Real Skill packageSource verifiedClawHub registry

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…

Identity and source

Publisher attributionSenseNova-Skillsregistry owner unverified by skillvetai
Functional categoryDocuments, PDF & Presentationsautomatically inferred · 73% rule confidence
Package forminstruction with code37 recorded files
Canonical sourceClawHub registryclawhub:sensenova-skills:sn-ppt-standard
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/19/2026.claude/skills/sn-ppt-standard

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/19/2026.agents/skills/sn-ppt-standard

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/19/2026skills/sn-ppt-standard

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @sensenova-skills/sn-ppt-standard
clawhub inspect @sensenova-skills/sn-ppt-standard --version 2026.8.19

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
37 / 37 inspected as text
Checked
8/19/2026, 4:03:31 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highEncoded content is decoded and executedscripts/export_pptx/lib/pptx_builder.mjs:196 · confidence 90%base64
1 High/Critical review queue entry
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
6 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • browser control — automatically inferred
8 dependency and API indicators
  • npm: pptxgenjs ^3.12.0
  • npm: playwright 1.58.2
  • npm: echarts ^5.4.3
  • api: clawhub.ai
  • api: github.com
  • api: registry.npmjs.org
  • api: token.sensenova.cn
  • api: www.w3.org
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/19/2026, 3:16:24 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:0d6406fc76bd3e87c7130421b28b1a506a7c00b114c27d7d657d67622bc2ef8e
Show up to 30 recorded paths
  • lib/__init__.py
  • lib/model_client.py
  • prompts/asset_plan.md
  • prompts/asset_qc.md
  • prompts/deck_review.md
  • prompts/outline.md
  • prompts/page_html_rewrite.md
  • prompts/page_html.md
  • prompts/page_review.md
  • prompts/page_rewrite.md
  • prompts/refine_apply.md
  • prompts/refine_review.md
  • prompts/style_samples.md
  • prompts/style_spec.md
  • references/html_constraints.md
  • references/style_catalog.md
  • scripts/build_style_catalog.py
  • scripts/export_pptx/html_to_pdf.mjs
  • scripts/export_pptx/html_to_pptx.mjs
  • scripts/export_pptx/lib/browser_setup.mjs
  • scripts/export_pptx/lib/cli_guards.mjs
  • scripts/export_pptx/lib/dom_extractor.mjs
  • scripts/export_pptx/lib/echarts_to_pptx.mjs
  • scripts/export_pptx/lib/image_downloader.mjs
  • scripts/export_pptx/lib/postprocess_pptx.mjs
  • scripts/export_pptx/lib/pptx_builder.mjs
  • scripts/export_pptx/lib/style_parser.mjs
  • scripts/export_pptx/package-lock.json
  • scripts/export_pptx/package.json
  • scripts/export_pptx/screenshot.mjs

Source changelog

sn-ppt-standard 2026.8.19 - Refined pipeline for standard and fast PPT generation, with all LLM/VLM/T2I calls handled via a single CLI entry. - Fast mode: autonomously drafts entire decks immediately, then provides structured, actionable refinement suggestions to guide user improvements. - Standard mode: plans thoroughly with a three-deck preview checkpoint, performs web/image research, and prompts user to choose the final deck style. - Clear division of responsibilities between agent and script; strict rules to avoid loops, prompt-writing, image placeholder use, silent failures, or data fabrication. - Language and output integrity strictly enforced: language matches user query, images are always local, and all data is document- or web-sourced. - Skill must be invoked via entrypoint (`/skill sn-ppt-entry`), never directly; missing prerequisites trigger halt with user guidance.