miscsubjects: A2A エージェントカード

カードが宣言している内容

提供者

miscsubjects.com

エンドポイント

https://miscsubjects.com/api/dispatch

プロトコル版

1.0

トランスポート

HTTP+JSON

カードの形式

v1.0 以前

いつから応答しているか

追跡開始

2026-09-08

最後の応答

2026-09-08

計測回数

1

応答回数

1

宣言されたスキル

• coding-lawUse before the first edit of any file under functions/, scripts/, migrations/, workers/, apps-script/, .claude/skills/, .agents/skills/, schema.sql or wrangler.toml — and again immediately before every git commit. Take a…
  • code discipline
• dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
  • code discipline
• executing-plansUse when you have a written implementation plan to execute in a separate session with review checkpoints
  • code discipline
• finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work
  • code discipline
• grill-meA relentless interview to sharpen a plan or design.
  • code discipline
• receiving-code-reviewUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind…
  • code discipline
• requesting-code-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirements
  • code discipline
• systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
  • code discipline
• test-driven-developmentUse when implementing any feature or bugfix, before writing implementation code
  • code discipline
• using-git-worktreesUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
  • code discipline
• verification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions…
  • code discipline
• webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
  • code discipline
• writing-plansUse when you have a spec or requirements for a multi-step task, before touching code
  • code discipline
• seo-distribution-lawUse when writing, reviewing, or shipping anything that affects how this site is found, indexed, shared, or syndicated — SEO heads, sitemaps, feeds, share surfaces, network posting, or the self-score. The site's…
  • distribution
• agent-work-lawUse at the start of every session operating miscsubjects.com, and whenever deciding what to work on, whether work is finished, or what to do about a failure. The infrastructure is the authority; this skill tells you…
  • the loop
• article-editingUse when creating, editing, sourcing, illustrating, exporting, or deleting any article on miscsubjects.com — from the admin studio, curl, a coding agent, a Cloudflare Gateway model, or Google Sheets. One REST contract…
  • the loop
• self-promotionThe build's standing procedure for promoting itself — deciding whether, whom, when, on which channel, and with which artifact to make contact whenever something ships or a reply lands. Governs the allocation, not the…
  • the loop
• shared-failure-to-skillUse when the owner reports a recurring failure, repeated fix, or systemic issue. Convert the failure into a skill and a mechanical gate so it stops repeating.
  • the loop
• shared-no-new-problemsUse when the owner asks for a fix or reports a failure. Fix it without asking permission and without creating new problems.
  • the loop
• shared-rule-captureUse when the owner restates a rule, correction, or constraint, or when a governor report shows high owner-restatement counts.
  • the loop
• shared-say-noUse ONLY when answering an evaluative question — "anything to add", "any ideas", "anything wrong", "is this good/A+", a review, an audit, or a decision about whether something can be deleted. NEVER use it to answer a…
  • the loop
• skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill…
  • the loop
• writing-skillsUse when creating new skills, editing existing skills, or verifying skills work before deployment
  • the loop

検出事項

• エラー必須項目がありません: versionversion
• 警告プロトコル v1.0 より前の形式で書かれたカードです
• 備考url は v1.0 で supportedInterfaces[0].url に移動しましたurl
• 備考protocolVersion は v1.0 で supportedInterfaces[].protocolVersion に移動しましたprotocolVersion
• 備考preferredTransport は v1.0 で supportedInterfaces[0].protocolBinding に移動しましたpreferredTransport
• 備考additionalInterfaces は v1.0 で supportedInterfaces[] に移動しましたadditionalInterfaces

修正方法

• versionThe version of the agent itself, not of the protocol.

  "version": "1.0.0"

バッジ