humanize-ppt

A presentation system for agent-made PPTs — born for the talk, not just the template. It turns raw material into an AST (audience-state-transfer) outline with per-page visual-enhancement decisions (image / SVG diagram / video), hands a production brief to a downstream renderer (HTML-PPT skills or native PPTX), then runs a capped 3-round presentation checkup (演讲体检) on the rendered deck. It never renders slides itself. Use before generating PPT/HTML slides from raw material, and after rendering when the user says things like "给这份 deck 做演讲体检" or "PPT 渲染质检". If all you want is one beautiful template page with no outline and no checkup, a rendering skill alone is enough.

Quality

75%

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/community/humanize-ppt/SKILL.md

Quality

Content

67%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-structured overview with a concrete output contract, a clear OPC workflow, and a real QA feedback loop. It loses points mainly on motivational verbosity and on referencing files that are not present in the reviewed bundle.

Suggestions

Trim the 'Positioning' prose to factual capability boundaries and drop repeated inline version numbers in favor of a single version note.

Inline one minimal copy-paste CLI example pair (brief mode, then --qa-from) so the body is actionable without requiring docs/local-demo.md.

Reconcile referenced paths — either ship adapters/, docs/, SPEC.md, and registry/ in the bundle or stop referencing them from SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete contracts and file lists, but the 'Positioning' section carries motivational prose ('born for the talk', 'the pretty shell outruns the content density') and repeated version stamps (v0.6.4, v1.1.1) that could be tightened.	3 / 5
Actionability	Provides concrete CLI flags (--qa-from, --style-gallery, --renderer ppt-master, --out), an enumerated output-contract file list, and named renderers; full executable examples are deferred to docs/local-demo.md and SPEC.md rather than inlined.	4 / 5
Workflow Clarity	The O-P-Q-C workflow is clearly sequenced with a capped 3-round QA feedback loop (iterate/pass/needs-human) and the --out wipe/refuse/--force guard, but validation checkpoints are spread across several prose sections rather than one unified checklist.	4 / 5
Progressive Disclosure	Good structure with a dedicated 'Operational references' section giving one-line descriptions and one-level-deep links; however several referenced paths (adapters/ppt-master-bridge-notes.md, docs/index.md, docs/local-demo.md, SPEC.md, registry/renderer_registry.json) are absent from the bundle.	4 / 5
	Total	15 / 20 Passed

Description

83%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 strong: it states concrete capabilities, gives explicit when/when-not guidance with natural trigger phrases, and draws a clear boundary against rendering skills. Its main weakness is domain jargon (AST, 演讲体检) and the broad PPT category leaving slight conflict risk.

Suggestions

Add a plain-language synonym like 'presentation' or 'PowerPoint' alongside PPT/PPTX so the description matches the most common user phrasing.

Soften the AST acronym on first use (e.g. 'audience-state-transfer outline') so the capability reads concretely without insider terminology.

Move the Chinese-only trigger phrases ('演讲体检') alongside an English equivalent ('presentation checkup') to maximize distinctiveness for non-Chinese users.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'turns raw material into an AST outline with per-page visual-enhancement decisions', 'hands a production brief to a downstream renderer', 'runs a capped 3-round presentation checkup', 'never renders slides itself' — but the AST jargon keeps it shy of fully comprehensive coverage.	4 / 5
Completeness	Explicitly answers both what (outline + media decisions + brief + checkup orchestrator) and when ('Use before generating PPT/HTML slides from raw material, and after rendering when the user says...'), with concrete trigger phrases and a clear when-not clause.	5 / 5
Trigger Term Quality	Good natural-term coverage including 'PPT/HTML slides', 'PPTX', 'deck', and quoted user phrases like '给这份 deck 做演讲体检' and 'PPT 渲染质检'; a few common synonyms (e.g. 'presentation', 'powerpoint') are only implied.	4 / 5
Distinctiveness Conflict Risk	Clear niche as a brief orchestrator that 'never renders slides itself' and 'a rendering skill alone is enough', with distinctive checkup triggers; minor overlap risk remains because it operates in the crowded PPT/presentation space alongside the renderers it coordinates with.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: nexu-io/open-design
Path: plugins/community/humanize-ppt/SKILL.md
Commit: 1a7a23d

Reviewed: about 6 hours 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.