Каталог навыков агентов

Process multiple video generation requests efficiently with Kling AI. Use when generating multiple videos or building co...

Analyzes completed projects to identify generalizable patterns, common workflows, and reusable knowledge worth extractin...

Trace a changed claim to affected notes, decisions, and outputs and propose bounded updates with evidence. 用于结论更正后的影响检查；...

跨多个存储层（本地文件、MCP memory、向量存储、Git 仓库）的知识库管理、摄取、同步和检索。在用户想要保存、组织、同步、去重或跨知识系统搜索时使用。

Use this skill whenever working inside any of Nick's repos (under ~/Developer/) or whenever a conversation touches Nick'...

AI工作经验知识库管理。适用于用户明确要求'保存到Obsidian'、'记录这个'、'save this insight'、'memo this'、'capture this'等知识沉淀场景。将对话中的提示词、模式、问题修复、想法和效率优化...

Where a piece of MythiStone knowledge lives (the code, one short comment, a gotcha, AGENTS.md or nowhere) so that every...

Connect your OpenClaw agent to your Konteks account (konteks.app) for persistent memory, task management, and context sh...

Own an outcome until it is verifiably done, across days or months: a goal folder in Files (`goal.json`, `log.md`, `notes...

The continual-harness refinement protocol — how an agent inspects its recent trajectory for failure signatures and impro...

Guide a new Kortix user through their first session: set expectations about what Kortix is, turn a vague ask into a stro...

基于 KPI 体系管理智能体关键绩效指标与执行任务。当用户提到 KPI、指标管理、达成率、绩效复盘、评分、经验沉淀时使用，并将信息维护到 memory/kpi.md。

Kpi Dashboard Template - Auto-activating skill for Enterprise Workflows.Triggers on: kpi dashboard template, kpi dashboa...

Review soul discoveries (fixes, improvements, corrections) one by one, accept or discard each, implement accepted ones,...

Use when executing an approved Krypton plan, GOAL.md, or implementation plan that already defines intent, ownership, con...

Use when a user has a feature request, bugfix, refactor, migration, architecture change, or product goal and needs an im...

Use kspec CLI for task and spec management. Invoke when working with tasks, tracking work, capturing ideas, checking ses...

Route Kubernetes tasks to the narrowest specialist or team of specialists from the catalog. Use when you do not already...

Compare multiple approaches to a problem, evaluating trade-offs, feasibility, and alignment with constraints.

Identify, evaluate, and mitigate technical, operational, and strategic risks in proposed plans.

Break complex objectives into well-scoped subtasks with explicit dependencies and execution order.

Operate and monitor this repository's AWS DynamoDB, ADB DynamoDB API, and OCI NoSQL benchmarks through the existing dash...

Automates KYC identity verification by securely managing and submitting identity documents. Always asks user permission...

自有游戏、离线调试、状态与引擎分析

Long-duration autonomous task with checkpoints and verification. Use when: - User says "overnight", "long running", "aut...

Automate L2s tasks via Rube MCP (Composio). Always search tools first for current schemas.

Constrained optimization skill for maximizing or minimizing objectives under budgets, capacities, safety limits, equalit...

Plan and synthesize evidence-grounded product research. Use when deciding what evidence is needed, designing actor walkt...

Land requested changes, inspect available landing workflows, or manage repository landing preferences. Use for "land it"...

Develop and compare land maneuver COAs for brigade-to-platoon operations. Use when selecting axes of advance, phasing mo...

Use when building stateful multi-step agents, agent graphs, or workflows with LLMs. Triggers on: 'langgraph', 'state gra...

Plan language documentation, design recording sessions, edit annotations, curate lexical evidence, and prepare archive d...

Meta-cognitive and practical strategies for learning any language -- learner autonomy, goal setting, strategy taxonomy (...

Use when writing or reviewing Laravel code that reads, writes, invalidates or locks through the cache: cache-aside reads...

Lightweight review of last 30 days activities and accomplishments.

Research recent developments using sources published or materially updated within the last 30 days, prioritizing officia...

Lateralización de conocimiento Gentleman a otros proyectos - sync, propagación y evolución continua.

Launch readiness across every department: code, content, store, marketing, community, infrastructure, legal, go/no-go si...

Take someone from a business goal to a verified, paused-then-live Meta/Facebook/Instagram campaign without making them l...

Plan and execute a launch runbook covering pre-launch verification, go-live procedures, DNS cutover, post-launch monitor...

Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building mul...

Transform complex concepts into progressive, first-principles explanations

Use when you have raw LC/MS data in mzML or mzXML format and need to initiate untargeted metabolomics analysis.

Builds a job aid as a checklist, decision table or one-page flow, with where it lives in the workflow and who updates it...

Use when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementatio...

Qualify an inbound lead — "is this lead worth my time", "qualify this lead", "should I take this client". Applies MEDDIC...

When the user wants to build data enrichment workflows, score leads against ICP, set up Clay waterfalls, or improve cont...

Takes raw leads and enriches them to outreach-ready status. Chains company-researcher, cro-auditor, decision-maker-finde...

Use when researching prospects or accounts before outreach. Covers qualification, finding the trigger event, identifying...

Route a validated lead to direct outreach planning, nurture planning, or a recorded hold, preserving why that path was c...

Runbook for scoring and routing a new HubSpot lead to the right rep for {{projectName}} — territory matching, segment sp...

Lead Qualification And Scoring Specialist. Use to define ICP filters, score inbound and outbound leads, and improve pipe...

Set or review OKRs for a team or individual — 2-3 objectives with measurable key results, baselines and targets, aligned...

Facilitate a team retrospective in Start/Stop/Continue format on how the team works together, digging into root causes a...

Define a team's purpose, 3-5 values with concrete behaviors, and the target culture for decisions, communication and con...

This skill should be used when the user asks to "set up my league", "configure my league", "add my league settings", "up...

Run a Lean waste audit on any process, workflow, or team. Identifies the 7 wastes, maps the value stream, suggests cuts,...

Create or review lean canvas deliverables with traceable assumptions, decision criteria, ownership, and risk controls. U...

Formalize mathematical definitions, theorem statements, and proofs in Lean 4 with Mathlib. Use when converting LaTeX res...

Leap integration. Manage Organizations, Pipelines, Projects, Users, Goals, Filters. Use when the user wants to interact...

Turn a screen-recorded demonstration on your computer into a reusable skill. Use when a teach recording finishes.

Extract actionable skill knowledge from academic papers and research articles, assess credibility, run security checks,...

Learning technical topics through Socratic dialogue with Claude

Turns real agent failures, repeated prompts, team-specific workflows, and durable project lessons into better SDD skills...

Explain advanced technical decisions and implementations from the current session. Tailored for Manifesting Generator le...

Use when you need to learn a new domain rapidly, build a study plan, or master a high-stakes professional skill.

[Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows). Scans .learnings/ files on a schedu...

Promote verified, reusable engineering lessons into `.notebook/LEARNING.md`. Use when the user requests learning curator...

当用户要求复盘、沉淀经验、记录长期规则、整理 support 卡，或继续把这些候选 codify 成正式资产时使用。

Analyzes history/ directories to extract patterns, writes learned rules to .claude/rules/learned/ (auto-loaded), updates...

Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.

Design personalized learning plans for skills, topics, and career development

Help humans learn through partnership, not instruction.

Trigger: one-off /learn session, bounded explanation, learn something now. Independent answer-first teaching from suppli...

Structured learning and spaced repetition system. Use when user wants to learn a topic, start a study session, review ma...

세션에서 새로운 기술/라이브러리/개념 학습 내용을 추출하여 TIL(Today I Learned) 문서로 정리. 독립 실행 또는 daily-work-logger의 서브 에이전트로 호출 가능. "학습 정리", "TIL"...

The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per i...

Durable in-repo task state for coding agents — Kanban tasks with stable IDs, evidence-backed status marks, blocked-by de...

Render compositing and post-production capability for passes/AOVs, color management, grading, depth, bloom, denoise, mot...

Govern and integrate LeeWay automation across Runtime Fabric, Formula F8, n8n, Home Assistant, Device Bridge, agents/wor...

Plans and executes a strangler-fig migration route by route, with parity checks. Use when the task involves legacy-moder...

Legal umbrella skill. Use when Codex should emphasize obligations, risk, and missing protections in documents or decisio...

Swiss legal intake — transforms vague or complex queries into actionable execution plans. Two modes: **Refine** (single-...

Review the intellectual property terms in an agreement — background and foreground IP, assignment and work-for-hire, lic...

Search Korean laws and precedents via local hybrid index (FTS + vector). USE FOR: 법률 검색, 판례 검색, semantic search, zmd que...

Generate a mutual or one-way Non-Disclosure Agreement — definition of confidential information, standard exclusions, per...

Research a legal question with jurisdiction, date, procedural posture, current primary law, authoritative guidance, dead...

Check operational concepts for legal and ROE alignment. Use when reviewing targeting, detention, collection, and escalat...

Automate Leiga tasks via Rube MCP (Composio). Always search tools first for current schemas.

Gestión de memoria del ecosistema — guarda, consulta y organiza información en Engram para mantener contexto permanente...

Übt evidenzbasierte Lernstrategien für das Jurastudium — Spaced Repetition, aktiver Abruf (Retrieval Practice), Interlea...

Use on EVERY response, always, with no exception. Requires each claim about a file, command, output, tool, service, test...

Process chat sessions into durable lessons — walk unprocessed transcripts (Claude first; other lanes as enumerators land...

Interactive lesson-level quiz for Claude Code tutorials. Tests understanding of a specific lesson (01-10) with 8-10 ques...

Record a lesson learned after a user correction, or review existing lessons at session start

Manage lessons learned with global scope