SenseNova-Skills is a collection of modular skills that extend SenseNova models with office-assistant capabilities such as image generation, presentation creation, spreadsheet analysis, and research. The skills are designed for use in agent runtimes and can be combined into productivity workflows; the catalogue entries are individual skills and agents from this collection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OpenSenseNova/SenseNova-Skills --skill sn-ppt-standardgit clone --depth 1 https://github.com/OpenSenseNova/SenseNova-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/opensensenova/sensenova-skills/sn-ppt-standard)<a href="https://agentmods.dev/skills/opensensenova/sensenova-skills/sn-ppt-standard"><img src="https://agentmods.dev/badge/skills/opensensenova/sensenova-skills/sn-ppt-standard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/opensensenova/sensenova-skills/sn-ppt-standard"><img src="https://agentmods.dev/badge/skills/opensensenova/sensenova-skills/sn-ppt-standard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 38 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00182 | $0.12481 |
| Opus 5.5 | $0.00073 | $0.04992 |
| Sonnet 5.5 | $0.00036 | $0.02496 |
| Haiku 4.5 | $0.00018 | $0.01248 |
Grade A, and why
sn-ppt-standard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sn-ppt-standard
把本文件当作路线图，不要当作需要一次背完的规范全集。只读取已准备任务的 Entry/Story 交接、该路径要求的 reference 和职责卡。
Box-Agent 兼容入口
当当前 harness 暴露 sub_agent、inspect_images、generate_image、bash 等 Box-Agent 原生工具时，开始任何制作动作前必须完整读取 references/box-agent-tool-contract.md。该契约只覆盖工具名称、参数、脚本路径、委派方式和权限边界；本文件及各职责卡的事实、设计、质量和交付标准仍然有效。委派任何角色时，都要在 task 中显式要求其先读取同一契约与自己的 subagents/<role>.md。
Hermes 环境等效工具
Hermes 不暴露 Box-Agent 工具名，但提供等价能力。在 Hermes 宿主中，正文下文中出现的
bash / inspect_images / generate_image / sub_agent 调用一律按下表翻译后执行，
且无须读取 references/box-agent-tool-contract.md（该契约仅用于 Box-Agent harness）：
| Box-Agent 写法（正文） | Hermes 等效工具 | 翻译要点 |
|---|---|---|
bash(command, timeout) |
terminal(command, timeout) |
参数直接对应；Hermes 专属参数（workdir/pty）按需使用 |
inspect_images(image_paths=[...], instruction=..., strategy="native") |
vision_analyze(image_url=<单张路径>, question=<instruction>) |
每张图一次调用；strategy 参数 Hermes 无，忽略 |
generate_image(prompt, output_path, size, watermark=false) |
image_generate(prompt, aspect_ratio=<按尺寸取>) |
无 output_path，生成后回读返回路径验证落盘 |
sub_agent(title, task, required_tools, write_scope, budget) |
delegate_task(goal=<task>, context=<背景>) |
用 Hermes 参数形态；自包含 task、语言合同、绝对路径与产物双读验证的要求不变 |
委派仍要求子任务自包含、携带语言合同与职责卡绝对路径，并用 read_file / search_files
验证声明的产物；正文的阶段划分、质量标准与交付要求不因宿主变化而放宽。
Entry / Story 输入契约（最高优先级）
本 Skill 不接收裸 query，不自行创建任务目录。只接受绝对 DECK_DIR，且必须存在 task_pack.json、info_pack.json 和 outline.md。
choices.output 必须为 static_html，且 ppt_mode 必须为 standard。开始和恢复时重新读取磁盘上的 outline.md；不得自行 Research、重复解析材料、改写 outline、增删页面、重排页序或新增事实。输入不满足时返回 Entry。
1. 所有模式共享的合同
1.1 Orchestrator 的职责与边界
Orchestrator 只负责：读取 Entry/Story 交接、规划、委派、合并、验收和确定性收尾。
- 可写：
plan/、base.css、知识汇总和构建产物。 - 不直接写：
slides/slide_NN.html；页面由 Slide 或 Review 修改。 - 不伪装工具能力，不把计划动作写成已完成动作。
- 每个 subagent 必须有显式 label；失败、超时或未自然收尾的结果不得当成完成品。
sub_agent(title, task, skills, required_tools, files, write_scope, budget)负责委派；其返回的结构化 contract、artifact paths 与handoff_path是父级交接真相，Orchestrator 不读取子 Agent 的messages.json、tool_log.json或 system/tool 快照来轮询进度。父级负责通过inspect_images完成视觉检查，以及通过 bash、render、build 和 export 完成确定性收尾。
What ships with it
44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 350 B
- assets/licenses/OFL-1.1.txt 3.9 KB
- assets/vendor/echarts.min.js 1005 KB runs code
- references/base-template.css 35 KB
- references/box-agent-tool-contract.md 5.7 KB
- references/design-rules.md 63 KB
- references/design-styles.md 26 KB
- references/editing-contract.md 4.9 KB
- references/fonts.md 10 KB
- references/layout-patterns.md 17 KB
- references/planning-contract.md 27 KB
- references/quality-checklist.md 30 KB
- scripts/deck.py 59 KB runs code
- scripts/export_pptx/html_to_pptx.mjs 6.3 KB runs code
- scripts/export_pptx/lib/browser_picker.mjs 5.5 KB runs code
- scripts/export_pptx/lib/cli_guards.mjs 14 KB runs code
- scripts/export_pptx/lib/dom_extractor.mjs 37 KB runs code
- scripts/export_pptx/lib/echarts_discovery.mjs 1.2 KB runs code
- scripts/export_pptx/lib/echarts_to_pptx.mjs 30 KB runs code
- scripts/export_pptx/lib/image_downloader.mjs 4.1 KB runs code
- scripts/export_pptx/lib/postprocess_pptx.mjs 6.9 KB runs code
- scripts/export_pptx/lib/pptx_builder.mjs 85 KB runs code
- scripts/export_pptx/lib/style_parser.mjs 19 KB runs code
- scripts/export_pptx/package-lock.json 9.1 KB
- scripts/export_pptx/package.json 268 B
- scripts/export_pptx/screenshot.mjs 2.7 KB runs code
- scripts/export_pptx/test/fixtures/dom-layout-regression.html 758 B
- scripts/export_pptx/test/fixtures/echarts-fallback.html 1.2 KB
- scripts/export_pptx/test/test_color_srgb_regression.mjs 881 B runs code
- scripts/export_pptx/test/test_dom_layout_regression.mjs 1.5 KB runs code
- scripts/export_pptx/test/test_echarts_discovery.mjs 1.4 KB runs code
- scripts/export_pptx/test/test_echarts_fallback.mjs 2.0 KB runs code
- scripts/export_pptx/test/test_echarts_to_pptx_regression.mjs 2.3 KB runs code
- scripts/export_pptx/test/test_radial_overlay_regression.mjs 1.0 KB runs code
- scripts/export_pptx/test/test_text_box_padding_regression.mjs 675 B runs code
- scripts/font_bundle.py 39 KB runs code
- scripts/image_cutout.py 14 KB runs code
- scripts/install.sh 13 KB runs code
- scripts/render.py 95 KB runs code
- scripts/serper_images.py 4.2 KB runs code
- scripts/stage_materials.py 38 KB runs code
- subagents/image.md 14 KB
- subagents/review.md 26 KB
- subagents/slide.md 24 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -141 lines · +12 tokens per session 04079018e575
- 1mo ago Changed e76d3365def5
- 2mo ago First seen · 478 lines · 170 tokens per session scan A 4743e18ab104
sn-ppt-standard is a skill published in the GitHub repository OpenSenseNova/SenseNova-Skills (6,031 stars, last pushed 3d ago), licensed MIT. It adds 182 tokens to every session and 12,481 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
sn-ppt-standard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sn-ppt-standardOpenSenseNova/SenseNova-Skills | Skill | 6.0k | 3d ago | MIT | A | 182 | Codex |
| article-writernetease-youdao/LobsterAI | Skill | 6.2k | yesterday | MIT | A | 62 | Claude Code, Codex |
| skin-creatornetease-youdao/LobsterAI | Skill | 6.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| content-plannernetease-youdao/LobsterAI | Skill | 6.2k | yesterday | MIT | A | 63 | Claude Code, Codex |
| ad-spend-watch-getting-startedmakecindy/cindy | Skill | 9.3k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| apple-search-ads-review-opsmakecindy/cindy | Skill | 9.3k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| sable-game-art-opsmakecindy/cindy | Skill | 9.3k | yesterday | Apache-2.0 | A | 89 | Claude Code, Codex |