agent-discovery — community agent-discovery, agent_template_public, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for AI Agents requiring structured domain-specific discovery workflows, such as those utilizing BABOK or AMA frameworks. Agent Template Framework for Domain-Specific Agent Generation - Public Version

matsuni-kk matsuni-kk
[0]
[0]
Updated: 2/27/2026

Agent Capability Analysis

The agent-discovery skill by matsuni-kk is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for AI Agents requiring structured domain-specific discovery workflows, such as those utilizing BABOK or AMA frameworks.

Core Value

Empowers agents to conduct comprehensive content analysis, generating draft requirements and framework research using Markdown files like draft_requirements.md and framework_research.md, while leveraging discovery checklists and industry-standard frameworks.

Capabilities Granted for agent-discovery

Automating discovery workflows for new domain-specific agent creation
Generating draft requirements and framework research documents
Conducting preflight checks using discovery checklists and industry-standard frameworks like BABOK or AMA

! Prerequisites & Limits

  • Requires access to industry-standard frameworks and documentation
  • Limited to Markdown file format for draft requirements and framework research
  • Needs pre-existing discovery checklists and research questions like those in discovery_questions.md
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

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

Boot Container Sandbox

agent-discovery

Install agent-discovery, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Agent Discovery Workflow

新規ドメイン特化エージェント作成のためのDiscoveryフェーズ。主成果物はdraft_requirements.mdとframework_research.md。

Instructions

1. Preflight(事前確認)

  • ./assets/discovery_checklist.md を先に読み、必須項目を確認する。
  • 対象ドメインの業界標準フレームワーク(BABOK、AMA等)をWeb検索で調査する。
  • 既存資料があれば収集し、参照元リンクと取得日時を記録する。
  • 確認できなかった資料は「未参照一覧」として明記する。

2. 生成

  • ./questions/discovery_questions.md に従い以下を収集する:
    • ドメイン名(スネークケース)、エージェント表示名
    • 解決したい課題・ペインポイント
    • 対象ユーザー(ペルソナ)
    • 期待成果・KPI・成功条件
    • 必須機能(3-5個)、推奨機能、将来機能
    • 利用シナリオ、成果物フォーマット
    • データソース・外部システム連携
  • ./assets/requirements_template.md に従いdraft_requirements.mdを生成する。
  • ./assets/framework_research_template.md に従いframework_research.mdを生成する。
  • 不確定事項はTODO形式で列挙し、合意時刻を明記する。
  • 元資料にない項目は省略せず「未記載」と明記する。

3. 構造承認

  • Flow / Stock / Archived の初期構成を説明する。
  • エージェント要件とフォルダ設計についてユーザー承認を得る。
  • 承認が得られない場合は後続工程へ進まない。

4. QC(必須)

  • recommended_subagents のQC Subagent(qa-skill-qc)に評価を委譲する。
  • Subagentは ./evaluation/discovery_criteria.md をReadし、QCを実施する。
  • 指摘を最小差分で反映する(最大3回)。
  • 指摘に対し「修正した/しない」と理由を成果物に残す。

5. バックログ反映

  • タスクリスト({{flow_day_dir}}/{{today}}_agent_creation_tasklist.md)を生成する。
  • 未決事項、次アクションをタスクリストへ追記する。
  • framework_research_done=true を記録してから次工程へ進む。

subagent_policy:

  • 品質ループ(QC/チェック/フィードバック)は必ずサブエージェントへ委譲する
  • サブエージェントの指摘を反映し、反映結果(修正有無/理由)を成果物に残す

recommended_subagents:

  • qa-skill-qc: 必須項目網羅、曖昧表現、推測混入、業界標準整合、承認確認を検査

Resources

  • questions: ./questions/discovery_questions.md
  • assets: ./assets/discovery_checklist.md
  • assets: ./assets/requirements_template.md
  • assets: ./assets/framework_research_template.md
  • assets: ./assets/tasklist_template.md
  • evaluation: ./evaluation/discovery_criteria.md
  • triggers: ./triggers/next_action_triggers.md

Next Action

  • triggers: ./triggers/next_action_triggers.md

起動条件に従い、条件を満たすSkillを自動実行する。

FAQ & Installation Steps

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

? Frequently Asked Questions

What is agent-discovery?

Ideal for AI Agents requiring structured domain-specific discovery workflows, such as those utilizing BABOK or AMA frameworks. Agent Template Framework for Domain-Specific Agent Generation - Public Version

How do I install agent-discovery?

Run the command: npx killer-skills add matsuni-kk/agent_template_public/agent-discovery. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for agent-discovery?

Key use cases include: Automating discovery workflows for new domain-specific agent creation, Generating draft requirements and framework research documents, Conducting preflight checks using discovery checklists and industry-standard frameworks like BABOK or AMA.

Which IDEs are compatible with agent-discovery?

This skill is compatible with 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. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for agent-discovery?

Requires access to industry-standard frameworks and documentation. Limited to Markdown file format for draft requirements and framework research. Needs pre-existing discovery checklists and research questions like those in discovery_questions.md.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add matsuni-kk/agent_template_public/agent-discovery. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use agent-discovery immediately in the current project.

Related Skills

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

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI