2.4K skills · sorted by relevance
Turn a vague idea into a concrete, actionable spec through a short Socratic dialogue, then hand the result off to an existing moflo surface — a /flo ticket, a spell, or memory. Use BEFORE you have a defined unit of work, when the goal is still fuzzy.
The English summary is being prepared. Showing the original description.
Consult the Eldar — audit a project's moflo + Claude Code setup for portable, high-leverage gaps and guide remediation. Default mode is read-only audit with severity-ranked findings; --fix presents an interactive triage menu and walks the user through each chosen fix (healer, missing CLAUDE.md, sparse guidance, hook/MCP wiring, empty memory namespaces, stack→guidance gaps). Use when starting in a new project, when Claude feels lost or inefficient, when guidance/CLAUDE.md is sparse, or as a periodic health check.
The English summary is being prepared. Showing the original description.
Structured multi-hop web research with explicit confidence gating — plan the inquiry, search (WebSearch/WebFetch), score your own confidence, and keep digging until the answer is well-supported or a hop cap is hit, then emit a cited synthesis. Learns across sessions by storing each research case to memory and reusing prior strategies. Use when a question needs more than one search — comparisons, current-best-practice questions, anything where a single lookup leaves you unsure.
The English summary is being prepared. Showing the original description.
Quicken the codebase — an ad-hoc performance audit that reveals what drags (N+1 queries, needless re-renders, missing caching, memory leaks, redundant computation, hot-path complexity) and prescribes the fix, surfaced inline in the session. Scoped to your current diff by default, or to a path/area you name. Use before a perf-sensitive merge, when something feels slow, or when you want a targeted optimization pass. Replaces the old always-on `optimize` daemon worker (alias: /perf-audit).
The English summary is being prepared. Showing the original description.
Adaptive learning for moflo agents via ReasoningBank: trajectory storage, verdict judgment, memory distillation, consolidation, and MMR retrieval. Use when building agents that should improve from experience across runs.
The English summary is being prepared. Showing the original description.
Learn project rules from accumulated fix patches in .unikit/code/patches/. Analyzes past mistakes, extracts prevention points, classifies each as a coding rule (→ RULES.md) or a per-skill workflow rule (→ skill-context), and proposes them for approval. Use when the user wants to turn past fixes into rules — "evolve", "evolve the rules", "learn from past mistakes", "learn from the fixes", "analyze the patches", "what rules should we add from recent fixes". Best run after several /unikit-fix sessions have left patches behind. This derives rules from accumulated patch history — to add a single rule by hand use /unikit-rules, and to promote mature RULES.md entries into the knowledge base use /unikit-memory migrate-rules.
The English summary is being prepared. Showing the original description.
Persistent, adaptive vector memory for agents on a ruOS desktop — a Rust-native vector database with local semantic embeddings, HNSW retrieval, and graph relationships. Use to remember and recall across sessions with no database server or API key.
The English summary is being prepared. Showing the original description.
MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles from orthogonal angles, confirm root cause, lock with a failing test, fix minimally, QA by actually USING the system, scrub artifacts. The actual HOW lives in `references/` — READ THEM. Triggers: 'debug this', 'why is X not working', 'hanging', 'attach a debugger', 'reverse engineer', 'pwndbg', 'gdb', 'lldb', 'node inspect', 'tsx debug', 'pdb', 'dlv', 'delve', 'rust-gdb', 'set a breakpoint', 'context window exploded', 'why is the response empty', 'attach the debugger', 'debug it', 'why is this happening', 'trace this bug', 'reproduce and fix', 'silent failure', 'HTTP 200 but empty', 'why did it stop', 'inspect the binary', 'reverse engineering', 'playwright'.
The English summary is being prepared. Showing the original description.
Comprehensive Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents and workflows. Covers documentation lookup strategies (embedded docs, remote docs), core concepts (agents vs workflows, tools, memory, RAG), TypeScript requirements, and common patterns. Use this skill for all Mastra development to ensure you're using current APIs from the installed version or latest documentation.
The English summary is being prepared. Showing the original description.
Pre-compaction housekeeping. Walks a checklist (persistent memory updates, git hygiene, trash cleanup) plus an open-judgment audit, produces an SBAR with a go/no-go recommendation, and emits a copy-pasteable resume prompt for the post-compaction agent if work remains. Run this immediately before /compact.
The English summary is being prepared. Showing the original description.
Design AI-first interfaces that build ongoing relationships through memory, trust evolution, and collaborative planning, not just isolated screen interactions
The English summary is being prepared. Showing the original description.
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
The English summary is being prepared. Showing the original description.
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
The English summary is being prepared. Showing the original description.
Design, build, deploy, and operate production AI agent systems — single agents, multi-agent teams, and autonomous swarms. Complete methodology from agent architecture through orchestration, memory systems, safety guardrails, and operational excellence.
The English summary is being prepared. Showing the original description.
Implements the Active Learning Protocol (R3). Allows the agent to programmatically internalize lessons into MEMORY.md and generate structured "ask for help" requests.
The English summary is being prepared. Showing the original description.
Error pattern tracking for AI agents. Detects corrections, escalates recurring mistakes, learns mitigations. The 'something's off' detector from the AI Brain series.
The English summary is being prepared. Showing the original description.
Design, configure, debug, and optimize OpenClaw AI agent deployments. Master guide for gateway configuration, openclaw.json settings, model routing and fallback chains, skills development and publishing, cron job scheduling, memory systems (Qdrant, Neo4j, SQLite), Docker infrastructure, and Tailscale VPN networking. Includes config analyzer that audits your openclaw.json and suggests improvements, plus health checker that validates all OpenClaw subsystems. Built for AI agents — Python stdlib only, no dependencies. Use for OpenClaw setup, gateway debugging, skill building, cron management, model optimization, cost reduction, and infrastructure troubleshooting.
The English summary is being prepared. Showing the original description.
Structured memory system for OpenClaw agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, local semantic search, and session transcript repair.
The English summary is being prepared. Showing the original description.
Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or choose between local planning and persistent project tracking.
The English summary is being prepared. Showing the original description.
融合单元的范围判定与收益前置评估：判定「哪些计算该被融进同一个融合单元、边界画在哪、 融了值不值」。结构侧按融合单元构造规则切边界——函数边界即候选组；FA（含 BSA 等变种）为 禁融锚点；以 norm / rope / FA 为分界分区，全 Vec 区域优先试融；区域内有 Cube 时以 Cube 为 首算子向后包裹 Vec（Σvec 小于 cube 或遇下一 Cube 封口）；一轮之后纯 Vector 单元之间再迭代； MLP / MoE 以矩阵乘族（MatMul / BatchMatMul / GroupedMatmul）为界；若该段计算已由单个 融合算子承载，按规则 6 先确认载体是否已生效（不重复建单元）。 收益侧按计算单元利用率判型（memory_bound、*_vec|mac|mte2|mte3_ratio、cube_utilization）， 叠加带宽下限 / 区域占比 / 天花板法 / 地板先行 / Amdahl 传导校验给出 go/no-go。 当用户问「这几个算子能不能融成一个」「融合边界画在哪」「融多大范围」「融了值不值得」， 或 profiling-analyze 给出融合机会候选需要定范围与收益时使用；即使用户只说「这条链要不要 合成一个 kernel」「这里能不能省一次读写」也应触发。 **已经做完、实测收益却打平或为负时同样触发**——此时的任务不是接受"融合无收益"， 而是按事后复核做**等功忙计数对照**归因，并在缺陷落在融合核自身时**升级 operator-dev**。 边界：只出「融合单元草案 + 收益判定 + 否决理由」。不做采纳与选点（dit-perf-opt 依收益选 top 并派活）、不做采集与瓶颈定位（profiling-collect / profiling-analyze）、不写 kernel、不写 pattern、 不做使能与并行选型、不定义验收标准（引 accuracy-gate / perf-gate）。 由 profiling-analyze（融合机会候选）与 operator-dev（实现前的收益评估）调用。
The English summary is being prepared. Showing the original description.
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.
The English summary is being prepared. Showing the original description.
Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.
The English summary is being prepared. Showing the original description.
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.
The English summary is being prepared. Showing the original description.
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
The English summary is being prepared. Showing the original description.