Kit4Some

22 verified skills44 total stars

skills/code-review

--- name: code-review description: > Multi-pass code review with scope drift detection and Fix-First heuristic. Triggers on "코드 리뷰", "리뷰해줘", "PR 확인", "code review", "review this", "check my code", "review PR", "코드 검토". Pass 1 auto-fixes mechanical issues; Pass 2 security audit; Pass 3 flags judgment-required items. WTF-likelihood safety gate. allowed-tools: - Bash - Read - Edit

tools2

skills/autonomous-ops

--- name: autonomous-ops description: > 24/7 autonomous operation loop combining OMC multi-agent orchestration with OpenClaw-CC's messenger and scheduler. Triggers on "자율 모드", "autonomous", "24/7 모드", "자동 운영", "autonomous mode", "self-driving", "unattended" and similar requests. Polls messenger for user requests, analyzes tasks, dispatches OMC teams for execution, persists results t

documentation2

skills/careful

--- name: careful description: > Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. Triggers on "careful", "조심", "안전 모드", "prod mode", "safety mode", "프로덕션 모드", "be careful", "careful mode". allowed-tools: - Bash - Read hooks: PreToolUse: - matcher: "Bash" hooks:

tools2

skills/deep-research

--- name: deep-research description: > Multi-agent deep research with parallel execution and knowledge graph integration. Triggers on "심층 조사", "deep research", "thorough investigation", "comprehensive analysis", "깊이 파봐", "detailed study", "in-depth research" and similar requests. Spawns multiple research agents in parallel, synthesizes via analyst, deduplicates against existing know

documentation2

skills/freeze

--- name: freeze description: > Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Triggers on "freeze", "편집 제한", "이 폴더만", "restrict edits", "only edit this folder", "lock down edits", "범위 제한". allowed-tools: - Bash - Read - AskUserQuestion hooks: PreToolUse: - matcher: "Edit" hooks: - type: command

tools2

skills/investigate

--- name: investigate description: > Systematic debugging with root cause investigation. Six stages: investigate, reproduce, analyze, hypothesize, implement, verify. Iron Law: no fixes without root cause. Triggers on "디버깅", "버그 찾아", "investigate", "왜 안 돼", "debug", "find the bug", "root cause", "에러 분석". allowed-tools: - Bash - Read - Write - Edit - Grep - Glob - Agent

tools2

skills/knowledge-refiner

--- name: knowledge-refiner description: > Memory refinement with OMC team pipeline. Triggers on "메모리 정리", "지식 정리", "중복 제거", "refine", "메모리 최적화", "memory cleanup", "deduplicate", "optimize memories", "consolidate" and similar. v3: Uses OMC analyst agent for detection, executor for merge execution, verifier for confirmation. Reports via messenger. Runs as nightly cron task automatica

devops2

skills/knowledge-sync

--- name: knowledge-sync description: > Bidirectional synchronization between OMC's project-memory and OpenClaw-CC's persistent memory store. Triggers on "지식 동기화", "sync memory", "knowledge sync", "메모리 동기화", "OMC 동기화", "synchronize", "sync state" and similar requests. Ensures knowledge is shared across both systems — OMC's ephemeral state becomes persistent, and OpenClaw-CC's long-t

documentation2

skills/memory-ops

--- name: memory-ops description: > Unified memory interface with associative search and OMC integration. Triggers on "기억해", "저장해", "메모리", "뭐였지", "지난번에", "기록해", "잊지마", "정리해", "요약해줘", "remember", "save", "store", "what was it", "last time", "record this", "don't forget", "organize", "summarize" and similar. v3: Default to associative search mode (5-signal ranking). Uses memory-specia

testing2

skills/qa

--- name: qa description: > Systematically QA test code and fix bugs found. Run tests, find failures, fix them with atomic commits, re-verify. Triggers on "qa", "QA", "테스트", "find bugs", "test and fix", "버그 찾아서 고쳐", "품질 검사". Three tiers: Quick (critical/high), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and ship-readiness summary.

development2

self-optimize

Self-optimization loop that analyzes system performance, identifies failure patterns, and improves skill prompts autonomously. Triggers on "자기 최적화", "self-optimize", "시스템 개선", "성능 분석", "optimize yourself", "improve yourself", "evolve", "자가 개선", "스스로 개선해" and similar requests. Also runs weekly via cron. Reads error/success logs from memory, identifies weak skills, rewrites prompts, commits changes, and tracks improvement over time. Includes automatic rollback if metrics worsen.

documentation2

skills/session-tracker

--- name: session-tracker description: > Session context tracking with OMC state bridge. Triggers automatically at session start or on "마지막 세션", "이전 작업", "어디까지 했지", "last session", "continue where I left off", "resume work" and similar. v3: Dual-writes to both OMC state (notepad/project-memory) and OpenClaw-CC persistent memory. Uses session-manager agent for cross-system continuity

documentation2

skills/ship

--- name: ship description: > Automated release workflow with comprehensive quality gates. Triggers on "배포", "릴리스", "ship it", "PR 만들어", "release", "deploy", "create PR", "push this", "ship". Non-interactive: user says /ship, next thing they see is the PR URL. Delegates commit organization to OMC git-master, review to code-reviewer, verification to verifier. Sends PR notification vi

development2

skills/task-analyzer

--- name: task-analyzer allowed-tools: - Bash - Read - Write - Edit - Glob - Grep - Agent - AskUserQuestion - WebSearch description: > Autonomously analyzes and executes tasks with a structured plan. Triggers on "분석해", "작업 계획", "이거 해줘", "자동으로 처리해", "계획 세워", "workflow 만들어", "analyze", "task plan", "do this", "handle automatically", "make a plan", "create a workflow",

tools2

skills/unfreeze

--- name: unfreeze description: > Remove edit scope restriction set by /freeze or /guard. Triggers on "unfreeze", "편집 제한 해제", "잠금 해제", "remove freeze", "unlock edits". allowed-tools: - Bash - Read --- # /unfreeze — Remove Edit Restrictions ## Preamble Before executing this skill: 1. **Load context from memory**: ``` memory_search(query: "{skill-relevant-query}", associative:

tools2

skills/web-researcher

--- name: web-researcher description: > Web research with OMC team parallel execution. Triggers on "웹에서 찾아", "최신 정보", "리서치해", "동향", "web research", "find online", "latest info", "look up", "search the web", "trend analysis" and similar. v3: Spawns research-agent in parallel for multi-angle search. Deduplicates via memory_similar. Builds knowledge graph connections. For comprehensive

development2

skills/research-collector

--- name: research-collector description: > Automated web research pipeline with OMC integration. Triggers on "조사해", "수집해", "리서치", "찾아봐", "동향 파악", "경쟁사 분석", "뉴스 모아", "트렌드 분석", "research", "collect", "find out", "trend analysis", "competitor analysis" and similar. v3: Delegates to research-agent for parallel collection, uses memory_similar for deduplication, builds knowledge graph co

development2

skills/doc-fetcher

--- name: doc-fetcher description: > API/SDK documentation fetcher via Context Hub MCP + web fallback. Triggers on "API docs", "SDK docs", "docs for X", "how to use X", "documentation", "API reference", "API 문서", "라이브러리 사용법", "패키지 문서" and similar. Uses chub MCP tools (chub_search, chub_get) for curated registry access. Falls back to web search when unavailable. Progressive Disclosur

tools2

skills/guard

--- name: guard description: > Maximum safety mode — activates both /careful (destructive command warnings) and /freeze (edit scope restriction) together. Triggers on "guard", "가드", "최대 안전", "max safety", "maximum safety", "안전 모드 풀". allowed-tools: - Bash - Read - AskUserQuestion hooks: PreToolUse: - matcher: "Bash" hooks: - type: command command: "ba

tools2

skills/daily-routine

--- name: daily-routine description: > Daily routine automation skill with OMC integration. Triggers on "오늘 할일", "데일리", "모닝 브리핑", "오늘 일정", "할일 정리", "하루 마무리", "이번주 요약", "today's tasks", "daily", "morning briefing", "today's schedule", "organize tasks", "wrap up the day", "end of day", "weekly summary", "weekly review" and similar. v3: Polls messenger at start, includes OMC team statu

tools2

skills/retro

--- name: retro description: > Engineering retrospective with git + memory data analysis. Triggers on "retro", "회고", "weekly retro", "이번 주 리뷰", "what did we ship", "엔지니어링 회고", "주간 회고", "지난주 리뷰". Analyzes commits, memory activity, work patterns. Persistent history with trend tracking. allowed-tools: - Bash - Read - Write - Glob - AskUserQuestion --- # /retro — Engineering

tools2

skills/office-hours

--- name: office-hours description: > Idea validation and design brainstorming. Two modes: Startup (6 forcing questions for demand validation) and Builder (generative brainstorming for side projects). Triggers on "브레인스토밍", "아이디어", "이거 만들어볼까", "office hours", "brainstorm", "help me think through", "is this worth building", "사업 아이디어". Produces a design document saved to memory. No cod

development2

Kit4Some

skills/code-review

skills/autonomous-ops

skills/careful

skills/deep-research

skills/freeze

skills/investigate

skills/knowledge-refiner

skills/knowledge-sync

skills/memory-ops

skills/qa

self-optimize

skills/session-tracker

skills/ship

skills/task-analyzer

skills/unfreeze

skills/web-researcher

skills/research-collector

skills/doc-fetcher

skills/guard

skills/daily-routine

skills/retro

skills/office-hours

Adoption

Kit4Some

skills/code-review

skills/autonomous-ops

skills/careful

skills/deep-research

skills/freeze

skills/investigate

skills/knowledge-refiner

skills/knowledge-sync

skills/memory-ops

skills/qa

self-optimize

skills/session-tracker

skills/ship

skills/task-analyzer

skills/unfreeze

skills/web-researcher

skills/research-collector

skills/doc-fetcher

skills/guard

skills/daily-routine

skills/retro

skills/office-hours