ワンクリックでManusで任意のスキルを実行

repo-gauntlet

スター1

フォーク0

更新日2026年6月2日 08:01

Gauntlet is a two-role adversarial MCP server that infers software correctness by observing how code behaves under sustained, targeted attack. Built for dark-factory environments where code is written by bots and verified by attack. Triggers - gauntlet, adversarial-mcp-server, attack-driven-verification

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

coilyco-flight-deck

coilyco-flight-deck/gauntlet

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

repo-gauntlet

Pointer to ~/projects/coilysiren/gauntlet/.

README.md - what it is, quickstart, layout.
AGENTS.md - agent-facing operating context for the repo.
docs/FEATURES.md - what ships today.

Read those before answering substantive questions about gauntlet.

このリポジトリの他の Skills

同じリポジトリ

gauntlet

coilyco-flight-deck/gauntlet

Adversarial API inspection via the Gauntlet MCP server. Use this skill when the user wants to run their service through the gauntlet — stress-test a running HTTP API under attack, validate authorization/ownership/input invariants before promoting code, or drive Gauntlet's role-disciplined adversarial loop against a SUT. Triggers include "run the gauntlet", "run my service through the gauntlet", "run it through the gauntlet", "adversarial test", "check before merging", "attack this API", "run the hardening loop".

2026-04-251

gauntlet-author

coilyco-flight-deck/gauntlet

Author Gauntlet Trial YAMLs from a product spec. Use this skill when the user wants to translate a verbose product specification, design doc, or natural-language description of an HTTP service into testable invariants packaged as Gauntlet Trials. Triggers include "author trials from this spec", "generate gauntlet trials", "propose trials for this API", "make trials from this design doc", "what should we test about this service".

2026-04-231

name	repo-gauntlet
description	Gauntlet is a two-role adversarial MCP server that infers software correctness by observing how code behaves under sustained, targeted attack. Built for dark-factory environments where code is written by bots and verified by attack. Triggers - gauntlet, adversarial-mcp-server, attack-driven-verification