← Back to Skills Marketplace
52yuanchangxing

Weekly Review Pilot

by vx:17605205782 · GitHub ↗ · v1.0.0 · MIT-0
darwinlinuxwin32 ✓ Security Clean
139
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install weekly-review-pilot
Description
汇总本周完成、阻塞、经验教训与下周计划,形成管理层版和执行版摘要。;use for weekly-review, planning, retrospective workflows;do not use for 杜撰完成项, 替代工时系统.
Usage Guidance
This skill appears coherent and low-risk: it only needs python3 and uses a local script plus templates to produce weekly-review summaries. Before installing or running it: (1) inspect scripts/run.py locally (no obfuscation or network calls are present), (2) do not point --input at home or root directories or repositories containing secrets (the script will read many text file types when given a directory), (3) run the provided smoke test (python3 scripts/run.py --input examples/example-input.md) in a sandboxed workspace, and (4) avoid supplying sensitive PII unless you sanitize inputs first. If you want extra assurance, run it in an isolated environment and grep the repo for 'http', 'requests', 'subprocess', or access to os.environ before trusting it with real data.
Capability Analysis
Type: OpenClaw Skill Name: weekly-review-pilot Version: 1.0.0 The skill bundle is a well-structured tool designed for generating weekly reports and performing basic file audits. The primary script, `scripts/run.py`, includes functionality to summarize text, parse CSVs, and scan directories for specific patterns; notably, it contains regex to detect (but not execute) potentially dangerous strings like 'curl|bash' or hardcoded API keys for auditing purposes. The code uses only standard Python libraries, lacks network access, and includes explicit safety instructions in `SKILL.md` to prevent the AI agent from fabricating data or executing high-risk commands.
Capability Assessment
Purpose & Capability
Name/description (weekly review, retrospectives) align with what is included: a template, spec, examples, and a Python script that produces structured summaries and simple audits. Required binary is only python3, which is reasonable.
Instruction Scope
SKILL.md limits behavior to generating review drafts and dry-run audit output. It explicitly forbids fabricating completed items and changing external systems. The runtime instruction to run scripts/run.py or to use the template/spec when execution isn't available is coherent with the stated purpose.
Install Mechanism
No install spec or external downloads. The included scripts are run locally with python3 and use only standard library modules. There are no network fetches, archive extracts, or package installs in the repository.
Credentials
The skill requires no environment variables or credentials. The script will read local files (markdown, csv, code, etc.) when given a directory or file as input; this is consistent with its 'directory audit' and 'structured_brief' modes, but users should avoid pointing it at directories containing unrelated sensitive data.
Persistence & Privilege
The skill does not request persistent inclusion (always:false) and does not modify other skills or system-wide agent settings. It can be invoked by the agent (normal default) but has no elevated privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install weekly-review-pilot
  3. After installation, invoke the skill by name or use /weekly-review-pilot
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
weekly-review-pilot v1.0.0 - Initial release. - Summarizes completed work, blockers, lessons learned, and plans for next week. - Produces both management and execution-focused summaries. - Follows strict rules: does not invent finished items, does not replace timesheet systems, and highlights items needing confirmation. - Provides a structured review draft for user approval, based on provided logs and templates. - Emphasizes transparency, safety, and review before action.
Metadata
Slug weekly-review-pilot
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Weekly Review Pilot?

汇总本周完成、阻塞、经验教训与下周计划,形成管理层版和执行版摘要。;use for weekly-review, planning, retrospective workflows;do not use for 杜撰完成项, 替代工时系统. It is an AI Agent Skill for Claude Code / OpenClaw, with 139 downloads so far.

How do I install Weekly Review Pilot?

Run "/install weekly-review-pilot" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Weekly Review Pilot free?

Yes, Weekly Review Pilot is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Weekly Review Pilot support?

Weekly Review Pilot is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).

Who created Weekly Review Pilot?

It is built and maintained by vx:17605205782 (@52yuanchangxing); the current version is v1.0.0.

💬 Comments