- Skills
- 37
- 仓库
- 1
- 职业覆盖
- 2
- 场景覆盖
- 2
- Stars
- ★ 98
POM 的 Skills 37
live_supervisor
暂无简介
jokes
暂无简介
creative
暂无简介
hello
暂无简介
vibecomfy-executor
Arnold pipeline that classifies a user query, optionally researches via Hivemind/Banodoco, optionally edits a ComfyUI workflow, and always emits a final reply.
simplify-writing
Fan out DeepSeek Pro critics and a Kimi editor to iteratively simplify a piece of writing.
folder-audit
Walk a directory tree and audit whether each folder's children belong at the right level of abstraction. Produces a structured JSON audit plus a nested Markdown annotated tree.
epic-blitz
Three-round adversarial critique of epic drafts (high / mid / low abstraction) with revision after each round. Produces a chain-ready revised epic.
deliberation
Deliberation Pipeline
deliberation
暂无简介
superfixer-debug
暂无简介
subagent-launcher
Launch an external model as a subagent for a second opinion, adversarial review, or delegated work. Default pathway is an agentic DeepSeek / Kimi / Zhipu GLM omp subagent (file/web/terminal tools, one process or fanned out N-wide); also Codex (GPT-5.5), Claude via the Agent tool, and Grok via omp (same x.ai token as the grok CLI). Use for independent root-cause analysis, cross-checking your reasoning, judge/jury panels, or handing implementation to a different model.
pipeline-babysitting
The merged babysitting protocol for the fix-the-fixer loop: a once-per-hour check-in that (1) checks for failures and repeated fixer misses, (2) runs the fixing loop — DeepSeek Flash swarm to understand, Grok for the recommendation, DeepSeek to implement, all inside sub-agents, biased toward fixing the fixer — and (3) escalates to extreme intervention when the fixer itself is stuck for structural reasons (its prompt missing, its engine broken), fixing the actual megaplan code itself with the same loop plus Grok sense-checks via the sub-agent launcher. Plus the three layers of fixing, evidence-first, minimalism, per-epic branch lineage, cost discipline, the living evidence doc, honest logging, the aspirational principles for harness improvements, and the anti-principles that cause the most pain. Use when deciding HOW to fix a stalled chain/fixer, when escalating a repeated blocker, when improving the Arnold/megaplan harness, or when reviewing whether a gate/pin/check is overzealous. Includes the one-command status tools (fixer-status, epic-board).
megaplan
暂无简介
megaplan-tickets
暂无简介
megaplan-prep
暂无简介
megaplan-observe
暂无简介
megaplan-epic
暂无简介