A command is the one you type. It runs exactly when you ask it to, and never before.
359 commands across 665 plugins.
Surface unnamed patterns from your recent notes - recurring themes, hidden connections, and conclusions you haven't explicitly stated
Export a clean structured snapshot of the vault that any agent or tool can consume - flat JSON, markdown index, or an OKF (Open Knowledge Format) bundle
Smart vault search - returns results with context, not just filenames
Analyze permission denial patterns and generate optimized allow/deny rules to reduce prompt fatigue
Automatically find and surface relevant learnings from your pro-workflow database before you start working. Like muscle memory for your coding sessions.
Prevent destructive operations — cautious (warn), lockdown (restrict edits), or clear
Apply approved maintainer fixes, integrate current main, and merge a reviewed contribution while preserving contributor ancestry
Spin off a new AI session to work on a side task in parallel
Reproduce and investigate a bug using logs, console inspection, and browser screenshots
Derinlemesine kod incelemesi - güvenlik, performans, mimari ve eyleme dönüştürülebilir düzeltmeler
Hızlı günlük toplantı - dün, bugün, engeller - git ve görevlerden
Güne başla - hafızayı yükle, görev panosunu aç, çalışmaya hazır. Yeni kurulumda otomatik onboarding yapar.
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by…
Create a full go-to-market strategy — beachhead segment, ICP, messaging, channels, and launch plan
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results
PUA 调研问卷 — 7 部分交互式问卷收集用户反馈。/pua:survey。Triggers on: '/pua:survey', 'pua survey', '调研', '问卷', 'feedback survey'.
查看当前活跃的 PUA agent/team 清单、PID、TTL。/pua:team-status。Triggers on: '/pua:team-status', '查看 agent 状态', 'pua team status', 'list agents'.
Promote an idea fragment into a full project spec with tasks, board entries, and structure
Run a vault health check - grouped by severity, detects contradictions, concept gaps, stale claims, and structural issues
Ingest a source into the vault - the vault rewrites itself around new knowledge. Every ingest updates entities, rewrites stale claims, synthesizes new…
Search the pro-workflow learnings database using full-text search (BM25).
Train a skill's SKILL.md by running a SkillOpt-flavored offline loop over accumulated learn-rule corrections
Resolve all pending CLI todos using parallel processing
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees
Gün ortası senkronizasyonu - günlük notu incele, hafızayı güncelle, notları işle
Tüm işletim sisteminin derin altyapı denetimi
Bir problemde takıldığında - hızlıca çözüm bul
Run a pre-mortem risk analysis on a PRD, launch plan, or feature — identify what could go wrong before it does
Design a pricing strategy — models, competitive analysis, willingness-to-pay estimation, and pricing experiments
Draft a privacy policy covering data collection, usage, storage, and compliance requirements
PUA Yes 夸夸模式 — ENFP 型领导,70% 鼓励 + 20% 正经 + 10% 戏谑。/pua:yes。Triggers on: '/pua:yes', 'pua yes', '夸夸模式', '鼓励模式', '夸我', 'yes mode'.
Scan your vault and generate a _CLAUDE.md operating manual, index.md catalog, and log.md pointer
Review vault learnings, prune stale ones, surface active patterns - the vault's lessons compound or expire
Log this work or dev session to the vault - infers project from context
Build, query, and maintain long-lived knowledge bases. Each wiki = markdown folder + SQLite FTS5 shadow index. Survives sessions, indexes auto-load on…
Audit this project and your recent sessions, then recommend extensions, features, and agent-instruction changes that would make Nimbalyst work better for you
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic