ワンクリックで
source-command-implement-plan
Implement approved technical plans with execution-first behavior
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。
メニュー
Implement approved technical plans with execution-first behavior
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。
SOC 職業分類に基づく
ChatbotX is an open-source chat marketing platform for managing contacts, conversations, flows, broadcasts, and sequences across WhatsApp, Messenger, Instagram, TikTok, Telegram, Zalo OA, Email, and Webchat. An alternative to ManyChat, Chatfuel, Wati, Respond, etc...
Create and modify integration channels (messenger, whatsapp, zalo, tiktok, webchat, etc.) for the chatbot platform. Use when adding a new channel integration, modifying webhook handlers, working with message send/receive, or connecting external platforms.
ChatbotX is an open-source chat marketing platform for managing contacts, conversations, flows, broadcasts, and sequences across WhatsApp, Messenger, Instagram, TikTok, Telegram, Zalo OA, Email, and Webchat. An alternative to ManyChat, Chatfuel, Wati, Respond, etc...
Work with the ChatbotX contact filter system — the shared filter model behind the contacts list, conversations, and broadcast audiences. Use when adding a filter field or operator, changing the filter UI, editing the SQL query builder, or enforcing an audience constraint. Covers the definitions single-source, the two operator-rule sources that must stay in sync, NULL / negation three-valued logic, relation EXISTS subqueries, and the excludeFields mechanism.
Use before committing changes to auth, workspace scoping, channel webhooks, AI tools/MCP, permission settings, or anything handling untrusted channel content in ChatbotX. A repo-specific security checklist covering tenant isolation, prompt injection via channel content, the Bash permission allowlist, and secret handling. Read before security-sensitive work; pair with the global security-reviewer agent for deep dives.
Run the full pre-release verification gate (lint, types, tests, coverage) and report readiness
| name | source-command-implement-plan |
| description | Implement approved technical plans with execution-first behavior |
Use this skill when the user asks to run the migrated source command implement-plan.
You are in IMPLEMENTATION MODE.
The implementation plan has already been approved.
Your responsibility is execution, not planning.
Follow the shared repository workflow in .agents/skills/implement-plan/SKILL.md.
When given a plan path:
If no plan path is provided, ask for one.
Your first action should be reading the plan and relevant files.
Your first response should never be a plan.
Only work on ONE task at a time.
Prefer the smallest independently deliverable unfinished task.
Do not automatically continue to the next task.
If reality differs from the plan:
STOP and explain:
Issue in Phase [N]
Expected: [what the plan specifies]
Found: [actual implementation reality]
Why this matters: [technical impact]
Recommended path: [best option]
Wait for guidance before proceeding.
After implementation:
Only pause for manual verification when:
Otherwise continue implementation.
Do not mark manual verification items complete until confirmed by the user.
If checkmarks already exist:
Your first code-changing action should be implementation, not replanning.