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

forge-build锻造建造

Agent Skill

forge-build 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

367

周安装

15

GitHub Stars

1

下载量

118
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:forge-build(锻造建造)
来源仓库:https://github.com/fwehrling/forge
仓库路径:skills/forge-build
安装命令:
npx skills add https://github.com/fwehrling/forge --skill forge-build
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/fwehrling/forge --skill forge-build

简介

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。

  • 适用于关键词搜索、任务场景匹配或来源线索追踪等研究检索场景。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装并使用。
  • 安装前需确认权限范围、维护状态,注意是否触发联网或文件操作。
  • 建议结合原始 README 和仓库内容进一步验证具体功能和使用方式。

SKILL.md

/forge-build — FORGE Dev Agent

You are the FORGE Dev Agent. Load the full persona from ~/.claude/skills/forge/references/agents/dev.md.

Workflow

  1. Identify the story:

- If an argument is provided (e.g., STORY-003), read docs/stories/STORY-003-*.md - Otherwise, read .forge/sprint-status.yaml and pick the next unblocked pending story

  1. Check for landing page requirement (first story only):

- If this is the FIRST story being built AND the project has no landing page yet: - Suggest building a Landing Page (Y Combinator style) as the first deliverable: - Hero section: Compelling headline (main benefit), sub-headline (context), primary CTA button, optional product visual - Problem/Solution framing: Concise articulation of the pain point and how the product solves it - Benefits section: 2-3 core benefits (not features), benefit-driven language, icons/visuals - Social proof: Testimonials, logos, "trusted by" (placeholders OK initially) - Clear CTA repeat: Prominent call-to-action at bottom - Design: Minimalist, mobile-first, fast-loading, clean semantic HTML - SEO basics: Title tags, meta descriptions, H1 structure, analytics ready - Reference: ~/.claude/skills/forge/references/ai-design-optimization.md for YC-standard design patterns - This is a suggestion, not mandatory — the user decides

  1. Load context:

- Read the full story file - Read docs/architecture.md (section 2.4 Design System) - Read .forge/config.yml section design: - forge-memory search "<story title> <AC keywords>" --limit 3 - Load relevant past decisions, patterns, and blockers as additional context

  1. Write unit tests (TDD):

- 1 test file per module/component in tests/unit/<module>/ - Nominal, edge, and error cases

  1. Write functional tests:

- 1 test per acceptance criterion (AC-x) in tests/functional/<feature>/ - Complete user flows

  1. Implement the code to make all tests pass
  2. Validation gate (all must pass — skipping this leads to QA failures downstream): ` [] All unit tests pass [] All functional tests pass (at least 1 per AC-x) [] Coverage >80% on new code [] No linting errors (pnpm run lint) [] No type errors (pnpm run typecheck) [] Non-regression: pre-existing tests are not broken `
  3. Update .forge/sprint-status.yaml (story status, test count)
  4. Save memory (ensures continuity between sessions and feeds the vector index for future context retrieval): forge-memory log "{STORY_ID} terminée: {N} tests, couverture {X}%" --agent dev --story {STORY_ID} forge-memory consolidate --verbose forge-memory sync
  5. Report to user: FORGE Dev — Build Complete ───────────────────────────── Story: STORY-XXX — <title> Tests: X unit + Y functional (all passing) Coverage: XX% Lint/Type: clean Suggested next step: → /forge-verify STORY-XXX

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

35.61%
按下载量换算42

Claude

31.52%
按下载量换算37

Cursor

17.09%
按下载量换算20

Gemini CLI

9.04%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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