Evolve Reusable Coding Agent Skills From Failed Trajectories With Evoskill

Name: Evolve Reusable Coding Agent Skills From Failed Trajectories With Evoskill
Author: agentskillexchange

ASecurity

Mine failed agent runs for reusable skills, benchmark the candidates, and keep only the variants that improve a supported coding agent over your baseline.

36 stars
0 votes
0 copies
1 view
Added June 8, 2026

ai-agentspythongogitapisecuritydocumentation

Works with

claude code
cli
api

Security analysis

A92/100

mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned June 8, 2026

npx -y skills add agentskillexchange/skills --skill evolve-reusable-coding-agent-skills-from-failed-trajectories-with-evoskill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Evolve Reusable Coding Agent Skills From Failed Trajectories With Evoskill?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Evolve Reusable Coding Agent Skills From Failed Trajectories With Evoskill

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/agentskillexchange-evolve-reusable-coding-agent-skills-from-failed-tr/badge)](https://www.skillsdirectory.com/skills/agentskillexchange-evolve-reusable-coding-agent-skills-from-failed-tr)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

---
name: "Evolve reusable coding-agent skills from failed trajectories with EvoSkill"
slug: "evolve-reusable-coding-agent-skills-from-failed-trajectories-with-evoskill"
description: "Mine failed agent runs for reusable skills, benchmark the candidates, and keep only the variants that improve a supported coding agent over your baseline."
github_stars: 489
verification: "security_reviewed"
source: "https://github.com/sentient-agi/EvoSkill"
author: "Sentient"
publisher_type: "organization"
category: "Templates & Workflows"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "sentient-agi/EvoSkill"
  github_stars: 489
---

# Evolve reusable coding-agent skills from failed trajectories with EvoSkill

Mine failed agent runs for reusable skills, benchmark the candidates, and keep only the variants that improve a supported coding agent over your baseline.

## Prerequisites

Python environment, a supported coding agent such as Claude Code, OpenCode, OpenHands, Goose, or Codex CLI, and a benchmark or task set to optimize against

## Installation

Use the upstream install or setup path that matches your environment:
- uv sync
- pip install -e .
- brew install --cask claude-code # Claude Code
- brew install opencode # OpenCode (v1.4.0+)

Requirements and caveats from upstream:
- [Python API](#python-api)
- Python 3.12+

Basic usage or getting-started notes:
- Also join us on [Discord](https://discord.gg/sentientfoundation) to discuss your experience, share suggestions, or show off your work!
- ## 🤖 Supported agents
- <table>

- Source: https://github.com/sentient-agi/EvoSkill
- Extracted from upstream docs: https://raw.githubusercontent.com/sentient-agi/EvoSkill/HEAD/README.md

## Documentation

- https://github.com/sentient-agi/EvoSkill

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/evolve-reusable-coding-agent-skills-from-failed-trajectories-with-evoskill/)