sn-ppt-standard

Standard and fast PPT pipeline. All LLM / VLM / T2I calls are wrapped in a single CLI entry (scripts/run_stage.py). The main agent's job is simple: emit ONE shell command per stage, never write loops, never write prompts. Standard mode plans thoroughly with a three-sample deck preview checkpoint (three concatenated deck images plus a preview URL), web research, image search, and user-selected final output format (PPTX or PDF) for polished, delivery-ready presentations. Fast mode builds a complete draft immediately with autonomous decisions, then provides structured refinement suggestions so the user can iterate quickly. Supports AI-generated infographics (U1) for diagrams and flowcharts, web image search (Serper) for real photos, and ECharts for data charts.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/sn-ppt-standard/SKILL.md

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.

The body is highly actionable and clearly sequenced with strong validation checkpoints, but it is held back by redundancy across the failure-handling sections and a couple of dangling references to a missing prompts/ directory.

Suggestions

Consolidate the 'SN API model pitfall', 'Stage failure handling', and 'SN API timeout fallback' sections into one failure-handling block to remove the repeated retry and manual-fallback steps.

Fix the references to prompts/outline.md, prompts/page_html.md, and prompts/page_html_rewrite.md — either add a prompts/ directory to the bundle or correct the paths to point at real files such as references/html_constraints.md.

Move the long workbench bridge-mode and provider-configuration detail into a separate reference file, keeping the SKILL.md body as an overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance, but the 'SN API model pitfall', 'Stage failure handling', and 'SN API timeout fallback' sections overlap heavily and the manual fallback steps and retry rule #7 are restated multiple times.	3 / 5
Actionability	Provides copy-paste-ready bash commands for every pipeline stage, exact progress-echo strings, concrete file paths, named env vars, and step-by-step manual fallback instructions covering common failure cases.	5 / 5
Workflow Clarity	Sequences the full pipeline (preflight -> style-samples -> style -> outline -> asset-plan -> gen-image -> page-html -> export) with resume semantics, validation checkpoints (HTML content check pre-export, post-batch file-size spot-check), retry caps, and explicit error-recovery feedback loops.	5 / 5
Progressive Disclosure	Points to real references like references/html_constraints.md and uses scripts/ helpers, but body references a prompts/ directory (prompts/outline.md, prompts/page_html.md) that does not exist in the bundle, and some inlined operational detail (workbench bridge/provider config) could live in a reference file.	4 / 5
	Total	17 / 20 Passed

Description

75%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 specific and clearly distinct, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness and slightly limits its natural-term coverage. Adding a concrete trigger phrase would lift the two weaker dimensions.

Suggestions

Append an explicit 'Use when...' clause naming user-facing trigger phrases (e.g., 'Use when the user asks to generate a PPT, create a presentation/slides/deck, or convert content to PPTX/PDF').

Add natural synonyms users actually say — 'slides', 'deck', 'PowerPoint' — alongside 'PPT/PPTX' to broaden trigger term coverage.

Move or mirror the entry-point trigger guidance ('生成 PPT', '/skill sn-ppt-entry') into the description so the 'when' is self-contained.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both modes — wrapped CLI calls, three-sample deck preview checkpoint, web research, image search, AI-generated infographics (U1), Serper web image search, and ECharts data charts — giving comprehensive coverage.	5 / 5
Completeness	The description gives a clear, detailed 'what' but contains no explicit 'Use when...' trigger clause; per the rubric, a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Covers natural terms like 'PPT', 'PPTX', 'PDF', 'presentations', 'diagrams', 'flowcharts', and 'data charts', but is missing common synonyms such as 'slides', 'deck', or 'PowerPoint' and leans somewhat technical.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — a SenseNova PPT generation pipeline with standard/fast modes via a single CLI entry — with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

75%

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 — 12 / 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
referenced_paths_exist	Referenced path issues: 2 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: OpenSenseNova/SenseNova-Skills
Path: skills/sn-ppt-standard/SKILL.md
Commit: 61b60bb

Reviewed: 8 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.