evo — for Claude Code community, for Claude Code, ide skills, and embeds the EVO harness from, kb-stdin, ## Resources, inconsistent, kb-file, python -c, kb-b64

v1.0.0
GitHub

このスキルについて

適した場面: Ideal for AI agents that need what this skill does. ローカライズされた概要: Explicit-assumption Verification Orchestrator # EVO What this skill does Defines an EVO subagent persona via agents/openai.yaml with a strict "Prolog-first" verification workflow. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

機能

What this skill does
Defines an EVO subagent persona via agents/openai.yaml with a strict "Prolog-first" verification
Ask EVO to solve a problem and require it to use Prolog derivations before stating conclusions.
Example (default, no KB file creation):
observation(example).

# 主なトピック

for Claude Code and embeds the EVO harness from kb-stdin ## Resources inconsistent kb-file
machinelearning2014 machinelearning2014
[0]
[0]
更新日: 3/9/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

適した場面: Ideal for AI agents that need what this skill does. ローカライズされた概要: Explicit-assumption Verification Orchestrator # EVO What this skill does Defines an EVO subagent persona via agents/openai.yaml with a strict "Prolog-first" verification workflow. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

このスキルを使用する理由

推奨ポイント: evo helps agents what this skill does. Explicit-assumption Verification Orchestrator # EVO What this skill does Defines an EVO subagent persona via agents/openai.yaml with a strict "Prolog-first" verification

おすすめ

適した場面: Ideal for AI agents that need what this skill does.

↓ 実現可能なユースケース for evo

ユースケース: Applying What this skill does
ユースケース: Applying Defines an EVO subagent persona via agents/openai.yaml with a strict "Prolog-first" verification
ユースケース: Applying Ask EVO to solve a problem and require it to use Prolog derivations before stating conclusions

! セキュリティと制限

  • 制約事項: Ask EVO to solve a problem and require it to use Prolog derivations before stating conclusions.
  • 制約事項: Do not use Write/Edit tools to create temporary KB files for routine runs.
  • 制約事項: How to use Ask EVO to solve a problem and require it to use Prolog derivations before stating conclusions

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Labs デモ

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ とインストール手順

These questions and steps mirror the structured data on this page for better search understanding.

? よくある質問

evo とは何ですか？

適した場面: Ideal for AI agents that need what this skill does. ローカライズされた概要: Explicit-assumption Verification Orchestrator # EVO What this skill does Defines an EVO subagent persona via agents/openai.yaml with a strict "Prolog-first" verification workflow. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

evo はどうやって導入しますか？

次のコマンドを実行してください: npx killer-skills add machinelearning2014/evo。Cursor、Windsurf、VS Code、Claude Code など19以上のIDEで使えます。

evo の主な用途は？

主な用途は次のとおりです: ユースケース: Applying What this skill does, ユースケース: Applying Defines an EVO subagent persona via agents/openai.yaml with a strict "Prolog-first" verification, ユースケース: Applying Ask EVO to solve a problem and require it to use Prolog derivations before stating conclusions。

evo に対応するIDEは？

このスキルは Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer に対応しています。統一された導入には Killer-Skills CLI を使えます。

evo に制限はありますか？

制約事項: Ask EVO to solve a problem and require it to use Prolog derivations before stating conclusions.. 制約事項: Do not use Write/Edit tools to create temporary KB files for routine runs.. 制約事項: How to use Ask EVO to solve a problem and require it to use Prolog derivations before stating conclusions.

↓ このスキルの導入方法

  1. 1. ターミナルを開く

    プロジェクトディレクトリでターミナルまたはコマンドラインを開きます。

  2. 2. インストールコマンドを実行

    npx killer-skills add machinelearning2014/evo を実行してください。CLI がIDEまたはエージェントを自動検出し、スキルを設定します。

  3. 3. スキルを使い始める

    このスキルはすぐに有効になります。現在のプロジェクトで evo をすぐ使えます。

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

evo

Install evo, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

EVO

What this skill does

  • Defines an EVO subagent persona via agents/openai.yaml with a strict "Prolog-first" verification workflow.
  • Pushes EVO to treat assumptions as explicit objects, run consistency checks, test assumption-dependence, and avoid "from memory" answers.

How to use

  • Ask EVO to solve a problem and require it to use Prolog derivations before stating conclusions.
  • To actually execute Prolog locally, use skills/evo/scripts/evo_run.py, which wraps skills/prolog-runner/scripts/run_prolog.py and embeds the EVO harness from skills/evo/references/evo_harness.pl.
  • For routine runs, keep KB text in memory and pipe to --kb-stdin (do not create temporary *.pl files unless explicitly requested).

Example (default, no KB file creation):

PowerShell: @' observation(example). rule(r1, conclusion(ok), [example]). '@ | python C:\\Users\\trung\\.codex\\skills\\evo\\scripts\\evo_run.py --kb-stdin --assumption some_assumption

Do not use Write/Edit tools to create temporary KB files for routine runs.

Claude default (no temporary .pl file creation):

cat path/to/task.pl | python C:\\Users\\trung\\.claude\\skills\\evo\\scripts\\evo_run.py --kb-stdin --assumption some_assumption

Resources

  • skills/evo/references/evo_harness.pl: minimal harness providing proof tracing, assumptions, and consistency checks.
  • skills/evo/references/template_kb.pl: starter template for task KBs.
  • skills/evo/scripts/evo_run.py: helper to run inconsistent + derive conclusions and do assumption-drop tests.

Tip: prefer --kb-stdin over --kb-file for routine runs, and avoid large inline python -c base64 snippets. Use --kb-file only for explicit file artifacts and --kb-b64 only when stdin piping is unavailable.

関連スキル

Looking for an alternative to evo or another community skill for your workflow? Explore these related open-source skills.

すべて表示

openclaw-release-maintainer

Logo of openclaw
openclaw

ローカライズされた概要: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

ローカライズされた概要: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

ローカライズされた概要: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 138.4k
⑂ 0
ブラウザ

pr-review

Logo of pytorch
pytorch

ローカライズされた概要: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 98.6k
⑂ 0
開発者