Agent skill

Kapso

Optimize code using KAPSO (Knowledge-Grounded Optimization).

Install Kapso

skills CLI

$ npx skills add Leeroo-AI/kapso --skill kapso -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Leeroo-AI/kapso kapso --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Leeroo-AI/kapso.git skills-src && mkdir -p .claude/skills && cp -r skills-src/moltbook_bot/openclaw_skill .claude/skills/kapso && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "kapso" agent skill from https://github.com/Leeroo-AI/kapso/tree/main/moltbook_bot/openclaw_skill into .claude/skills/kapso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kapso", 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

$skill-installer install https://github.com/Leeroo-AI/kapso/tree/main/moltbook_bot/openclaw_skill

Type 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.

skills CLI

$ npx skills add Leeroo-AI/kapso --skill kapso -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Leeroo-AI/kapso kapso --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Leeroo-AI/kapso.git skills-src && mkdir -p .agents/skills && cp -r skills-src/moltbook_bot/openclaw_skill .agents/skills/kapso && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "kapso" agent skill from https://github.com/Leeroo-AI/kapso/tree/main/moltbook_bot/openclaw_skill into .agents/skills/kapso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kapso", 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.

skills CLI

$ npx skills add Leeroo-AI/kapso --skill kapso -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Leeroo-AI/kapso kapso --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Leeroo-AI/kapso.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/moltbook_bot/openclaw_skill .cursor/skills/kapso && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "kapso" agent skill from https://github.com/Leeroo-AI/kapso/tree/main/moltbook_bot/openclaw_skill into .cursor/skills/kapso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kapso", 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

$ gemini skills install https://github.com/Leeroo-AI/kapso.git --path moltbook_bot/openclaw_skill

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Leeroo-AI/kapso --skill kapso -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Leeroo-AI/kapso kapso --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Leeroo-AI/kapso.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/moltbook_bot/openclaw_skill .gemini/skills/kapso && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "kapso" agent skill from https://github.com/Leeroo-AI/kapso/tree/main/moltbook_bot/openclaw_skill into .gemini/skills/kapso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kapso", 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.

GitHub CLI

$ gh skill install Leeroo-AI/kapso kapso

Installs 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).

skills CLI

$ npx skills add Leeroo-AI/kapso --skill kapso -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Leeroo-AI/kapso.git skills-src && mkdir -p .github/skills && cp -r skills-src/moltbook_bot/openclaw_skill .github/skills/kapso && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "kapso" agent skill from https://github.com/Leeroo-AI/kapso/tree/main/moltbook_bot/openclaw_skill into .github/skills/kapso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kapso", 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.

skills CLI

$ npx skills add Leeroo-AI/kapso --skill kapso -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Leeroo-AI/kapso kapso --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Leeroo-AI/kapso.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/moltbook_bot/openclaw_skill .opencode/skills/kapso && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "kapso" agent skill from https://github.com/Leeroo-AI/kapso/tree/main/moltbook_bot/openclaw_skill into .opencode/skills/kapso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kapso", 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: kapso
GitHub stars: 121
Token cost: ~642 tokens
SKILL.md length: 99 words
Files: 2
Skills in repo: 2
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Optimize code using KAPSO (Knowledge-Grounded Optimization).

Works in 3 steps: Submit Optimization Request → Check Job Status → Health Check
You need to write
SKILL.md covers When to Use, How to Use, Example: Optimize O(n²) to O(n) and Response Format for Moltbook, plus 2 more sections
Calls curl and python

What it does

Kapso is an agent skill from Leeroo-AI/kapso. Optimize code using KAPSO (Knowledge-Grounded Optimization). Use when you need to write, optimize, or fix code. Connects to a local KAPSO server that iteratively improves solutions through experimentation.

Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `HEARTBEAT.md`).

It sits in Agent Workflows, covering Autonomous loops and A/B testing. The repository describes itself as: Kapso by Leeroo: Long-running agents that optimize AI and Data systems, and learn from every experience. 1 open-source on MLE-Bench; ALE-Bench; RelBench. The licence is MIT.

When your agent uses it

You need to write
Tasks that involve Autonomous loops
Tasks that involve A/B testing

Example prompts

“/kapso”

Requirements

Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

Submit Optimization Request
Check Job Status
Health Check

What it can do on your machine

Read from SKILL.md and the folder at commit 3b5140a. 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
Shell commands in SKILL.md call:
- curl
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
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

Kapso loads about 642 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 99 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~53
When it runs · the whole SKILL.md, loaded when a task matches: ~642

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 passed

The automated check found no risky patterns in SKILL.md.

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 Leeroo-AI/kapso at commit 3b5140a, republished under its MIT licence (© Leeroo-AI). 99 words, ~642 tokens.

Download SKILL.mdSave it as .claude/skills/kapso/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: kapso
description: Optimize code using KAPSO (Knowledge-Grounded Optimization). Use when you need to write, optimize, or fix code. Connects to a local KAPSO server that iteratively improves solutions through experimentation.

KAPSO Bridge Skill

KAPSO is a knowledge-grounded optimization framework that iteratively improves code through experimentation.

When to Use

Use this skill when you need to:

Optimize inefficient code (e.g., O(n²) → O(n))
Fix bugs with verification
Improve algorithm performance
Generate optimized solutions

How to Use

1. Submit Optimization Request

bash

curl -X POST http://${KAPSO_URL:-localhost:8000}/optimize \
  -H "Content-Type: application/json" \
  -d '{
    "goal": "Describe what needs to be optimized",
    "code": "def your_code(): pass",
    "context": "Optional additional context"
  }'

Response:

json

{
  "job_id": "abc123",
  "status": "running",
  "thought_process": "Optimization started..."
}

2. Check Job Status

bash

curl http://${KAPSO_URL:-localhost:8000}/status/{job_id}

Response when complete:

json

{
  "job_id": "abc123",
  "status": "completed",
  "code": "def optimized_code(): ...",
  "cost": "$0.042",
  "thought_process": "KAPSO Optimization Complete..."
}

3. Health Check

bash

curl http://${KAPSO_URL:-localhost:8000}/health

Example: Optimize O(n²) to O(n)

Input:

python

def find_duplicates(arr):
    duplicates = []
    for i in range(len(arr)):
        for j in range(i + 1, len(arr)):
            if arr[i] == arr[j] and arr[i] not in duplicates:
                duplicates.append(arr[i])
    return duplicates

After KAPSO optimization:

python

def find_duplicates(arr):
    seen = set()
    duplicates = set()
    for item in arr:
        if item in seen:
            duplicates.add(item)
        seen.add(item)
    return list(duplicates)

Response Format for Moltbook

When posting optimized code to Moltbook, use this format:

markdown

**KAPSO Optimization Report**

Original complexity: O(n²)
Optimized complexity: O(n)
Cost: $0.042

\`\`\`python
# Optimized code here
\`\`\`

*Optimized by [KAPSO](https://github.com/Leeroo-AI/kapso) - Knowledge-Grounded Optimization*

Environment Variables

KAPSO_URL: URL of the KAPSO server (default: http://localhost:8000)

Server Requirements

The KAPSO server must be running:

bash

cd /home/ubuntu/kapso && python kapso_server.py

Files

SKILL.md and 1 other file in moltbook_bot/openclaw_skill of Leeroo-AI/kapso.

SKILL.md
HEARTBEAT.md

Open the folder on GitHubat commit 3b5140a

Compare with similar skills

Kapso 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.

Kapso compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Kapso this skillLeeroo-AI/kapso	121	—	~642	Automated safety check: Pass	MIT	yesterday
Autoresearchgrandamenium/cortextos	101	—	~1.9k	Automated safety check: Pass	MIT	17 days ago
Autoresearchericosiu/ai-marketing-skills	3.6k	2 repos	~2.2k	Automated safety check: Pass	MIT	17 days ago
Autoresearchgithub/awesome-copilot	40k	1 repos	~2.8k	Automated safety check: Pass	MIT	today
Edt MCP Tool DescriptionsDitriXNew/EDT-MCP	295	—	~3k	Automated safety check: Pass	AGPL-3.0	2 days ago
Evo MemoryEvoScientist/EvoSkills	476	3 repos	~4.8k	Automated safety check: Pass	Apache-2.0	9 days ago

Similar skills

Autoresearch
grandamenium/cortextos
The analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation.
101 GitHub stars~1.9k tokensUpdated 17 days ago
Agent WorkflowsAuto-check passed
Autoresearch
ericosiu/ai-marketing-skills
Run Karpathy-style autoresearch optimization on any content.
3.6k GitHub starsUsed in 2 repos~2.2k tokens
Marketing & SEOAuto-check passed
Autoresearch
github/awesome-copilot
Official
Autonomous iterative experimentation loop for any programming task.
40k GitHub starsUsed in 1 repo~2.8k tokens
Agent WorkflowsAuto-check passed
Edt MCP Tool Descriptions
DitriXNew/EDT-MCP
How to size, write and A/B-test the text of a tool — its description and its inputSchema parameter prose — so that cutting it does not cost call quality, and so that a tool that IS getting called…
295 GitHub stars~3k tokensUpdated 2 days ago
Agent WorkflowsAuto-check passed
Evo Memory
EvoScientist/EvoSkills
Manages persistent research memory across ideation and experimentation cycles.
476 GitHub starsUsed in 3 repos~4.8k tokens
Agent WorkflowsAuto-check passed
Spec Optimize
leo-kuang-ai/spec-first
Run metric-driven iterative optimization loops. An agent skill from leo-kuang-ai/spec-first.
107 GitHub stars~13k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed

Questions about Kapso

What does Kapso do?

Optimize code using KAPSO (Knowledge-Grounded Optimization). Kapso is an agent skill from Leeroo-AI/kapso. Optimize code using KAPSO (Knowledge-Grounded Optimization).

When should I use Kapso?

Kapso fits situations like: you need to write; tasks that involve Autonomous loops; tasks that involve A/B testing.

How do I install Kapso in Claude Code?

Run `npx skills add Leeroo-AI/kapso --skill kapso -a claude-code`. Or copy the skill folder (moltbook_bot/openclaw_skill in Leeroo-AI/kapso) into .claude/skills/kapso in your project. Claude Code loads it when a task matches its description.

How do I install Kapso in Codex?

Run `npx skills add Leeroo-AI/kapso --skill kapso -a codex`. Or copy the skill folder (moltbook_bot/openclaw_skill in Leeroo-AI/kapso) into .agents/skills/kapso in your project. Codex loads it when a task matches its description.

Can I use Kapso 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 Leeroo-AI/kapso --skill kapso -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kapso, .gemini/skills/kapso, .github/skills/kapso and .opencode/skills/kapso in your project.

What does Kapso need to run?

Going by SKILL.md and its folder, Kapso needs the command-line tools its instructions call (curl and python). Our summary lists: Python 3.

Does Kapso access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Kapso safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Kapso use?

Kapso 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 Kapso use?

About 642 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Kapso?

Skills that share tags, products or a category with Kapso: Autoresearch (grandamenium/cortextos, 101 stars), Autoresearch (ericosiu/ai-marketing-skills, 3.6k stars), Autoresearch (github/awesome-copilot, 40k stars) and Edt MCP Tool Descriptions (DitriXNew/EDT-MCP, 295 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kapso?

Leeroo-AI (a GitHub organization) maintains it in Leeroo-AI/kapso, which has 121 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.

Source: Leeroo-AI/kapso on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Kapso

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

KAPSO Bridge Skill

When to Use

How to Use

1. Submit Optimization Request

2. Check Job Status

3. Health Check

Example: Optimize O(n²) to O(n)

Response Format for Moltbook

Environment Variables

Server Requirements

Files

Compare with similar skills

Similar skills

Autoresearch

Autoresearch

Autoresearch

Edt MCP Tool Descriptions

Evo Memory

Spec Optimize

More from Leeroo-AI/kapso

Kapso

Related

Questions about Kapso