sn-ppt-standard

仅在 `sn-ppt-entry` 与 `sn-ppt-story` 已准备绝对 `DECK_DIR` 和 `outline.md` 后使用；生成每页独立 HTML（1600×900）、渲染 PNG、逐页讲稿、`present.html`，并按 `static_postprocess` 选择生成由 Standard 自有 exporter 转换的 PPTX。**`present.html` 始终是必交付产物，缺失即技术故障，不得交付；`static_postprocess` 含 `pptx` 时 PPTX 同为必交付产物（缺一即技术故障），且只能由 Standard 自有 exporter 生成；仅当用户明确要求只要 HTML（`static_postprocess` 为 `[]`）时，PPTX 才可不交付。**

Quality

71%

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 ./skills/sn-ppt-standard/SKILL.md

Quality

Content

73%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, highly actionable orchestration roadmap with clear staged workflow, validation gates, and real reference routing. Its main weakness is verbosity — repeated emphasis of the same mandatory-deliverable and image-scan rules and long prose paragraphs that could be condensed.

Suggestions

De-duplicate the present.html-mandatory and PPTX-mandatory rules: state them once in §1.4 and the §5 hard gate, then reference rather than re-explain in 阶段5 and the red-line section.

Convert the long image_opportunity scan prose in 阶段2 into a compact checklist or decision table; move exhaustive caveats into design-rules.md or planning-contract.md.

Tighten multi-clause sentences (many run 60+ Chinese characters with several semicolons) into bulletted conditions so the workflow reads as a roadmap rather than a spec wall.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the present.html-mandatory rule and image_opportunity:none caveats are repeated across many sections, and several paragraphs (e.g. 阶段2 image scan, 阶段5) are very long prose that could be tightened into checklists.	2 / 5
Actionability	Fully executable commands (deck.py prepare/build, the exact node html_to_pptx.mjs export command, install.sh) plus concrete enums (image_opportunity, presentation 四枚举) and explicit role/file contracts give copy-paste-ready guidance.	5 / 5
Workflow Clarity	Clearly sequenced 阶段0–5 for new decks and 3.1–3.4 for edits, with explicit validation checkpoints (Grounding gate, Style Lock/planning freeze conditions, Review ≤3 with refine loops, 产物核验硬门) and failure/recovery branches.	5 / 5
Progressive Disclosure	Good routing table signals one-level-deep references to real files (design-rules.md, planning-contract.md, quality-checklist.md, etc., all present in references/) and a scripts table, though the body still inlines substantial contract detail that could live in those references.	4 / 5
	Total	16 / 20 Passed

Description

68%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 highly specific and distinctive with concrete deliverables and clear prerequisites, but relies on internal contract jargon rather than natural user trigger phrases. Adding a plain-language 'Use when...' clause would materially raise trigger and completeness scores.

Suggestions

Append a 'Use when...' clause with natural user-facing triggers (e.g. 'create presentation slides', 'generate 1600×900 HTML deck with speaker notes', 'export PPTX') instead of only contract terms like static_postprocess and DECK_DIR.

Lead with a one-line plain summary of what the skill does before the prerequisite/delivery contract detail.

Add common synonyms/file extensions users say (slides, 演示文稿, .pptx, 讲稿) so the description matches natural request phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 生成每页独立 HTML（1600×900）、渲染 PNG、逐页讲稿、present.html、PPTX — with comprehensive coverage of what the skill produces.	5 / 5
Completeness	Answers both what (artifacts produced) and when (仅在 entry/story 准备 DECK_DIR 与 outline.md 后使用), but the when is pipeline-internal ordering rather than a user-intent trigger and could be more explicit.	4 / 5
Trigger Term Quality	Dominantly technical-contract jargon (sn-ppt-entry, static_postprocess, DECK_DIR) with a few generic tokens (HTML, PNG, PPTX); missing the natural phrases a user would actually say to invoke this skill.	2 / 5
Distinctiveness Conflict Risk	Gated on specific sibling-skill prerequisites and named artifacts (1600×900, present.html, Standard 自有 exporter), giving it a clear niche with minimal overlap risk.	5 / 5
	Total	16 / 20 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
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: OpenSenseNova/SenseNova-Skills
Path: skills/sn-ppt-standard/SKILL.md
Commit: 5abde96

Reviewed: 10 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.