← 返回 Skills 市场
157
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install project-memory-ledger
功能描述
Engineering project memory ledger with evidence + rollback (Invariants, Decision Log, Change Log). Use to extend conversations over time, reduce hallucinatio...
安全使用建议
This skill appears coherent with its description, but review a few things before installing/use: (1) run in local mode first (backend=local) to confirm where files are written and to avoid unintended Drive operations; (2) check and set the config paths (local_dir, projects_root_dir) to directories you control and avoid default /root locations if you are not running as root; (3) if you enable Drive backend, authenticate gws yourself and set the exact Drive folder IDs you want the skill to use (it will create folders/docs under those IDs); (4) inspect the included scripts (scripts/ledger.py) if you need to verify behavior—operations call gws via subprocess (no shell) and write local files, so run in a sandbox if you need extra assurance.
功能分析
Type: OpenClaw Skill
Name: project-memory-ledger
Version: 0.1.3
The project-memory-ledger skill is a utility designed to help an AI agent maintain a structured log of project invariants, decisions, and changes. The core logic in `scripts/ledger.py` implements local file operations (appending to Markdown files) and optional Google Drive integration via the `gws` CLI. The code uses safe subprocess execution (`shell=False`), performs standard project scaffolding, and follows the behavior described in its documentation (`SKILL.md`, `README.md`). No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
Name/description match what the files implement: a local Markdown ledger plus optional Drive scaffolding via the gws CLI. Declared required binary (python3) and recommended gws are appropriate for the stated features; no unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md and README instruct reading a config file and writing local Markdown ledgers and, if chosen, invoking gws to create Drive folders/docs. The runtime instructions and the included script operate on the declared config paths and workspace files only; they do not attempt to read unrelated system credentials or post data to unexpected external endpoints. Note: default config examples point at /root paths which may be surprising for non-root setups.
Install Mechanism
No install spec and only an included Python script—no network downloads or external install steps in the skill bundle. Risk is limited to running the packaged script with python3 and optionally calling the gws CLI if Drive backend is used.
Credentials
The skill requires no environment variables or credentials in its metadata. Drive use requires the user to have gws authenticated or to provide Drive folder IDs in config; these are proportionate to the optional Drive features. There are no unexplained secret requests.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. It writes files into workspace-configured directories and may create project folders; this is expected for a ledger and does not modify other skills or system-wide agent settings.
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 project-memory-ledger - 安装完成后，直接呼叫该 Skill 的名称或使用
/project-memory-ledger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
v0.1.3
No changes in functionality or documentation; this release is identical to the previous version.
- No code or documentation updates since the last version.
- Version number incremented to 0.1.3.
v0.1.2
- Added metadata section to SKILL.md, specifying required and recommended binaries.
- Updated skill description for clarity about optional Drive project-doc scaffolding.
- Removed reference to the obsolete scripts/drive_ledger.py file.
- Documentation adjusted for improved accuracy and clarity regarding configuration and backend behavior.
v0.1.1
- Added example configuration values and documentation hints to references/default_config.json.
- Improved code comments and minor logic updates in scripts/ledger.py for clarity and maintainability.
- No breaking changes; user workflows and ledger structure remain the same.
v0.1.0
Initial release of project-memory-ledger skill:
- Introduces a durable, low-pollution ledger split into Invariants, Decisions, and Changes books.
- Supports both local Markdown and Google Drive (via gws) backends for document storage.
- Enforces explicit project tagging and traceable record-keeping with a default project fallback.
- Includes scripts to initialize, append entries, register projects, and propose PRD updates.
- Provides configuration and usage details for flexible deployment.
元数据
常见问题
Project Memory Ledger 是什么？
Engineering project memory ledger with evidence + rollback (Invariants, Decision Log, Change Log). Use to extend conversations over time, reduce hallucinatio... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 157 次。
如何安装 Project Memory Ledger？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install project-memory-ledger」即可一键安装，无需额外配置。
Project Memory Ledger 是免费的吗？
是的，Project Memory Ledger 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Project Memory Ledger 支持哪些平台？
Project Memory Ledger 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Project Memory Ledger？
由 Pascal（@zcweah1981）开发并维护，当前版本 v0.1.3。
推荐 Skills