report-to-google-slides

Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing HTML analytics report into a native Google Slides deck.

Quality

81%

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

Quality

Content

81%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 well-structured, actionable skill body with strong workflow sequencing and explicit validation/feedback loops, appropriately offloading implementation to a bundled helper script. Slight gains are available from tightening intro prose and surfacing the JSON output schemas as reference material.

Suggestions

Tighten the intro paragraph and trim verbose Standards bullets (e.g., the stakeholder-skimming sentence) to push conciseness toward level 5.

Make the step-5 repair action concrete by naming which helper flag or source assumption to revise, or point to the script's options for regeneration.

Add a short reference (inline or a bundled doc) showing the expected shape of manifest.json and deck_plan.json so the inspect-outputs step is fully actionable.

Dimension	Reasoning	Score
Conciseness	Efficient and assumes Claude's competence (no basic-concept explanations), but a few sentences could be trimmed, such as the stakeholder-skimming framing in the intro and some verbose Standards bullets, keeping it just below level 5.	4 / 5
Actionability	Provides an executable helper invocation with flags, named MCP tools with explicit modes, an `unzip -t` check, and concrete output filenames; minor gaps remain in the vague step-5 'revise ... regenerate' direction and the absence of example JSON output structures.	4 / 5
Workflow Clarity	A clear six-step sequence with explicit validation checkpoints (preflight `status: "passed"`, `unzip -t`, per-slide thumbnail verification) and a feedback loop that repairs and regenerates before handoff, matching the level 5 anchor.	5 / 5
Progressive Disclosure	A clear overview delegates heavy implementation to the real one-level-deep helper script via a well-signaled path placeholder; the long inline Standards list and undocumented JSON output schemas keep it just short of level 5.	4 / 5
	Total	17 / 20 Passed

Description

82%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.

A tightly scoped, well-gated description that clearly states both its purpose and an explicit invocation trigger, with strong distinctiveness and good (though not exhaustive) trigger terms. Its only real limitation is naming a single concrete action rather than enumerating several.

Dimension	Reasoning	Score
Specificity	Names the domain ('existing HTML analytics report') and one concrete action ('convert ... into a native Google Slides deck'), matching the 1-2 concrete actions anchor; it does not enumerate several distinct actions to reach level 4.	3 / 5
Completeness	Explicitly answers both what ('convert an existing HTML analytics report into a native Google Slides deck') and when ('Invoke only when the user explicitly asks to convert ...') with a concrete trigger phrase, matching the level 5 anchor.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('convert', 'HTML analytics report', 'Google Slides', 'deck') with good coverage, but omits common synonyms ('presentation', 'slides') and file extensions, so it falls short of comprehensive level 5.	4 / 5
Distinctiveness Conflict Risk	A clear narrow niche (HTML analytics report to native Google Slides deck) gated by 'only when the user explicitly asks', giving it distinct triggers and minimal conflict risk per the level 5 anchor.	5 / 5
	Total	17 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/data-analytics/workflows/build-report/report-to-google-slides/SKILL.md
Commit: be5af90

Reviewed: 4 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.