Agent skill

SenseNova PPT Entry

by OpenSenseNova in OpenSenseNova/SenseNova-Skills

Entry point for SenseNova presentation generation: creates a task folder, picks depth, output format and design richness, and routes to the right PPT skill.

MITAuto-check: notesDocuments & Office

SKILL.md written in Chinese; this summary is our English description.

Install SenseNova PPT Entry

skills CLI
$ npx skills add OpenSenseNova/SenseNova-Skills --skill sn-ppt-entry -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OpenSenseNova/SenseNova-Skills sn-ppt-entry --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OpenSenseNova/SenseNova-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sn-ppt-entry .claude/skills/sn-ppt-entry && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sn-ppt-entry
GitHub stars
5.7k
Token cost
~2.7k tokens
SKILL.md length
575 words
Files
4 (incl. scripts)
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

Entry point for SenseNova presentation generation: creates a task folder, picks depth, output format and design richness, and routes to the right PPT skill.

  • Works in 6 steps: 先执行 pwd -P,把该命令实际返回的完整绝对路径逐字记为… → 唯一父目录是 /ppt_decks/。 → 目录名是 _。 → …
  • Creating a presentation or slide deck from a query and optional files
  • SKILL.md covers Box-Agent 兼容入口, 三个独立选择, 唯一目录规则 and task_pack.json, plus 6 more sections
  • Runs Python scripts from its folder; calls python

What it does

sn-ppt-entry is the entry point for SenseNova's presentation skills. It accepts a request to make a PPT, creates a unique task directory and prepares materials, then must call sn-ppt-story to generate a shared outline.md before handing off by output choice to sn-ppt-standard, sn-ppt-dazzle or sn-ppt-creative. Requests to modify an existing PPTX go straight to sn-ppt-edit. It is not a standalone runtime: it uses the host agent's own understanding, search and image tools, and falls back to the bundled sn-ppt-tools only when native ones are missing. The skill text is in Chinese.

Three independent choices shape a task: execution depth (draft, standard or deep, where deep runs a full research skill first and standard does targeted external searches), output format (static HTML, dynamic HTML or creative) and design richness (restrained, rich by default, or high-creative). The entry recommends a value for each without blocking, and all state lives in task_pack.json inside a task folder under ppt_decks in the real working directory, which is reused when a task is resumed. Bundled scripts parse user documents and time stages.

When your agent uses it

  • Creating a presentation or slide deck from a query and optional files
  • Resuming an existing SenseNova presentation task
  • Choosing between draft, standard and deep generation
  • Routing a request to static HTML, dynamic HTML or creative output

Example prompts

  • “Make a deck on our product roadmap from the attached notes.”
  • “Resume the presentation task in ppt_decks and apply my outline changes.”
  • “Create a restrained, standard-depth presentation about data privacy for the legal team.”

Requirements

  • Python with the packages listed in requirements.txt

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 先执行 pwd -P,把该命令实际返回的完整绝对路径逐字记为 workspace_root。宿主显示的
  2. 唯一父目录是 /ppt_decks/。
  3. 目录名是 _。
  4. 创建后在同一条命令中用 pwd -P/绝对化结果回显 deck_dir,立即写入
  5. 不使用用户 home 根、Skill 目录、repo 根、/tmp、另一个 workspace 或
  6. 不能创建 /ppt_decks/ 时停止并报告权限问题,不换地方继续。

What it can do on your machine

Read from SKILL.md and the folder at commit 7838651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

SenseNova PPT Entry loads about 2.7k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 575 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:210
    Hermes/OpenClaw 实际读取的用户级 `.env`、缺失项和配置模板。

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from OpenSenseNova/SenseNova-Skills at commit 7838651, republished under its MIT licence (© OpenSenseNova). 575 words, ~2,658 tokens.

Download SKILL.mdSave it as .claude/skills/sn-ppt-entry/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
sn-ppt-entry
description
Use when a user asks to create a presentation, slide deck, PPT, or PPTX from a query and optional files, or to resume an existing SenseNova presentation task.
metadata.project
SenseNova-Skills
metadata.tier
1
metadata.category
scene
metadata.user_visible
true
triggers
生成 PPT, 做一套 PPT, 做一份演示, 继续生成 PPT, sn-ppt-entry

sn-ppt-entry

统一接收 PPT 生成请求,建立唯一任务目录,准备材料。Standard 先完成定向外部证据补充, Deep 先完成完整 Research,下一步必须调用 sn-ppt-story 生成公共 outline.md,再按 choices.output 分发到 sn-ppt-standard、sn-ppt-dazzle 或 sn-ppt-creative。

这是一套 Skill 的入口,不是独立运行时。文本理解、视觉理解和推理使用宿主 Agent 已有能力。普通搜索、图片搜索和图片生成优先使用宿主原生工具;原生能力不存在或实际 调用不可用时,才使用 PPT 整包自带的 sn-ppt-tools。不得要求用户另外配置模型客户端, 不得调用 model_client.py、stage.py 或为本流程再造 CLI 调度层。

Box-Agent 兼容入口

在 Box-Agent 中,从本次加载的 Skill 提示取得 Entry 的绝对 Skill Root,记为 <ENTRY_SKILL_ROOT>。Entry 的所有确定性脚本都必须使用 python "<ENTRY_SKILL_ROOT>/scripts/<name>.py" 调用;禁止使用 $SKILL_DIR、当前工作目录 或相对的 skills/ 路径。所有任务产物仍必须写入同一个绝对 $DECK_DIR,并在调用 Story 和出口 Skill 时逐字复用该路径。

三个独立选择

执行深度
  • draft:尽快形成可看的方向稿。默认不做外部事实搜索,大纲完成后直接生产。
  • standard:质量和等待时间平衡。Story 前由 Entry 做定向外部搜索和证据补充,不运行 完整 sn-deep-research;生成前让用户看 outline.md。
  • deep:先完成 sn-deep-research,再生成正式 outline.md;生成前让用户确认。

Entry 根据任务复杂度、事实时效性、材料完整度和用户措辞推荐一档,同时展示 Draft / Standard / Deep。用户可以覆盖;用户未覆盖时采用推荐,不为这个选择增加一轮 阻塞问答。

输出格式
  • static_html -> sn-ppt-standard
  • dynamic_html -> sn-ppt-dazzle
  • creative -> sn-ppt-creative

用户提供已有 PPTX、模板或半成品并要求修改时,直接进入 sn-ppt-edit,不是先走生成 出口。Static HTML 仍由 sn-ppt-standard 自己后处理(默认导出 PPTX)。Entry 只负责路由、验证真实文件并登记 artifact。

设计丰富度
  • restrained(克制):政企、学术、法务、财务或明确要求简洁。
  • rich(丰富):默认,适合多数业务汇报、产品介绍和正式演示。
  • high_creative(高创意):发布会、品牌传播、创意提案或明确要求强视觉。

用户明确指定时直接采用;否则结合场景、受众、输出格式和措辞推荐。显示当前选择与 三档名称,但不单独阻塞。用户在生成前、确认大纲时或后续修改中覆盖时,更新同一份 task_pack.json。丰富度只决定视觉投入,不改变事实标准和 Story 遵循要求。

唯一目录规则

新任务的输出位置沿用已经验证稳定的原 Entry 规则,不得重新推断:

  1. 先执行 pwd -P,把该命令实际返回的完整绝对路径逐字记为 workspace_root。宿主显示的 session workspace、repo 根或其他路径标签都不能替代这次 pwd -P 的结果;尤其不得自行 删除返回路径末尾的 output、workspace 等目录名。
  2. 唯一父目录是 <workspace_root>/ppt_decks/。
  3. 目录名是 <topic_concise>_<YYYYMMDD_HHMMSS>。
  4. 创建后在同一条命令中用 pwd -P/绝对化结果回显 deck_dir,立即写入 task_pack.deck_dir,此后全链路只逐字复用该值,禁止根据框架 workspace 信息重新拼接。
  5. 不使用用户 home 根、Skill 目录、repo 根、/tmp、另一个 workspace 或 PPT_DECK_ROOT。
  6. 不能创建 <workspace_root>/ppt_decks/ 时停止并报告权限问题,不换地方继续。

Box-Agent 的文件工具相对根通常是 <session_workspace>/output,而会话元数据中的 workspace 可能是它的父目录。两者不是同一路径。创建 task_pack.json、info_pack.json、outline.md 和后续产物时必须全部使用上述同一个 deck_dir;每次文件工具返回的绝对落盘路径都要位于 该目录。若返回路径不一致,立即停止并修正路径,不得在两个 ppt_decks/ 之间继续。JSON 和 Markdown 直接用文件工具写入,不要用 execute_code 内嵌一个重新推导的绝对路径。

已有任务必须复用已有 task_pack.json 中的绝对 deck_dir;继续任务不得新建目录。 所有 Skill 安装目录只读。

task_pack.json

创建目录后立即写入,并在每个阶段边界原地更新。它在任务完成后仍然保留,用于进度 展示、任务中断恢复和后续编辑。保持字段少而稳定:

json
{
  "schema_version": "ppt_task_v2",
  "deck_id": "topic_20260729_143015",
  "deck_dir": "/absolute/workspace/ppt_decks/topic_20260729_143015",
  "workspace_root": "/absolute/workspace",
  "ppt_mode": "standard",
  "params": {
    "role": "...",
    "audience": "...",
    "scene": "...",
    "page_count": 8,
    "language": "zh-Hans",
    "image_source": "auto",
    "infographic_source": "echarts"
  },
  "request": {
    "query": "...",
    "source_files": []
  },
  "choices": {
    "execution_depth": "standard",
    "output": "static_html",
    "design_richness": "rich",
    "static_postprocess": ["pptx"]
  },
  "state": {
    "status": "preparing",
    "current_stage": "entry",
    "completed_stages": [],
    "research": {
      "required": false,
      "executor": null,
      "mode": null
    },
    "capabilities": {},
    "artifacts": {},
    "last_error": null,
    "updated_at": "ISO-8601"
  },
  "created_at": "ISO-8601"
}

当 choices.output 是 static_html 时,ppt_mode 必须是 standard,static_postprocess 默认必须是 ["pptx"]。只有用户明确说“只要 HTML”或“不要 PPTX”时才写 []。

其他输出出口的后处理字段写 [],不触发 Static 后处理。

ppt_mode 是旧出口的兼容字段:

choices.outputppt_mode
static_htmlstandard
dynamic_htmldazzle
creativecreative

阶段更新只修改相关字段,不重写用户选择和历史完成项。开始阶段时写 current_stage/status/updated_at;完成时把阶段加入 completed_stages 并把真实产物的 绝对路径写入 artifacts;失败时写 last_error。文件系统中的真实产物优先于过时的状态 字段。

info_pack.json

只承载材料和事实信息,不复制运行状态:

json
{
  "user_query": "...",
  "user_assets": {
    "reference_images": [],
    "reference_image_captions": {},
    "reference_docs": [],
    "reference_docs_failed": []
  },
  "document_digest": {
    "topic_summary": "...",
    "key_sections": [],
    "key_points": [],
    "data_highlights": [],
    "conflicts": [],
    "open_questions": [],
    "inherited_tables": [],
    "inherited_images": []
  },
  "raw_documents": "/absolute/deck/raw_documents.json",
  "research_report": null
}

document_digest 由宿主 Agent 阅读完整材料后直接写入,不通过额外模型 API。数字、专有 名词、时间、单位和材料间冲突必须保真。上传图片和文档内图片继续遵守“一张图片只理解 一次”的原有能力:宿主 Agent 用原生视觉能力读取后,把上传图片说明缓存到 reference_image_captions[absolute_path],把文档内图片说明缓存到 raw_documents.documents[].inherited_images[].visual_summary。已有缓存且图片未变时跳过, 下游统一读取缓存;不创建独立 caption 服务。

可选搜索与图像能力

把当前 Skill 的同级目录解析为 skills 根,并固定:

text
PPT_TOOLS_DIR = <skills root>/sn-ppt-tools

开始需要某项能力时读取 <PPT_TOOLS_DIR>/references/capability-policy.md,按 native -> bundled -> none 选择。sn-ppt-tools 是 PPT 整包的一部分,不做“是否安装” 判断,也不扫描其他仓库。只把每类能力的来源、状态、非敏感错误摘要和更新时间写入 task_pack.state.capabilities;不得记录 key 或 Authorization header。

媒体能力都不是 Entry 的强制前置。缺失时按 policy 继续;只有 Creative 已被明确选择且 原生、内置生图都不可用时,暂停 Creative 出口并保留全部前置产物,不自动切换出口。 需要用户处理配置时只提示运行 sn-ppt-doctor;不要在 Entry 重复变量清单。Doctor 会显示 Hermes/OpenClaw 实际读取的用户级 .env、缺失项和配置模板。

新任务流程

  1. 进入和识别:回显已经进入 Entry。提取角色、受众、场景、页数、语言、附件、 明确的设计要求,以及用户是否明确要求 Static 只交付 HTML。已经提供的信息不再询问。

  2. 路由已有 PPTX:若任务是编辑、优化、续写或模板填充,交给 sn-ppt-edit。若是从零生成,继续本流程。

  3. 推荐三个选择:确定执行深度、输出格式和设计丰富度。只有输出意图确实无法判断且会产生完全不同交付物时才询问;其他情况先给推荐并继续。

  4. 建立固定目录:严格按“唯一目录规则”创建目录和初始 task_pack.json。

  5. 解析附件:对 PDF、DOCX、MD、TXT 执行:

    bash
    python "<ENTRY_SKILL_ROOT>/scripts/parse_user_docs.py" \
      --files <absolute paths...> \
      --output "<deck_dir>/raw_documents.json" \
      --asset-dir "<deck_dir>/source_assets"

    Markdown 表格与本地图片引用、DOCX 表格与内嵌图片、PDF 文本、inherited_images 以及按需生成的 page_visuals 都要保留;page_visuals[].path 必须是 $DECK_DIR/source_assets/ 下的绝对路径,并随raw_documents.json 一起交接。未生成页图时,Figure 页裁切任务必须返回 blocked。一份文件失败时记录到 reference_docs_failed,继续处理其他文件。

  6. 理解全部材料:读取 raw_documents.json 中全部正文、表格和图片索引;必要时分段 阅读,但不得只读开头。用宿主 Agent 原生视觉能力逐张理解相关上传图片和文档内图片, 按上述兼容字段缓存,失败项记录后继续。再生成 document_digest,写 info_pack.json。Story 和出口不得重复理解已有缓存的图片,除非文件变化或当前任务确实 需要重新核对视觉细节。

  7. 启动生成进度工作台:task_pack.json 和 info_pack.json 都已存在后,立即调用 sn-ppt-workbench/scripts/open_workbench.py,始终传入当前任务的绝对 deck_dir 和可用的 同会话智能体参数。启动成功后立即向用户提供返回的 generation_url(固定为 /progress);启动失败或返回 skipped 时简要说明原因并继续生成,不得因此阻塞 Research、Story 或页面生产。不得在此步骤运行 npm、构建 Workbench 或切换任务目录。

  8. 决定外部证据路径:

    • Draft:默认跳过,写 required=false、executor=null、mode=null。用户明确要求核查 某个事实时,可直接用普通搜索完成该核查,但不为 Draft 启动完整 Deep Research。
    • Standard:默认写 required=true、executor=entry、mode=null。不得因为“用户材料 看起来足够”而跳过;只要用户未禁止联网且普通搜索可用,就必须在 Story 前执行至少一次 真实普通搜索。
    • Deep:写 required=true、executor=sn-deep-research;默认 mode=normal,复杂、 多维、争议、高时效或高风险任务使用 heavy。quick / normal / heavy 只属于 sn-deep-research,不用于描述 Standard。
    • 用户明确禁止外部搜索或要求只使用给定材料时,不联网,写 required=false、 executor=null、mode=null 和 skipped_reason=user_forbidden,只做材料内证据审计。
  9. 完成外部证据补充:先按可选能力规则确定普通搜索来源:宿主原生网页搜索可用时 直接使用;否则调用 <PPT_TOOLS_DIR>/scripts/web_search.py。

    • Standard 由 Entry 当前 Agent 做定向搜索,不调用 sn-deep-research,不做 scout、 多维拆解、补研循环或完整研究报告编排。搜索目标只来自用户 query、材料中的时效性风险、 关键事实和会影响叙事的明显缺口;优先官方和一手来源,记录标题、URL、日期、支持的结论 及未解决限制。停止条件是 Story 所需关键证据已经覆盖或缺口已经明确,不为扩写而漫游。 把简洁结果写到 <deck_dir>/research/report.md。
    • Deep 把普通搜索来源、绝对 report_dir=<deck_dir>/research 和当前任务材料交给 sn-deep-research,按 mode=normal|heavy 完整运行。sn-ppt-tools 只作为搜索能力 fallback,不是另一套 Research 流程。
    • 两条路径完成后都把同一个 <deck_dir>/research/report.md 写入 info_pack.research_report 和 task_pack.state.artifacts.research_report,再进入 Story。
    • 原生与内置搜索都不可用时,不伪造 Research,也不阻塞 PPT:把 state.research.required=false、state.research.executor=null、 state.research.skipped_reason=search_unavailable 和 info_pack.document_digest.open_questions 中的事实覆盖限制写清楚,然后直接进入 Story。
    • 搜索能力存在但 Research 本身尚未完成时,仍不得先写正式大纲。
  10. 调用 Story:把同一 deck_dir 交给 sn-ppt-story。Story 读取 query、 info_pack.json、raw_documents.json 和已有 Research,生成唯一 <deck_dir>/outline.md。

  11. 大纲交互:Draft 默认继续生产,同时告知大纲路径;Standard / Deep 展示一行整体 叙事和路径,等待用户修改或确认。继续前重新读取磁盘上的 outline.md,不能使用聊天 中的旧副本。

  12. 出口分发:Story 已完成且当前磁盘 outline.md 已按本档位确认后,按 choices.output 调用唯一对应 Skill:static_html 调用 sn-ppt-standard, dynamic_html 调用 sn-ppt-dazzle,creative 调用 sn-ppt-creative。始终传绝对 deck_dir。不得绕过 Story 把原始 query 直接交给任一出口;三个出口都只做表达与产物生产,不 再研究、重排页面或重写 Story。

  13. 后处理和收尾:Static HTML 默认在页面完成后由 sn-ppt-standard 内置 exporter(scripts/export_pptx/html_to_pptx.mjs)导出 PPTX;该出口必须同时交付 present.html 和 PPTX 两个产物,缺一即技术故障(用户明确要求只要 HTML 时,PPTX 可缺、present.html 仍必须存在)。PPTX 只能由该内置 exporter 生成:禁止用 python-pptx、自写脚本或宿主原生工具替代。Entry 最终把各出口生成的真实产物写回 task_pack.state.artifacts;转换失败保留已有 HTML 产物、状态置 partial 并如实说明,不得另起炉灶补产出或伪造 PPTX 路径。

Show full SKILL.md (100 more words)Show less

恢复规则

当用户提供 deck 目录,或当前目录下存在明确的任务包时:

  1. 读取 task_pack.json、info_pack.json 和磁盘实际文件。
  2. 当前 outline.md 存在时,以磁盘版本为 Story 真相。
  3. Research 报告、outline、页面、渲染图和最终产物存在时,不因状态字段滞后而重做。
  4. 从最早一个“必要产物确实缺失”的阶段继续。
  5. 用户修改 outline 后,只失效 Story 之后受影响的页面及其派生 PPTX;Research 和材料解析不自动重跑;若 HTML、PNG、讲稿、播放器均完整而仅 PPTX 缺失,只重跑对应出口的 exporter。
  6. 不创建 task_pack_v2.json、outline_v2.md 或第二个 deck 目录。

进度反馈

超过约 30 秒的工作必须让用户看到进度。至少在以下边界各回显一句:

  • 已识别任务与三个选择;
  • 已建立 deck_dir;
  • 附件解析开始/完成;
  • 生成进度工作台已启动并提供 /progress,或说明非阻塞的跳过原因;
  • Research 开始/完成或明确跳过;
  • Story 开始/outline.md 已生成;
  • 等待确认或已进入出口;
  • 页面生产进度;页面完成后回显 present.html、PNG、讲稿和播放器的真实路径。
  • 后处理与最终产物;PPTX 失败时保留 HTML、PNG、讲稿和播放器,状态为 partial,不得伪造 PPTX 路径,并把失败原因写入 task_pack.state.last_error。

进度以用户能理解的阶段描述为主,不暴露内部 prompt、模型调用或细碎状态字段。

硬规则

  1. 原有能力没有被明确删除时必须保留。
  2. 不在 Entry 生成页面、图片或视觉方案。
  3. 不允许出口自行搜索或重新决定页序、标题和核心结论。
  4. 不静默切换输出格式或设计档位。
  5. 可选搜索或图像能力失败时最多尝试原生一次、内置一次;随后执行 policy 的无工具路径。
  6. 不用 mock 数字冒充事实;缺口应回到 Research/Story 或明确标示。
  7. 不因 Static 默认的 PPTX 后处理失败删除可用的 HTML、图片或 PPTX。
  8. 不新增外部模型客户端、额外 API 配置、通用状态机或大型调度脚本。
  9. Workbench 启动是生成流程的最佳努力辅助能力;失败不得改变输出选择或中止生成。

© OpenSenseNova, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in skills/sn-ppt-entry of OpenSenseNova/SenseNova-Skills.

  • SKILL.md
  • requirements.txt
  • scripts/parse_user_docs.py
  • scripts/timing_helper.py

Open the folder on GitHubat commit 7838651

Compare with similar skills

SenseNova PPT Entry next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

SenseNova PPT Entry compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
SenseNova PPT Entry this skillOpenSenseNova/SenseNova-Skills5.7k—~2.7kAutomated safety check: NotesMIT
PPT Masterhugohe3/ppt-master58k1 repos~2.5kAutomated safety check: PassMIT
Image to Editable PPTXYuan1z0825/nature-skills47k—~2.5kAutomated safety check: PassMIT
Open Kimi Pptjinwyp/open-ppt-skill1592 repos~5.1kAutomated safety check: PassMIT
McKinsey-Style PPT Designlikaku/Mck-ppt-design-skill297—~2.1kAutomated safety check: PassApache-2.0
AI Image PowerPoint Generatorbytedance/deer-flow84k4 repos~7.1kAutomated safety check: PassMIT

Similar skills

  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    58k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed
  • Image to Editable PPTX

    Yuan1z0825/nature-skills

    Rebuilds slide images, screenshots, scanned PDFs or image-only PPTX files as PowerPoint with editable objects, using a local CLI with per-page manifests and QA.

    47k GitHub stars~2.5k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Open Kimi Ppt

    jinwyp/open-ppt-skill

    Create, edit, replicate, read, and export presentations. An agent skill from jinwyp/open-ppt-skill.

    159 GitHub starsUsed in 2 repos~5.1k tokens
    Documents & OfficeAuto-check passed
  • McKinsey-Style PPT Design

    likaku/Mck-ppt-design-skill

    Builds consultant-style PowerPoint decks from scratch with the MckEngine python-pptx wrapper, through a five-stage flow with scripted quality gates.

    297 GitHub stars~2.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Creates a PowerPoint deck by planning the slide structure, generating one AI image per slide in a chosen visual style, and assembling the images into a PPTX file.

    84k GitHub starsUsed in 4 repos~7.1k tokens
    Documents & OfficeAuto-check passed
  • PPTX Deck Editor

    EveryInc/hands-on-deck

    Reads, edits, creates, merges and visually verifies .pptx decks through one script, deck.py, which applies atomic JSON patches.

    219 GitHub stars~2.9k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

More from OpenSenseNova/SenseNova-Skills

All 36 skills in this repo
  • SN Motion HTML

    OpenSenseNova/SenseNova-Skills

    Builds HTML stories where one continuous camera journey advances with page progress, using researched structure, AI stills, Seedance video clips and browser QA.

    5.7k GitHub stars~2.2k tokensUpdated today
    Auto-check: notes
  • SenseNova PPT Fallback Tools

    OpenSenseNova/SenseNova-Skills

    Fallback scripts for web search, image search and download, and image generation that PPT skills use only when the host agent lacks or fails its own tools.

    5.7k GitHub stars~575 tokensUpdated today
    Auto-check: notes
  • SenseNova PPT Workbench

    OpenSenseNova/SenseNova-Skills

    Opens the PPT Workbench web editor for an existing SenseNova HTML slide deck so you can preview, inspect and visually edit it without regenerating.

    5.7k GitHub stars~2.5k tokensUpdated today
    Auto-check: notes
  • SenseNova PPT Creative Renderer

    OpenSenseNova/SenseNova-Skills

    Turns an approved slide outline into a full-page image for every slide, one 16:9 PNG per page, and optionally packages the set into a PPTX.

    5.7k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • China Market Open Data Search

    OpenSenseNova/SenseNova-Skills

    Researches Chinese market, macro, trade, procurement, listed-company and regulatory information from free official sources that need no sign-up or API key.

    5.7k GitHub stars~954 tokensUpdated today
    Auto-check: notes
  • SenseNova Image Base Tools

    OpenSenseNova/SenseNova-Skills

    Low-level SenseNova tools for image generation, image editing, image recognition with a VLM and text optimization with an LLM, meant to be called by higher-level skills rather than directly.

    5.7k GitHub stars~3.2k tokensUpdated today
    Auto-check passed

Questions about SenseNova PPT Entry

What does SenseNova PPT Entry do?

Entry point for SenseNova presentation generation: creates a task folder, picks depth, output format and design richness, and routes to the right PPT skill. sn-ppt-entry is the entry point for SenseNova's presentation skills.md before handing off by output choice to sn-ppt-standard, sn-ppt-dazzle or sn-ppt-creative.

When should I use SenseNova PPT Entry?

SenseNova PPT Entry fits situations like: creating a presentation or slide deck from a query and optional files; resuming an existing SenseNova presentation task; choosing between draft, standard and deep generation; routing a request to static HTML, dynamic HTML or creative output.

How do I install SenseNova PPT Entry in Claude Code?

Run `npx skills add OpenSenseNova/SenseNova-Skills --skill sn-ppt-entry -a claude-code`. Or copy the skill folder (skills/sn-ppt-entry in OpenSenseNova/SenseNova-Skills) into .claude/skills/sn-ppt-entry in your project. Claude Code loads it when a task matches its description.

How do I install SenseNova PPT Entry in Codex?

Run `npx skills add OpenSenseNova/SenseNova-Skills --skill sn-ppt-entry -a codex`. Or copy the skill folder (skills/sn-ppt-entry in OpenSenseNova/SenseNova-Skills) into .agents/skills/sn-ppt-entry in your project. Codex loads it when a task matches its description.

Can I use SenseNova PPT Entry in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenSenseNova/SenseNova-Skills --skill sn-ppt-entry -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sn-ppt-entry, .gemini/skills/sn-ppt-entry, .github/skills/sn-ppt-entry and .opencode/skills/sn-ppt-entry in your project.

What does SenseNova PPT Entry need to run?

Going by SKILL.md and its folder, SenseNova PPT Entry needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python with the packages listed in requirements.txt.

Does SenseNova PPT Entry access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is SenseNova PPT Entry safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does SenseNova PPT Entry use?

SenseNova PPT Entry is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does SenseNova PPT Entry use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to SenseNova PPT Entry?

Skills that share tags, products or a category with SenseNova PPT Entry: PPT Master (hugohe3/ppt-master, 58k stars), Image to Editable PPTX (Yuan1z0825/nature-skills, 47k stars), Open Kimi Ppt (jinwyp/open-ppt-skill, 159 stars) and McKinsey-Style PPT Design (likaku/Mck-ppt-design-skill, 297 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains SenseNova PPT Entry?

OpenSenseNova (a GitHub organization) maintains it in OpenSenseNova/SenseNova-Skills, which has 5,747 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 9, 2026.

Source: OpenSenseNova/SenseNova-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.