Agent skill

SenseNova PPT Fallback Tools

by OpenSenseNova in 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.

MITAuto-check: notesDocuments & Office

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

Install SenseNova PPT Fallback Tools

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

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

GitHub CLI
$ gh skill install OpenSenseNova/SenseNova-Skills sn-ppt-tools --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-tools .claude/skills/sn-ppt-tools && 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-tools
GitHub stars
5.7k
Token cost
~575 tokens
SKILL.md length
106 words
Files
7 (incl. scripts, references)
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 3 steps: 设置了 SN_PPT_ENV_FILE 时读取该文件; → OpenClaw 读取 ~/.openclaw/.env; → 其他环境默认读取 ~/.hermes/.env。
  • A PPT skill needs web search and the host has no search tool
  • SKILL.md covers 持久配置, 普通搜索, 图片搜索与下载 and 图片生成, plus 1 more section
  • Runs Python scripts from its folder; calls python3; needs SN_PPT_SEARCH_API_KEY and SERPER_API_KEY

What it does

A Chinese-language helper bundle for PPT skills, not a standalone content workflow. The host agent's equivalent native tool always comes first, and these scripts run only if that capability is absent or a real call has failed. The agent reads references/capability-policy.md before calling anything. Scripts cover web search, image search, image download through fetch_image.py and image generation.

Configuration comes from environment variables loaded from a user-level .env file, chosen by SN_PPT_ENV_FILE or defaulting to ~/.openclaw/.env under OpenClaw and ~/.hermes/.env elsewhere, with variables already in the process taking priority. Secrets must never go into the skill folder, workspace, command line, prompts or task pack. Search uses Serper-style endpoints and image generation uses an OpenAI or SenseNova compatible images/generations call. Scripts print one JSON line with a status of ok, unavailable or failed, write images only inside the given deck directory, and do not retry a failed capability in a loop.

When your agent uses it

  • A PPT skill needs web search and the host has no search tool
  • Downloading a chosen image into a deck folder
  • Generating slide images when native image generation fails

Example prompts

  • “Search the web for recent figures on this slide topic using the fallback tool.”
  • “Generate a background image for page one from its prompt file.”

Requirements

  • Python 3, to run the scripts
  • API keys and endpoint URLs set in a user-level .env file or the environment
  • A deck directory given as an absolute path

Workflow steps

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

  1. 设置了 SN_PPT_ENV_FILE 时读取该文件;
  2. OpenClaw 读取 ~/.openclaw/.env;
  3. 其他环境默认读取 ~/.hermes/.env。

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

    Shell commands in SKILL.md call:

    • python3

    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 these keys or tokens, usually read from environment variables:

    • SN_PPT_SEARCH_API_KEY
    • SERPER_API_KEY
    • SN_PPT_WEB_SEARCH_API_KEY
    • SN_PPT_IMAGE_SEARCH_API_KEY
    • SN_PPT_IMAGE_GEN_API_KEY
    • SN_IMAGE_GEN_API_KEY
    • SN_API_KEY

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

Context cost

SenseNova PPT Fallback Tools loads about 575 tokens when it runs, and up to ~1.3k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 106 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~575
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.3k

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:19
    四个脚本每次启动都会自动加载一个用户级 `.env`:
  • NoteMentions a .env fileSKILL.md:22
    2. OpenClaw 读取 `~/.openclaw/.env`;
  • NoteMentions a .env fileSKILL.md:23
    3. 其他环境默认读取 `~/.hermes/.env`。
  • NoteMentions a .env fileSKILL.md:25
    已有进程环境变量优先,`.env` 只补充缺失项。不要把 secret 写进 Skill 目录、workspace、

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). 106 words, ~575 tokens.

Download SKILL.mdSave it as .claude/skills/sn-ppt-tools/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
sn-ppt-tools
description
Use when another PPT Skill needs web search, image search or download, or image generation and the host Agent's equivalent native capability is absent or has failed.
metadata.project
SenseNova-Skills
metadata.tier
0
metadata.category
infrastructure
metadata.user_visible
false

sn-ppt-tools

这是 PPT Skill 整包自带的备用工具,不是独立内容生产流程。调用前先读 references/capability-policy.md。宿主 Agent 的等价原生工具始终优先;只有原生能力 不存在或一次实际调用确认不可用时,才调用这里的脚本。

持久配置

四个脚本每次启动都会自动加载一个用户级 .env:

  1. 设置了 SN_PPT_ENV_FILE 时读取该文件;
  2. OpenClaw 读取 ~/.openclaw/.env;
  3. 其他环境默认读取 ~/.hermes/.env。

已有进程环境变量优先,.env 只补充缺失项。不要把 secret 写进 Skill 目录、workspace、 命令行、prompt 或 task pack。完整模板和缺失项检查通过 sn-ppt-doctor 查看。

普通搜索

bash
python3 "$PPT_TOOLS_DIR/scripts/web_search.py" "QUERY" --num 10

配置:

  • URL:SN_PPT_WEB_SEARCH_URL;否则 SN_PPT_SEARCH_BASE_URL / SERPER_BASE_URL 加 /search。
  • Key:SN_PPT_WEB_SEARCH_API_KEY -> SN_PPT_SEARCH_API_KEY -> SERPER_API_KEY。

图片搜索与下载

bash
python3 "$PPT_TOOLS_DIR/scripts/image_search.py" "QUERY" --num 10

python3 "$PPT_TOOLS_DIR/scripts/fetch_image.py" \
  "https://example.com/image.png" \
  --deck-dir "$DECK_DIR" \
  --output "assets/image.png" \
  --referer "https://example.com/source-page"

图片搜索配置:

  • URL:SN_PPT_IMAGE_SEARCH_URL;否则 SN_PPT_SEARCH_BASE_URL / SERPER_BASE_URL 加 /images。
  • Key:SN_PPT_IMAGE_SEARCH_API_KEY -> SN_PPT_SEARCH_API_KEY -> SERPER_API_KEY。

先根据搜索元数据选择候选,再下载选中的图片。不得把远程 URL 直接留在最终 deck。

图片生成

bash
python3 "$PPT_TOOLS_DIR/scripts/image_generate.py" \
  --prompt-file "$DECK_DIR/pages/page_001.prompt.txt" \
  --deck-dir "$DECK_DIR" \
  --output "pages/page_001.png" \
  --size "2752x1536"

配置:

  • URL:SN_PPT_IMAGE_GEN_URL;否则 SN_IMAGE_GEN_BASE_URL / SN_BASE_URL 加 /images/generations。
  • Key:SN_PPT_IMAGE_GEN_API_KEY -> SN_IMAGE_GEN_API_KEY -> SN_API_KEY。
  • Model:SN_PPT_IMAGE_GEN_MODEL -> SN_IMAGE_GEN_MODEL。

只支持 OpenAI/SenseNova 兼容的同步 POST /images/generations 协议,响应可以是 data[].url 或 data[].b64_json。不在这里扩展其他 provider。

输出与失败

  • 成功输出单行 JSON,status 为 ok。
  • 缺少配置输出 status=unavailable,退出码为 2。
  • 请求或落盘失败输出 status=failed,退出码为 1。
  • 所有图片只能写入调用方给定的绝对 DECK_DIR 内。
  • Key 不通过命令行传递,不写入输出、日志、task pack 或 deck 文件。
  • 同一能力调用失败后不循环重试;由调用 Skill 按 policy 继续无工具路径。

© 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 6 other files (scripts, references) in skills/sn-ppt-tools of OpenSenseNova/SenseNova-Skills.

  • SKILL.md
  • references/capability-policy.md
  • scripts/env_config.py
  • scripts/fetch_image.py
  • scripts/image_generate.py
  • scripts/image_search.py
  • scripts/web_search.py

Open the folder on GitHubat commit 7838651

Compare with similar skills

SenseNova PPT Fallback Tools 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 Fallback Tools compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
SenseNova PPT Fallback Tools this skillOpenSenseNova/SenseNova-Skills5.7k—~575Automated safety check: NotesMIT
Image-Based PPT Deck Generatorningzimu/codex-ppt-skill6.5k—~2.6kAutomated safety check: NotesMIT
Slide Deck GeneratorJimLiu/baoyu-skills26k5 repos~5.8kAutomated safety check: PassMIT
Slide Deck Image GeneratorSpaceZephyr/design-buddy175—~6.5kAutomated safety check: PassNone
Nano BananaEvoScientist/EvoSkills4762 repos~3.5kAutomated safety check: PassApache-2.0
Gpt Image Slide Planhumantonylee/future-slide150—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • Image-Based PPT Deck Generator

    ningzimu/codex-ppt-skill

    Builds visually unified PowerPoint decks from articles, reports, papers, notes or outlines, with every slide generated as a full 16:9 image and assembled into a .pptx.

    6.5k GitHub stars~2.6k tokensUpdated 7 days ago
    Documents & OfficeAuto-check: notes
  • Slide Deck Generator

    JimLiu/baoyu-skills

    Turns source content into a deck of slide images: it writes an outline with style instructions, then renders each slide as its own image.

    26k GitHub starsUsed in 5 repos~5.8k tokens
    Documents & OfficeAuto-check passed
  • Slide Deck Image Generator

    SpaceZephyr/design-buddy

    Turns written content into designed slide images from an outline, merges them into PPTX or PDF, and can borrow styles from a registry of brand design systems.

    175 GitHub stars~6.5k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Nano Banana

    EvoScientist/EvoSkills

    Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing.

    476 GitHub starsUsed in 2 repos~3.5k tokens
    Documents & OfficeAuto-check passed
  • Gpt Image Slide Plan

    humantonylee/future-slide

    Persuasive GPT image deck-planning skill. An agent skill from humantonylee/future-slide.

    150 GitHub stars~2.6k tokensUpdated 4 mo ago
    Documents & OfficeAuto-check passed
  • Generates branded slide deck images from written content, with a content analysis step, a layout catalog and scripts that merge the slides into PowerPoint or PDF.

    108 GitHub stars~1.1k tokensUpdated 15 days 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 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
  • SenseNova PPT Entry

    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.

    5.7k GitHub stars~2.7k tokensUpdated today
    Auto-check: notes
  • 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 Fallback Tools

What does SenseNova PPT Fallback Tools do?

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. A Chinese-language helper bundle for PPT skills, not a standalone content workflow. The host agent's equivalent native tool always comes first, and these scripts run only if that capability is absent or a real call has failed.

When should I use SenseNova PPT Fallback Tools?

SenseNova PPT Fallback Tools fits situations like: A PPT skill needs web search and the host has no search tool; downloading a chosen image into a deck folder; generating slide images when native image generation fails.

How do I install SenseNova PPT Fallback Tools in Claude Code?

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

How do I install SenseNova PPT Fallback Tools in Codex?

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

Can I use SenseNova PPT Fallback Tools 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-tools -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-tools, .gemini/skills/sn-ppt-tools, .github/skills/sn-ppt-tools and .opencode/skills/sn-ppt-tools in your project.

What does SenseNova PPT Fallback Tools need to run?

Going by SKILL.md and its folder, SenseNova PPT Fallback Tools needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named SN_PPT_SEARCH_API_KEY, SERPER_API_KEY, SN_PPT_WEB_SEARCH_API_KEY and SN_PPT_IMAGE_SEARCH_API_KEY. Our summary lists: Python 3, to run the scripts; API keys and endpoint URLs set in a user-level .env file or the environment; A deck directory given as an absolute path.

Does SenseNova PPT Fallback Tools 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 Fallback Tools 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 Fallback Tools use?

SenseNova PPT Fallback Tools 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 Fallback Tools use?

About 575 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 749 tokens, read only when the agent opens those files.

What are the alternatives to SenseNova PPT Fallback Tools?

Skills that share tags, products or a category with SenseNova PPT Fallback Tools: Image-Based PPT Deck Generator (ningzimu/codex-ppt-skill, 6.5k stars), Slide Deck Generator (JimLiu/baoyu-skills, 26k stars), Slide Deck Image Generator (SpaceZephyr/design-buddy, 175 stars) and Nano Banana (EvoScientist/EvoSkills, 476 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains SenseNova PPT Fallback Tools?

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.