Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问许可证需确认审计通过

creation-feasibility-gate创建可行性门

Agent Skill

creation-feasibility-gate 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,129

周安装

48

GitHub Stars

25

下载量

396
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:creation-feasibility-gate(创建可行性门)
来源仓库:https://github.com/oimiragieo/agent-studio
仓库路径:skills/creation-feasibility-gate
安装命令:
npx skills add https://github.com/oimiragieo/agent-studio --skill creation-feasibility-gate
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/oimiragieo/agent-studio --skill creation-feasibility-gate

简介

creation-feasibility-gate 用于在执行创建前进行快速可行性预检。

  • 返回 PASS/WARN/BLOCK 判断与证据说明,不直接生成 artifacts。
  • 适用于防止低价值或重复技能/工作流的无效创建尝试。
  • 必须首先检查功能重复性,确认无等效 artifact 后再放行。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Creation Feasibility Gate

Overview

Run a fast preflight feasibility check before creating a new agent/skill/workflow/hook/template/schema. This prevents low-value or impossible creator runs.

When to Use

  • Phase 0.5 dynamic creation flow
  • User asks for net-new capability
  • Reflection/evolution recommends artifact creation

Iron Laws

  1. NEVER create artifacts inside this skill — return PASS/WARN/BLOCK with evidence only; all actual creation happens in the appropriate creator skill downstream.
  2. ALWAYS run the existence/duplication check first — never proceed toward PASS if a functionally identical artifact already exists in any catalog or registry.
  3. ALWAYS include concrete file-level evidence for every decision — a bare PASS or BLOCK without referencing specific paths or catalog entries is a spec violation.
  4. NEVER let WARN silently become PASS — every WARN must list exact caveats that the calling agent must acknowledge before creation proceeds.
  5. ALWAYS resolve BLOCK status with actionable next steps and recommended target agents — a BLOCK without remediation tasks is an incomplete gate decision.

Anti-Patterns

Anti-PatternWhy It FailsCorrect Approach
Returning PASS without running the duplication checkCreates duplicate artifacts that split agent traffic and inflate catalogsAlways query catalog + registry + filesystem before PASS
Returning BLOCK without remediation tasksCalling agent stalls with no path forwardInclude nextActions with specific agents/skills to unblock
Skipping the security/creator boundary checkCreator paths may be blocked by governance hooks; silently bypassing them causes runtime failuresAlways verify creator skill chain is reachable before PASS
Treating WARN as informational onlyWARN caveats are not surfaced to the user; creation proceeds with unresolved risksWARN must be acknowledged explicitly by the caller in its task metadata
Running creation steps inside the gate skillViolates separation of concerns; gate outputs can't be validated independentlyGate outputs only the decision JSON; delegate creation to creator skills

Workflow

Step 1: Resolve Target

  • Identify proposed artifact type and name
  • Identify expected runtime/tool dependencies
  • Identify expected owner agents

Step 2: Existence/Duplication Check (Iron Law #2)

Use the shared duplicate detection library:

const { checkDuplicate } = require('.claude/lib/creation/duplicate-detector.cjs');
const result = checkDuplicate({
  artifactType: artifactType, // from Step 1 classification
  name: proposedName,
  description: proposedDescription,
});

if (result.decision === 'EXACT_MATCH') {
  return {
    gate: 'BLOCK',
    reason: `Artifact exists at ${result.matchedPath}. Use the ${artifactType}-updater skill instead.`,
  };
}
if (result.decision === 'REGISTRY_MATCH') {
  return {
    gate: 'WARN',
    reason: `"${proposedName}" found in ${result.message} but file may be missing. Investigate.`,
  };
}
if (result.decision === 'SIMILAR_FOUND') {
  return {
    gate: 'WARN',
    reason: `Similar artifacts found: ${result.candidates.map(c => `${c.name} (${(c.score * 100).toFixed(0)}%)`).join(', ')}. Confirm creation is intentional.`,
  };
}
return { gate: 'PASS' };

The 3 detection layers (filesystem, registry/catalog, fuzzy/semantic) are handled internally by the library. See .claude/lib/creation/duplicate-detector.cjs for details.

Step 2.5: Additional Preflight Checks

Run these checks with concrete evidence:

  1. Stack compatibility check

- Required tooling/runtime present in current project conventions

  1. Integration readiness check

- Can it be routed/discovered/assigned after creation?

  1. Security/creator boundary check

- Ensure creator path and governance can be satisfied

Step 3: Decision

Return one status:

  • PASS: creation is feasible now
  • WARN: feasible with clear caveats
  • BLOCK: not feasible; must resolve blockers first

Use this output shape:

{
  "status": "PASS|WARN|BLOCK",
  "artifactType": "agent|skill|workflow|hook|template|schema",
  "artifactName": "example-name",
  "evidence": ["..."],
  "blockers": [],
  "nextActions": ["..."]
}

Output Protocol

If BLOCK, include concrete remediation tasks and recommended target agents. If PASS or WARN, include exact creator skill chain to run next.

Memory Protocol

Record feasibility patterns and recurring blockers to .claude/context/memory/learnings.md.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.66%
按下载量换算133

Claude

31.43%
按下载量换算124

Cursor

18.34%
按下载量换算73

Gemini CLI

8.65%
按下载量换算34

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills