mergisi/awesome-openclaw-agents

162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!

About the project

awesome-openclaw-agents is a curated collection of ready-to-use SOUL.md configurations that define AI agents for tasks across areas such as development, marketing, finance, support, and automation. It is for OpenClaw users who want predefined agent roles and workflows to adapt or deploy. The catalogue entries are agent-related skills drawn from this collection.

4.0kStars on the repository
16Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

cost-optimizer

01

mergisi/awesome-openclaw-agents

Skill Claude Code

Trigger when the user asks to audit Claude Code costs, reduce token spend, says "my Claude bill is too high", "optimize my CLAUDE.md", "why is this project burning tokens", or "/cost-optimizer". Scans a project for the common Claude Code cost leaks and returns a prioritized fix list.

not rated 4.0k +7 3mo ago A SkillSpector: warn 69 tokens original MIT

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Trigger when the user asks for an architecture diagram, says "draw the system", "update the architecture diagram", "give me an excalidraw of this codebase", or "/excalidraw-architecture". Generates or updates an Excalidraw JSON file at docs/architecture.excalidraw by reading the codebase's key entry points.

not rated 4.0k +7 3mo ago A SkillSpector: pass 78 tokens original MIT

git-commit-writer

03

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.

not rated 4.0k +7 3mo ago A SkillSpector: pass 53 tokens original MIT

model-cost-compare

04

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the…

not rated 4.0k +7 3mo ago A SkillSpector: pass 104 tokens original MIT

openclaw-debugger

05

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.

not rated 4.0k +7 3mo ago A SkillSpector: warn 71 tokens original MIT

code-explainer

06

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Paste any code snippet and get a plain English explanation of what it does and how it works.

not rated 4.0k +7 3mo ago A SkillSpector: pass 24 tokens original MIT

commit-message

07

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Generate a clean, conventional commit message from a description of your changes.

not rated 4.0k +7 3mo ago A SkillSpector: pass 17 tokens original MIT

cover-letter

08

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Describe the role and your background, get a concise, compelling cover letter paragraph.

not rated 4.0k +7 3mo ago A SkillSpector: pass 19 tokens original MIT

growth-ideas

09

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Describe your product or project and get three actionable growth ideas tailored to your stage.

not rated 4.0k +7 3mo ago A SkillSpector: pass 20 tokens original MIT

haiku-card

10

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Write a haiku about a topic and render it as a shareable card.

not rated 4.0k +7 3mo ago A SkillSpector: pass 20 tokens original MIT

meeting-notes

11

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Paste raw meeting notes and get a clean summary with key decisions and action items.

not rated 4.0k +7 3mo ago A SkillSpector: pass 20 tokens original MIT

pricing-advisor

12

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Describe your product and target customer, get a pricing strategy with three tiers and rationale.

not rated 4.0k +7 3mo ago A SkillSpector: pass 21 tokens original MIT

regex-builder

13

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Describe a text pattern in plain English and get a working regular expression with an explanation.

not rated 4.0k +7 3mo ago A SkillSpector: pass 20 tokens original MIT

sql-explainer

14

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Paste a SQL query and get a plain English explanation of what it does.

not rated 4.0k +7 3mo ago A SkillSpector: pass 20 tokens original MIT

standup-summary

15

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Tell Gemma what you did, what you're working on, and any blockers. Get a clean standup update.

not rated 4.0k +7 3mo ago A SkillSpector: pass 27 tokens original MIT

tone-shifter

16

mergisi/awesome-openclaw-agents

Skill Claude CodeCodex

Rewrite any text in a different tone — formal, casual, friendly, bold, or concise.

not rated 4.0k +7 3mo ago A SkillSpector: pass 23 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: