow step 5, and some phrasing could be tightened). The opening paragraph explaining why the skill exists is useful context but slightly verbose.	2 / 3
Actionability	Extremely actionable: provides literal copy-paste sub-agent prompts with specific tool calls, exact YAML output schemas, concrete template-token lists to scan for, specific severity categories, and precise aggregation format. The workflow is fully executable with named tools and parameters.	3 / 3
Workflow Clarity	The workflow is clearly sequenced (sanity check → spawn sub-agents → wait → aggregate → report), with explicit validation at multiple levels: input sanity checks, required `inspected_slide_ids` audit trails to prevent silent skips, a fix-then-rerun loop with an iteration cap at 3, and a clear READY/NOT READY decision gate. The loop contract with escalation after iteration 3 is a strong feedback loop.	3 / 3
Progressive Disclosure	The skill references `../google-slides/references/workflow.md` for the snapshot schema, which is good progressive disclosure. However, the skill itself is quite long (~250 lines) with the three full sub-agent prompts inline. These prompts could potentially be split into separate reference files, though an argument can be made they need to be inline since they're literal prompt arguments. No bundle files are provided to verify the referenced path exists.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly defines its niche (post-creation QA for Google Slides decks), lists specific failure modes it catches, provides natural trigger phrases, and explicitly scopes when it should and should not be used. The inclusion of anti-triggers (when NOT to use it) is a strong differentiator. The only minor note is the use of second-person-adjacent phrasing ('Use this skill') in the opening, though it transitions to third-person descriptions of capabilities.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: catching surviving placeholder text, unswapped template imagery, layout overflow, hidden-original leaks. These are precise, actionable QA checks rather than vague language.	3 / 3
Completeness	Clearly answers both 'what' (catches placeholder text, unswapped imagery, layout overflow, hidden-original leaks) and 'when' (at end of deck-creation flow, Step 9/QA, or when user asks 'is this deck ready?'). Also explicitly states when NOT to use it, adding further clarity.	3 / 3
Trigger Term Quality	Includes natural trigger phrases users would say ('is this deck ready?', 'QA my deck') and technical triggers ('Step 9 / QA'). Also specifies when NOT to trigger, which helps with precision. Terms like 'Google Slides', 'deck', 'QA' are natural user language.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — scoped specifically to QA of Google Slides decks created by the same agent in the current session, with explicit exclusion of externally-created decks. The dependency on a Step 5 pre-fill snapshot and the specific failure modes (placeholder text, template imagery, hidden-original leaks) make this very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: treasure-data/td-skills
Commit: adb83d7

Reviewed: 6 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.