OpenClaw Skills

Skill Store

Battle-tested skills verified by the lab

Skill Store · 100 items
🟢 🟢 Battle-tested🟡 🟡 Install-verified
Conduct a "Post-Mortem" Before the Meeting: How a Five-Minute Pre-Mortem Can Save Projects
🟢 Battle-testedAI Tools

Conduct a "Post-Mortem" Before the Meeting: How a Five-Minute Pre-Mortem Can Save Projects

Last week, I helped a friend conduct a retrospective on a product redesign. Two weeks after the new version launched, the core conversion rate dropped by 11%. T

Run a Dry Run First, Then Hit Confirm: Make It Muscle Memory
🟢 Battle-testedAI Tools

Run a Dry Run First, Then Hit Confirm: Make It Muscle Memory

Let’s start with a real-world scenario: A friend working in DevOps ran a "clean up expired logs" script at 8 AM one morning. The script itself was fine; the mis

Add Checkpoints to Long Tasks: Make AI Submit Intermediate Saves at Every Step
🟢 Battle-testedAI Tools

Add Checkpoints to Long Tasks: Make AI Submit Intermediate Saves at Every Step

When you hand a long task over to an AI, the most common failure mode looks like this: You wait twenty minutes for the final deliverable, only to open it and re

Paraphrase First, Then Act: Let AI Confirm Task Boundaries in One Sentence
🟢 Battle-testedAI Tools

Paraphrase First, Then Act: Let AI Confirm Task Boundaries in One Sentence

Last week, I asked an AI to revise a piece of copy. It interpreted "make it more conversational" as "convert it into a dialogue format." I only discovered the i

Stop Tinkering with Style via Prompts: Feed AI Three "Sample Anchors"
🟢 Battle-testedAI Tools

Stop Tinkering with Style via Prompts: Feed AI Three "Sample Anchors"

Last Tuesday, I was working on a series of product update drafts. I asked AI to write the first one, which started with, "In a rapidly changing market environme

Saying "What You Want" Isn't Enough: Include "Don't Do This" in Your AI Prompts
🟢 Battle-testedAI Tools

Saying "What You Want" Isn't Enough: Include "Don't Do This" in Your AI Prompts

Last week, I asked an AI to write a product copy draft. The first version was complete, but the screen was filled with clichés like "ultimate experience," "empo

Don’t Blindly Accept AI Deliverables: The Three-Column Review Method
🟢 Battle-testedAI Tools

Don’t Blindly Accept AI Deliverables: The Three-Column Review Method

The smoothest scenario when assigning tasks to AI is when it gets it right on the first try. The most common failure mode occurs when, to save effort, you simpl

Task Too Long? Write a One-Page "Relay Note" for the AI Before Switching Sessions
🟢 Battle-testedAI Tools

Task Too Long? Write a One-Page "Relay Note" for the AI Before Switching Sessions

Yesterday, I was tweaking my website’s navigation bar. By the 40th round of conversation, the AI started messing up—repeatedly bringing back color schemes I had

When Assigning Tasks to AI, Define "Done" First
🟢 Battle-testedAI Tools

When Assigning Tasks to AI, Define "Done" First

"Help me organize this weekly report"—if you send this, you’ll likely receive a mind-reading attempt. The biggest pitfall when using AI isn’t its capability; it

Before Finalizing Your Writing, Have AI "Take Roll Call" Item by Item: The Verification Statement Method
🟢 Battle-testedAI Tools

Before Finalizing Your Writing, Have AI "Take Roll Call" Item by Item: The Verification Statement Method

Last week, while revising a product copy, I asked AI to check for "exaggerated claims." It replied: "The overall tone is steady, and no obvious issues were foun

Logging Errors: Using a Mistake Log to Prevent Teams from Stumbling Over the Same Pitfalls
🟢 Battle-testedAI Tools

Logging Errors: Using a Mistake Log to Prevent Teams from Stumbling Over the Same Pitfalls

Last week, we reviewed a production incident and discovered that the same configuration parameter had caused issues three times within three months. The first t

Why Your Skill Library Gets Messier Over Time: Subtract from Your Backlog with the "Diff Note Method"
🟢 Battle-testedAI Tools

Why Your Skill Library Gets Messier Over Time: Subtract from Your Backlog with the "Diff Note Method"

Applicable Scenario: You have collected or written many skills (prompts, workflows, scripts), but you often can't remember which version works and which is long