ワンクリックで
cmd-gan-build
GAN pipeline: run gan-planner → gan-generator → gan-evaluator in sequence. Loops until evaluator score ≥ 7.0.
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
GAN pipeline: run gan-planner → gan-generator → gan-evaluator in sequence. Loops until evaluator score ≥ 7.0.
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
Scan installed skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files.
Audit all installed OpenClaw skills for quality: content overlap, freshness, and uniqueness. Supports Quick Scan (changed only) and Full Stocktake modes.
Cluster MEMORY.md entries by theme and optionally generate SKILL.md drafts.
Export MEMORY.md to a timestamped markdown file for sharing or backup.
Import memory entries from a markdown export file, merging with MEMORY.md without duplicating.
Show current workspace memory: MEMORY.md contents, pending recalls, and index status.
| name | cmd_gan_build |
| description | GAN pipeline: run gan-planner → gan-generator → gan-evaluator in sequence. Loops until evaluator score ≥ 7.0. |
| user-invocable | true |
| origin | openclaw-mas |
| argument-hint | <project-path> <build description> |
Run specialist agents in sequence: gan-planner → gan-generator → gan-evaluator.
Include in the task payload:
Execute specialist agents in sequence: gan-planner → gan-generator → gan-evaluator
{
"agentId": "gan-planner",
"sessionKey": "gan-planner",
"task": "<task description with full context from previous step>",
"runTimeoutSeconds": 0
}
Wait for this agent to complete before proceeding.
{
"agentId": "gan-generator",
"sessionKey": "gan-generator",
"task": "<task description with full context from previous step>",
"runTimeoutSeconds": 0
}
Wait for this agent to complete before proceeding.
{
"agentId": "gan-evaluator",
"sessionKey": "gan-evaluator",
"task": "<task description with full context from previous step>",
"runTimeoutSeconds": 0
}
Wait for this agent to complete before proceeding.
Do not spawn the next agent until the current one completes. Do not spawn agents in parallel. After all agents complete, return the final result to the user.