← 返回 Skills 市场
1921
总下载
2
收藏
2
当前安装
13
版本数
在 OpenClaw 中安装
/install pod-cog
功能描述
AI podcast production powered by CellCog. Full podcast episodes from a single prompt — multi-voice dialogue, intro/outro music, automatic editing to finished...
安全使用建议
This skill appears internally consistent: it uses the CellCog API to produce podcast assets and only asks for a single CELLCOG_API_KEY and python3. Before installing: 1) Confirm you trust CellCog (https://cellcog.ai), check their privacy, data retention, and billing policies because audio and transcripts may be sent to their servers. 2) Provide a scoped API key if possible, and avoid putting high-privilege credentials in the same environment. 3) Ensure the runtime has the cellcog Python package (or the platform will need to install it); the SKILL.md declares 'cellcog' but has no install step. 4) If you want to limit autonomous runs, restrict or monitor the agent's ability to invoke skills or review logs/usage alerts on your CellCog account. 5) Test with non-sensitive/sample content first, and rotate/remove the API key when no longer needed.
功能分析
Type: OpenClaw Skill
Name: pod-cog
Version: 1.0.12
The pod-cog skill bundle is a documentation-heavy integration for a podcast production service called CellCog. The SKILL.md file provides comprehensive instructions and prompt templates for generating scripts, show notes, and full audio episodes using an external 'cellcog' dependency. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the bundle functions as a standard wrapper for an AI-driven content generation tool.
能力标签
能力评估
Purpose & Capability
Name/description (podcast production with CellCog) matches the declared requirements: python3 and a CELLCOG_API_KEY. The SKILL.md shows calls to a CellCog client and describes audio/script generation features that reasonably require the service API.
Instruction Scope
SKILL.md instructs the agent to call the CellCog SDK/API and to produce scripts, audio, and related artifacts. It does not direct the agent to read unrelated local files, other secret env vars, or exfiltrate data to unknown endpoints. It references the 'cellcog' SDK and shows example client.create_chat calls — behaviour stays within the stated purpose.
Install Mechanism
This is an instruction-only skill with no install spec (low risk). SKILL.md declares a dependency 'cellcog' but provides no install instructions; runtime will require the cellcog package to already be available in the environment or the agent runtime to provide it. This is an operational mismatch (not a security red flag) that could cause execution failures.
Credentials
Only a single env var (CELLCOG_API_KEY) is required, which is appropriate for an integration that calls an external API. No unrelated credentials, system paths, or broad secrets are requested.
Persistence & Privilege
Skill does not request always:true and uses platform defaults for invocation. It does not request system-wide changes or access to other skills' configs. Allowing autonomous invocation is the platform default and is not by itself a concern here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install pod-cog - 安装完成后，直接呼叫该 Skill 的名称或使用
/pod-cog触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.12
- Added system requirements to metadata: now specifies required binaries (`python3`) and environment variable (`CELLCOG_API_KEY`).
- No changes to functionality or usage instructions.
v1.0.11
- Shortened and simplified the skill description for clarity.
- Clarified the usage instructions, specifying the difference between OpenClaw and other agent providers.
- No code or functional changes—documentation only.
- Content and feature list remain unchanged.
v1.0.10
- Updated skill description for greater clarity on features and output formats.
- Improved Python usage example to include explicit import and agent provider setup.
- Enhanced emphasis on AI, frontier voice quality, and top DeepResearch benchmark ranking.
- Added audiogram and interview prep to skill description for completeness.
- No changes made to logic or core functionality; documentation only.
v1.0.9
- Updated skill description and usage instructions for clarity.
- Consolidated and simplified the "How to Use" and prerequisites sections.
- Removed redundant explanations and trimmed repeated detail.
- Clarified usage examples for different agent environments.
- No core functionality changes; documentation only.
v1.0.8
v1.0.8 — Expanded documentation and clearer feature descriptions
- SKILL.md completely rewritten for clarity, depth, and examples covering all podcast production features
- Added concrete prompt examples and use cases for episode scripts, show notes, interview prep, audiograms, and planning
- Clarified supported podcast formats, content types (pre/post production), and recommended chat modes for various scenarios
- Updated description to highlight voice quality, research depth, and #1 ranking on DeepResearch Bench (Apr 2026)
- No code or logic changes; documentation only
v1.0.7
- Updated description for clarity and broader use (includes general audio and dialogue production, not just podcasts).
- Shortened and streamlined documentation for faster onboarding.
- Added internal feature summary: multi-voice dialogue, music generation, automated audio assembly, and deep research.
- Clarified recommended chat mode (`"agent"`) for podcast/audio production.
- Listed related skills for cross-referencing (audio-cog, music-cog).
- Removed long prompt examples and detailed production guidance to focus on core usage and capabilities.
v1.0.6
**Improved OpenClaw agent instructions and clarified code examples.**
- Added guidance for using OpenClaw agents with notify_session_key for long-running podcast tasks.
- Separated code examples for OpenClaw agents vs. blocking agents to improve clarity.
- Minor cleanup and wording changes to SDK/API reference sections.
- No changes to feature set or functionality.
v1.0.5
pod-cog 1.0.5 Changelog
- Updated SKILL.md to provide a more concise and clear code example for the quick start, replacing the older example with a simplified usage pattern.
- Clarified instructions to direct users to the main cellcog skill for full SDK reference, delivery modes, and API features.
- Removed legacy SDK example using `notify_session_key` and polling guidance, focusing documentation on the latest recommended workflow.
- Added emphasis on consulting the cellcog mothership skill for advanced details such as timeouts and file handling.
v1.0.4
- Updated DeepResearch Bench achievement from February 2026 to April 2026 in the description and feature list.
- No functional or usage changes; documentation date reference refreshed.
v1.0.3
pod-cog v1.0.3
- Updated SKILL.md description for conciseness and clarity.
- Added supported operating systems (darwin, linux, windows) to metadata.
- Added project homepage link.
- No core functionality changes. Documentation improvements only.
v1.0.2
pod-cog 1.0.2
- Added author and dependencies fields to SKILL.md metadata for clarity and compatibility.
- No changes to functionality or features in this release.
v1.0.1
- Adds new positioning: focuses on podcast quality — content depth, natural-sounding multi-voice delivery, and fully automated music/mixing.
- Highlights CellCog's #1 DeepResearch Bench ranking (Feb 2026) and production benchmarks.
- Updates skill description and introduction for clarity and impact.
- No changes to features or SDK usage; all previously supported podcast content creation still applies.
- Documentation is reworded, reorganized, and streamlined for easier reading.
v1.0.0
- Initial release of pod-cog: AI-powered podcast creation with CellCog.
- Supports episode scripts, show notes, audiograms, interview prep, transcripts, and planning.
- Includes detailed example prompts for solo, interview, panel, and narrative podcasts.
- Covers pre-production, production, post-production, and promotional podcast content types.
- Requires the CellCog mothership skill for SDK setup and API calls.
元数据
常见问题
Pod Cog 是什么？
AI podcast production powered by CellCog. Full podcast episodes from a single prompt — multi-voice dialogue, intro/outro music, automatic editing to finished... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1921 次。
如何安装 Pod Cog？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pod-cog」即可一键安装，无需额外配置。
Pod Cog 是免费的吗？
是的，Pod Cog 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Pod Cog 支持哪些平台？
Pod Cog 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, windows）。
谁开发了 Pod Cog？
由 CellCog（@nitishgargiitd）开发并维护，当前版本 v1.0.12。
推荐 Skills