Dive Into LangGraph
luochang212/dive-into-langgraph
A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search.
PenShot 项目开发 Skill。用于修改或审查 Agent、LangGraph 工作流、任务生命周期、记忆/RAG、配置、REST、MCP、CLI、测试和项目文档；先核实源码与工具配置，再按现有架构实施并验证。
Install Penshot
$ npx skills add neopen/story-shot-agent --skill penshot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install neopen/story-shot-agent penshot --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/neopen/story-shot-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/penshot .claude/skills/penshot && rm -rf skills-srcUse ~/.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/
Install the "penshot" agent skill from https://github.com/neopen/story-shot-agent/tree/main/.agents/skills/penshot into .claude/skills/penshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "penshot", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/neopen/story-shot-agent/tree/main/.agents/skills/penshotType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add neopen/story-shot-agent --skill penshot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install neopen/story-shot-agent penshot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/neopen/story-shot-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/penshot .agents/skills/penshot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "penshot" agent skill from https://github.com/neopen/story-shot-agent/tree/main/.agents/skills/penshot into .agents/skills/penshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "penshot", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add neopen/story-shot-agent --skill penshot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install neopen/story-shot-agent penshot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/neopen/story-shot-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/penshot .cursor/skills/penshot && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "penshot" agent skill from https://github.com/neopen/story-shot-agent/tree/main/.agents/skills/penshot into .cursor/skills/penshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "penshot", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/neopen/story-shot-agent.git --path .agents/skills/penshot--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add neopen/story-shot-agent --skill penshot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install neopen/story-shot-agent penshot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/neopen/story-shot-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/penshot .gemini/skills/penshot && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "penshot" agent skill from https://github.com/neopen/story-shot-agent/tree/main/.agents/skills/penshot into .gemini/skills/penshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "penshot", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install neopen/story-shot-agent penshotInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add neopen/story-shot-agent --skill penshot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/neopen/story-shot-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/penshot .github/skills/penshot && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "penshot" agent skill from https://github.com/neopen/story-shot-agent/tree/main/.agents/skills/penshot into .github/skills/penshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "penshot", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add neopen/story-shot-agent --skill penshot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install neopen/story-shot-agent penshot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/neopen/story-shot-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/penshot .opencode/skills/penshot && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "penshot" agent skill from https://github.com/neopen/story-shot-agent/tree/main/.agents/skills/penshot into .opencode/skills/penshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "penshot", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
penshot- GitHub stars
- 217
- Token cost
- ~547 tokens
- SKILL.md length
- 135 words
- Files
- 2 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
PenShot 项目开发 Skill。用于修改或审查 Agent、LangGraph 工作流、任务生命周期、记忆/RAG、配置、REST、MCP、CLI、测试和项目文档；先核实源码与工具配置，再按现有架构实施并验证。
- Works in 5 steps: 先读取相关源码、测试和配置，再判断实现位置。 → 按事实来源优先级核实现状，区分已确认、设计目标和待验证内容。 → 复用现有模块和扩展点，保持… → …
- Tasks that involve AI video generation
- SKILL.md covers 适用场景, 工作流程, 事实来源优先级 and 当前架构入口, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Penshot is an agent skill from neopen/story-shot-agent. PenShot 项目开发 Skill。用于修改或审查 Agent、LangGraph 工作流、任务生命周期、记忆/RAG、配置、REST、MCP、CLI、测试和项目文档；先核实源码与工具配置，再按现有架构实施并验证。
Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/project_understanding.md`).
It sits in AI & LLM Engineering, covering AI video generation, Building AI agents and Retrieval-augmented generation. It works with LangGraph, Model Context Protocol and Python. The repository describes itself as: 剧本分镜智能体（PenShot）：电影/动漫/短剧/小说→分镜片段→视频提示词。基于 LLM 通过 LangGraph+LlamaIndex实现任意格式剧本的自动解析，生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致，支持 MCP/REST API/Function Calls/A2A…. The licence is MIT.
When your agent uses it
- Tasks that involve AI video generation
- Tasks that involve Building AI agents
- Tasks that involve Retrieval-augmented generation
Example prompts
- “/penshot”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 先读取相关源码、测试和配置，再判断实现位置。
- 按事实来源优先级核实现状，区分已确认、设计目标和待验证内容。
- 复用现有模块和扩展点，保持 task、workflow、agent、knowledge 分层边界。
- 只修改需求所需范围，不创建重复规范、虚构配置 schema 或无依据兼容层。
- 按变更范围运行测试和质量检查，报告实际执行状态。
What it can do on your machine
Read from SKILL.md and the folder at commit ec74762. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Penshot loads about 547 tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 29 tokens; SKILL.md has 135 words of instructions outside code blocks.
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:66
入 API key、token、Authorization header、真实 `.env` 内容或私有凭据。
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from neopen/story-shot-agent at commit ec74762, republished under its MIT licence (© neopen). 135 words, ~547 tokens.
Download SKILL.mdSave it as
.claude/skills/penshot/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- penshot
- description
- PenShot 项目开发 Skill。用于修改或审查 Agent、LangGraph 工作流、任务生命周期、记忆/RAG、配置、REST、MCP、CLI、测试和项目文档；先核实源码与工具配置，再按现有架构实施并验证。
PenShot 项目开发 Skill
适用场景
使用本 Skill 处理以下任务：
- 修改 Agent、工作流节点、任务生命周期、记忆/RAG、配置、REST、MCP 或 CLI。
- 新增或调整测试、开发文档和质量检查。
- 排查 LangGraph 状态流转、任务恢复、外部 LLM/Redis/Chroma 集成问题。
工作流程
- 先读取相关源码、测试和配置，再判断实现位置。
- 按事实来源优先级核实现状，区分已确认、设计目标和待验证内容。
- 复用现有模块和扩展点，保持 task、workflow、agent、knowledge 分层边界。
- 只修改需求所需范围，不创建重复规范、虚构配置 schema 或无依据兼容层。
- 按变更范围运行测试和质量检查，报告实际执行状态。
事实来源优先级
出现冲突时按以下顺序核实，不把旧文档当作实现事实：
- 当前源码与测试。
pyproject.toml。.pre-commit-config.yaml。- 根目录
AGENTS.md。 - 本目录
references/中的按需参考资料。 - 其他设计文档、示例和历史报告。
文档中的结论应区分：已从当前代码确认、设计目标、待验证。
当前架构入口
- 接入层：
src/penshot/api/、http_server.py、mcp_server.py、cli.py。 - 任务层：
src/penshot/neopen/task/，负责提交、排队、生命周期、仓储和工作流实例注册。 - 工作流层：
src/penshot/neopen/agent/workflow/，负责状态、节点、条件路由、检查点和输出。 - Agent 层：
src/penshot/neopen/agent/，遵循现有基类、rule/llm 实现、factory 和 wrapper 结构。 - 知识与记忆层：
src/penshot/neopen/knowledge/，负责记忆、向量检索和模板知识。 - 测试：
tests/，按当前测试目录和pyproject.toml配置选择范围。
需要详细模块导航时，按需读取 references/project_understanding.md。该文件是有时效性的参考资料，不替代当前源码、测试和项目配置。
变更联动要求
- 新增工作流阶段时，同时检查
PipelineNode、节点注册、边、条件决策、状态类型和对应测试。 - 新增 Agent 时先复用现有 Agent 工厂和 wrapper，不套用与当前源码无关的通用模板。
- 修改任务状态时检查生命周期服务、仓储、处理器、恢复逻辑和状态测试。
- 修改配置时检查 YAML、环境变量映射、Pydantic Settings 与运行时
ShotConfig。 - 修改公开接口时检查 SDK、REST、MCP、CLI 及其序列化模型的影响。
工具链与验证
- Python 版本以
pyproject.toml的requires-python为准。 - Python 检查以
.pre-commit-config.yaml为准：Ruff、Ruff format、mypy；Markdown 使用 mdformat。 - 测试使用 pytest；异步测试行为以
pyproject.toml的 asyncio 配置为准。 - 先运行受影响范围的测试，再根据变更范围运行 lint、类型检查或完整检查。
- 报告结果时明确区分已执行通过、执行失败、未执行和因外部依赖无法验证。
安全与边界
- 不在共享文件、日志、测试输出或文档中写入 API key、token、Authorization header、真实
.env内容或私有凭据。 - 不把设计目标、历史报告、示例配置或未执行的检查写成当前能力或测试结果。
- 涉及真实 LLM、Redis、Chroma、部署、数据清理或其他外部副作用时，先核实环境和操作范围。
- 只修改完成需求所需的范围，不创建未经仓库支持的配置 schema、自动化 hook 或兼容性层。
规范职责边界
- 本 Skill：负责 PenShot 任务的工作流程、架构导航和验证要求。
- 根目录
AGENTS.md：负责所有会话通用的项目总览、命令和协作约定。 pyproject.toml：负责 Python 版本、依赖、pytest 和工具配置。.pre-commit-config.yaml：负责实际运行的格式化、lint、类型检查和其他 hook。- 当前源码与测试：负责实现和行为事实。
© neopen, 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 1 other file (references) in .agents/skills/penshot of neopen/story-shot-agent.
- SKILL.md
- references/project_understanding.md
Open the folder on GitHubat commit ec74762
Compare with similar skills
Penshot 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Penshot this skillneopen/story-shot-agent | 217 | — | ~547 | Automated safety check: Notes | MIT | |
| Dive Into LangGraphluochang212/dive-into-langgraph | 457 | — | ~837 | Automated safety check: Notes | Custom licence | |
| Tool Designagentailor/fullstack-langgraph-nextjs-agent | 132 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Strandsstrands-agents/harness-sdk | 8.7k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Agent Squad Python Guide2FastLabs/agent-squad | 7.8k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | |
| Add Example AgentGetBindu/Bindu | 10k | — | ~1.1k | Automated safety check: Notes | Custom licence |
Similar skills
Tool Design
agentailor/fullstack-langgraph-nextjs-agent
Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise).
Strands
strands-agents/harness-sdk
Build, extend, evaluate, or migrate applications with Strands Agents in Python or TypeScript.
Agent Squad Python Guide
2FastLabs/agent-squad
Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid.
Add Example Agent
GetBindu/Bindu
Add a new self-contained example agent under examples/. An agent skill from GetBindu/Bindu.
Failproof AI SDK Integration
FailproofAI/failproofai
Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs.
Related
Works with
Categories
Questions about Penshot
What does Penshot do?
PenShot 项目开发 Skill。用于修改或审查 Agent、LangGraph 工作流、任务生命周期、记忆/RAG、配置、REST、MCP、CLI、测试和项目文档；先核实源码与工具配置，再按现有架构实施并验证。. Penshot is an agent skill from neopen/story-shot-agent.
When should I use Penshot?
Penshot fits situations like: tasks that involve AI video generation; tasks that involve Building AI agents; tasks that involve Retrieval-augmented generation.
How do I install Penshot in Claude Code?
Run `npx skills add neopen/story-shot-agent --skill penshot -a claude-code`. Or copy the skill folder (.agents/skills/penshot in neopen/story-shot-agent) into .claude/skills/penshot in your project. Claude Code loads it when a task matches its description.
How do I install Penshot in Codex?
Run `npx skills add neopen/story-shot-agent --skill penshot -a codex`. Or copy the skill folder (.agents/skills/penshot in neopen/story-shot-agent) into .agents/skills/penshot in your project. Codex loads it when a task matches its description.
Can I use Penshot 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 neopen/story-shot-agent --skill penshot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/penshot, .gemini/skills/penshot, .github/skills/penshot and .opencode/skills/penshot in your project.
What does Penshot need to run?
SKILL.md names no scripts, command-line tools or credentials: Penshot is instructions for the agent only. Our summary lists: Python 3.
Does Penshot 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 Penshot 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. Review the folder before installing.
What licence does Penshot use?
Penshot 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 Penshot use?
About 547 tokens (SKILL.md is roughly 2.2k 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 3.4k tokens, read only when the agent opens those files.
What are the alternatives to Penshot?
Skills that share tags, products or a category with Penshot: Dive Into LangGraph (luochang212/dive-into-langgraph, 457 stars), Tool Design (agentailor/fullstack-langgraph-nextjs-agent, 132 stars), Strands (strands-agents/harness-sdk, 8.7k stars) and Agent Squad Python Guide (2FastLabs/agent-squad, 7.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Penshot?
neopen (a GitHub user) maintains it in neopen/story-shot-agent, which has 217 GitHub stars. The repository was last updated on October 3, 2026.
Source: neopen/story-shot-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.