Raccoon Ppt

What it does

When your agent uses it

• The user wants to create a brand-new full PPT deck
• Secondarily use it to continue a PPT generation task
• Check the result of an existing PPT task

Example prompts

• “/raccoon-ppt”

Requirements

• Python 3
• A credential in RACCOON_API_TOKEN
• A credential in CLEAN_TOKEN

Workflow steps

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

1. 1用自然语言交互，不暴露技术细节（如 job_id）
2. 2必须使用 skill 自带脚本，不要自己写 curl 或 Python 代码
3. 3waiting_user_input 是正常状态，把 API 返回的 question 转成自然语言问用户

What it can do on your machine

Read from SKILL.md and the folder at commit 037b6d6. 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 1 file 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

  Hosts in commands or code, which the agent is likely to contact:

  • xiaohuanxiong.com

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • RACCOON_API_TOKEN
  • CLEAN_TOKEN

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

Context cost

Raccoon Ppt loads about 1.5k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 277 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~100

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.9k

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

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 SenseTime-Copilot/raccoon-ppt-skill at commit 037b6d6, republished under its Apache-2.0 licence (© SenseTime-Copilot). 277 words, ~1,464 tokens.

name

raccoon-ppt

description

Raccoon (小浣熊) PPT generation skill powered by the PPT OpenAPI. Create PPT decks from a natural-language topic. Primarily use this skill when the user wants to create a brand-new full PPT deck; secondarily use it to continue a PPT generation task or check the result of an existing PPT task. Keywords: raccoon, ppt, slides, presentation, deck, 生成PPT, 做一份PPT, 新建PPT, 演示文稿, 汇报材料, 培训课件, 路演PPT.

homepage

https://xiaohuanxiong.com

source ~/.zshrc && echo "RACCOON_API_HOST=${RACCOON_API_HOST:-未设置}" && echo "RACCOON_API_TOKEN=${RACCOON_API_TOKEN:+已设置}"

export RACCOON_API_HOST="https://xiaohuanxiong.com"
export RACCOON_API_TOKEN="your-token-here"

CLEAN_TOKEN=$(echo "$RACCOON_API_TOKEN" | tr -d '\n\r')
RACCOON_API_TOKEN="$CLEAN_TOKEN" python3 scripts/main.py ...

用户："帮我做一份AI编程工具对比的PPT"
助手：你打算以什么身份来讲？（研究人员 / 产品经理 / 培训师）
用户："研究人员"
助手：在什么场合使用？（学术演讲 / 内部分享 / 客户演示）
用户："内部分享"
助手：给谁看？（公司内部 / 技术团队 / 管理层）
用户："技术团队"
助手：好的，开始生成...

source ~/.zshrc && CLEAN_TOKEN=$(echo "$RACCOON_API_TOKEN" | tr -d '\n\r') && \
cd ~/.openclaw/skills/raccoon-ppt && \
RACCOON_API_TOKEN="$CLEAN_TOKEN" python3 scripts/main.py auth-check

source ~/.zshrc && CLEAN_TOKEN=$(echo "$RACCOON_API_TOKEN" | tr -d '\n\r') && \
cd ~/.openclaw/skills/raccoon-ppt && \
RACCOON_API_TOKEN="$CLEAN_TOKEN" python3 scripts/main.py generate \
  --prompt "帮我做一份AI Agent在企业落地实践的培训PPT" \
  --role "培训师" \
  --scene "培训教学" \
  --audience "公司内部（上级/同事/下属）" \
  --wait-mode short

python3 scripts/main.py find-recent-job --statuses waiting_user_input

source ~/.zshrc && CLEAN_TOKEN=$(echo "$RACCOON_API_TOKEN" | tr -d '\n\r') && \
cd ~/.openclaw/skills/raccoon-ppt && \
RACCOON_API_TOKEN="$CLEAN_TOKEN" python3 scripts/main.py generate \
  --prompt "重点展开多Agent协作、权限治理和评估体系" \
  --resume-state <state-file>

用户：帮我做一份介绍 AI 编程工具的 PPT
助手：好的。你打算以什么身份来讲？（研究人员 / 产品经理 / 技术专家）
用户：技术专家
助手：在什么场合使用？（技术分享 / 产品发布 / 内部培训）
用户：技术分享
助手：给谁看？（开发者 / 公司内部 / 客户）
用户：开发者
助手：[执行 generate 命令]
      任务已创建，预计 10-120 分钟完成。我会定期检查进度并通知你。

[2 分钟后，API 返回 waiting_user_input 状态]
助手：小浣熊想了解更多细节：你希望重点对比哪些工具？（GitHub Copilot、Cursor、Claude 等）
用户：重点讲 Cursor 和 GitHub Copilot
助手：[执行 generate --resume-state 命令]
      已补充信息，继续生成中...

[30 分钟后]
用户：PPT 生成好了吗？
助手：[执行 check-job 命令]
      PPT 已生成完成！正在下载...
      [下载并打开文件]
      已保存到 ~/.openclaw/skills/raccoon-ppt/output/AI编程工具介绍.pptx

© SenseTime-Copilot, Apache-2.0. 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 7 other files (scripts, references) in the repository root of SenseTime-Copilot/raccoon-ppt-skill.

• SKILL.md
• .gitignore
• LICENSE
• README.md
• agents/openai.yaml
• references/API_REFERENCE.md
• references/CHEATSHEET.md
• scripts/main.py

Open the folder on GitHubat commit 037b6d6