nature-paper2ppt

Build a complete Nature-style Chinese PPTX presentation from a scientific paper, preprint, PDF, article text, figure legends, or reading notes. Use for journal club, group meeting, thesis seminar, paper sharing, conference or defense decks, and Chinese requests such as 论文做PPT、论文汇报、组会PPT、文献汇报、学术汇报、做幻灯片、读书报告PPT. It classifies paper type, builds an evidence-led story, selects key figures, writes Chinese slide content and speaker notes, creates the actual .pptx, and runs corrective QA for complete figure crops, stable alignment, text overflow, and de-templated Chinese academic expression. Also trigger when improving weak paper-to-PPT output with cropped figures, loose alignment, obvious AI-style wording, or heavy manual rework.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%

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

The router is a lean, well-sequenced, actionable instruction skill with an explicit audit→revise→re-run feedback loop. Its only real weakness is progressive-disclosure completeness: the manifest.yaml and static core layer it tells the reader to load first are absent from the provided bundle.

Suggestions

Ship manifest.yaml and the static/ core fragments (core/principles.md, core/toolchain.md, core/workflow.md, core/output-and-quality.md) alongside this router — the body's very first instruction is 'Read manifest.yaml', but that file is absent, so the disclosed navigation path breaks before it starts.

Resolve the ../nature-shared/core/terminology-ledger.md reference (and the nature-shared/ dependency): either bundle the shared ledger or repoint to a path that exists so the Terminology Ledger step is executable from this skill alone.

Add a one-line fallback for the QA loop when audit_pptx_quality.py is unavailable (the body already says 'unless the file is unavailable') so the validate→revise→re-run workflow has an explicit alternate path rather than silently skipping verification.

Dimension	Reasoning	Score
Conciseness	The router is intentionally lean, assumes competence, and avoids explaining concepts Claude already knows (no 'what a PPTX is', no library tutorials); every section earns its place by routing or constraining behavior. It matches the 'Lean and efficient; assumes Claude's competence' anchor rather than the level-2 'mostly efficient but could be tightened' or level-1 'verbose/padded' anchors.	3 / 3
Actionability	It gives concrete, executable guidance: exact paths to read ('manifest.yaml', 'core/principles.md', 'core/toolchain.md'), a numbered priority order, and a real command ('run scripts/audit_pptx_quality.py'); per the rubric, actionable instruction-only guidance is not penalized for lacking inline code. It sits at the 'Fully executable... specific examples' end rather than the vague level-1 or pseudocode level-2 anchors.	3 / 3
Workflow Clarity	The five-step routing protocol is clearly sequenced with checkpoints — 'State the detected value in one short line to the user... so they can correct you cheaply' — and an explicit feedback loop: 'run scripts/audit_pptx_quality.py... Treat high-severity findings as blockers, revise the deck, then re-run the audit and record the final result'. This matches the 'Clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	The on_demand reference table is exemplary one-level-deep signaling and its three referenced files (design-and-layout.md, figure-assets.md, self-review.md) plus audit_pptx_quality.py are all present, but the bundle is missing the linchpin manifest.yaml (the first file step 1 instructs the reader to open), the static/ core layer, and ../nature-shared/core/terminology-ledger.md. Per the guideline to score against the actual bundle, this broken navigation path caps the score at the 'some structure... navigation incomplete' level rather than a full 3.	2 / 3
	Total	11 / 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.

The description is specific, trigger-rich in both English and Chinese, and explicitly answers both what it does and when to use it, all in third person. It is a strong, low-conflict, well-targeted description.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Build a complete Nature-style Chinese PPTX presentation', 'classifies paper type', 'builds an evidence-led story', 'selects key figures', 'writes Chinese slide content and speaker notes', 'creates the actual .pptx', and 'runs corrective QA for complete figure crops, stable alignment, text overflow' — matching the 'Lists multiple specific concrete actions' anchor rather than the level-2 'some actions' or level-1 'vague' anchors.	3 / 3
Completeness	It explicitly answers both what ('Build a complete Nature-style Chinese PPTX presentation from a scientific paper, preprint, PDF...') and when ('Use for journal club, group meeting...' and 'Also trigger when improving weak paper-to-PPT output...'), matching the 'Clearly answers both what AND when with explicit triggers' anchor and exceeding the level-2 'has what, when implied' cap.	3 / 3
Trigger Term Quality	It covers natural terms users would say in both English ('journal club, group meeting, thesis seminar, paper sharing, conference or defense decks') and Chinese ('论文做PPT、论文汇报、组会PPT、文献汇报、学术汇报、做幻灯片、读书报告PPT'), plus remediation triggers ('cropped figures, loose alignment, obvious AI-style wording'), which is broad natural-term coverage rather than the level-2 'some relevant keywords' or level-1 'jargon/generic' anchors.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — Nature-style Chinese academic PPTX from scientific papers with distinctive Chinese-language triggers — making it unlikely to fire for unrelated skills, matching the 'Clear niche with distinct triggers; unlikely to conflict' anchor rather than the overlapping level-2 or generic level-1 anchors.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: Yuan1z0825/nature-skills
Path: skills/nature-paper2ppt/SKILL.md
Commit: 703c150

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.