Cron Jobs Stalled
Diagnose and recover cron jobs in jobs.json that stopped running (next_run_at=null, no recent execution). Distinguishes scheduler bug vs script quality issue. Applies 60-second recovery patch.
Harsh Critic
A Claude skill from humanerd-drew/opencode-drewgent.
{{AGENT NAME LOWER}} Runtime Checkup
{{AGENT_NAME}} 코어 시스템 (AIAgent, signal, kanban, dispatcher, worker) 의 기본기를 점검하는 6-Phase 절차. docs와 reality mismatch 발견 시 methodology.
Brain Signal System
Drewgent brain signal architecture — event bus, signal processor, awareness reporter, brain monitor
Daily Retro
매일 Discord로 작업 요약 + 회고 질문 발신, 사용자 답변을 vault에 구조화하여 저장. 30/70 rule 적용.
Vault Health
Maintain .drewgent as an Obsidian vault — graph connectivity overhaul (P-layer mesh, skill clusters, SEO article web), broken link detection, backlink density verification via Obsidian CLI, filename deduplication, bidirectional linking, auto-generated orphan management, cron output graph bloat prevention, and Obsidian compatibility.
Tool Integration Protocol
A Claude skill from humanerd-drew/opencode-drewgent.
Opencode Knowledge Convention
A Claude skill from humanerd-drew/opencode-drewgent.
Content Pipeline
{{AGENT_NAME}} content pipeline - editorial topic selection, draft writing, Korean humanization, review-ready publishing
Harvester Memory Sync
Sync trend-harvester analyzed output to P2-hippocampus memories — bidirectional bridge between P4-cortex growth engine and P2-hippocampus long-term memory
Kanban Dispatcher Hardening
{{AGENT_NAME}} kanban dispatcher의 logfile redirect + dead worker watchdog 적용 skill. PIPE deadlock 회피, dead worker 즉시 reclaim.
Content Management
>
Skill Gym
A Claude skill from humanerd-drew/opencode-drewgent.
Agent Dashboard Cf
{{AGENT_NAME}} 에이전트 상태를 Cloudflare Workers + KV로 호스팅. 4-tab insight-driven dashboard (Overview/System/Brain/Usage) + live agent activity + 23 collectors
Kanban Orchestrator
Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
N8n Password Reset
A Claude skill from humanerd-drew/opencode-drewgent.
Memory Md Cleanup
Clean up {{AGENT_NAME}}'s persistent memory file (MEMORY.md) when it nears the 8K char cap. Identify resolved/one-time entries, preserve operational facts, verify after.
N8n Self Hosted Diagnostics
A Claude skill from humanerd-drew/opencode-drewgent.
Ontology Query
A Claude skill from humanerd-drew/opencode-drewgent.
Agent Profiles
Authoring and using agent profiles — pre-defined subagent roles that set model, provider, toolsets, and instructions in one task() call. Covers profile format, the 14 standard roles, pipeline patterns, cost-tiered model assignment, and the ESCALATE mechanism for capability routing.
Macos Computer Use
|
Cron Script Fastpath
Add a script field to jobs.json + scheduler.py branch to bypass LLM for simple shell cron jobs (cost + reliability). Reusable pattern for any 'Run: python3 xxx.py' style cron.
Vault Naming Convention
Filename uniqueness, wikilink resolution safety, P-layer identity in naming, and Obsidian exclusion boundaries. Prevents duplicate-name ambiguity and graph pollution.
Qa Cycle
Contract-First QA pipeline - implements 3-phase QA (contract → micro-QA → full-QA) using P2-hippocampus qa-evidence system
Content Manager
CMO-style content agent — observes work activity, produces multi-format drafts with SVG/Mermaid/Excalidraw visuals, pushes to WordPress via MCP. User-facing: 'CMO 에이전트가 내 작업을 보고 콘텐트로 만든다'.
{{AGENT NAME LOWER}} Agent
Complete guide to using and extending {{AGENT_NAME}} Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure {{AGENT_NAME}}, troubleshoot issues, spawn agent instances, or make code contributions.
Architecture Diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
Webhook Subscriptions
Manage webhook subscriptions — register, verify, rotate, and monitor webhook endpoints for external service integrations.
Im Not Ai
AI(ChatGPT·Claude·Gemini)가 쓴 한글 텍스트를 사람이 쓴 글처럼 윤문한다. 번역투·영어인용·기계적병렬·AI관용구·피동태·접속사·리듬균일·이모지 등 10카테고리 60+ 패턴 탐지. 'AI 티 없애줘', '번역투 고쳐', '사람이 쓴 것처럼' 트리거.
Session Pattern Archiver
A Claude skill from humanerd-drew/opencode-drewgent.
Trend Harvester
AI Trend Collection & Filtering — collect GitHub trending repos, score via 5-axis philosophy filter, evaluate, apply, and retire.
Self Replicating Agent Tdd
TDD-PDCA plan for building a self-replicating branching agent in Drewgent. 단일 에이전트가 스스로 서브에이전트를 분기하고, 결과를 수렴시키는 구조.
Goose Acp Integration
Integrate Drewgent with ACP (Agent Client Protocol) agents. Reverse-engineered from goose's Rust ACP provider implementation.
Kanban Stuck Task Recovery
A Claude skill from humanerd-drew/opencode-drewgent.
Acp Thinking Spinner
Add a "Thinking..." spinner card to an ACP server's tool-call stack so ACP clients (Zed Agent Panel, openCode TUI, JetBrains/VS Code ACP UI) show a working indicator during the LLM API call phase. Triggers when working on an Agent Client Protocol (ACP) server and the user wants LLM-thinking visibility in the client's tool-call stack.
Wordpress Cms
WordPress CMS setup on Docker + Blocksy theme + MCP integration for autonomous content publishing
Kanban Worker
Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
Brain Dashboard System
A Claude skill from humanerd-drew/opencode-drewgent.
Cloudflare Workers Local Dev
Patterns, pitfalls, and workflows for local Cloudflare Workers development with D1, static assets, multi-source integration, and the m-log refactoring architecture.
Launchd Process Health Check
A Claude skill from humanerd-drew/opencode-drewgent.
Qa Scenario Gen
Generate test scenarios and acceptance criteria from user requirements
Semblent Search
Semantic code search using Semble — find code by intent rather than exact matches. Use when exploring unfamiliar codebases or searching for patterns that are hard to express as regex.
Minimax Usage
A Claude skill from humanerd-drew/opencode-drewgent.