Каталог навыков агентов

Delegate work to a running LibrAgent desktop/headless instance via the local HTTP Session API (`POST /api/sessions`, mes...

Open source license compliance including compatibility analysis, obligations tracking, and compliance workflows

Search jobs on Liepin, apply to positions, view and edit resumes.

Spawn transient agents with disposable identity, memory shard, and compute slot for JIT tasks. Use when you need “exist...

Hot-swap to the ephemeral model, run the atomic task, capture result, and hand it back. Use for spawn→solve→return flows...

Analyze existing research experiment results, especially after light-experiment. Use for 实验结果分析、方法比较、误差与不确定性、阴性结果、消融与机制解...

Create, refine, and audit scientific data figures in Python or R from real data, existing plotting code, or a reference...

Execute and document computational research experiments, especially after light-design. Use for 实验落地、实现并运行实验、数值仿真、训练与消融、...

Select and verify submission journals from research results, an outline, an abstract, or a manuscript. Use for 投稿选刊、期刊匹配...

Prepare evidence-backed patent invention disclosure materials for attorney or patent-agent review. Use when the user ask...

Lightpanda browser, drop-in replacement for Chrome and Openclaw default browser - faster and lighter for tasks without g...

Use for a diagram-first educational short that turns a topic or lesson material into concise narration, sparse line-dood...

Manage issues, projects, and team workflows in Linear via the Linear MCP server. Create, update, organize, and track wor...

Comprehensive workflow for managing Linear issues. Use when creating, grooming, or working on Linear issues. Handles res...

Change Linear issue statuses through the direct Linear GraphQL API using a local LINEAR_API_KEY. Use when the user asks...

Read Linear Custom Views through the direct Linear GraphQL API using a local LINEAR_API_KEY. Use when the user asks to i...

Link the current session to a Linear issue and keep it updated using the connected Linear MCP tools (no custom scripts,...

Scan all plans and wire up cross-topic dependencies. Finds unresolved external dependencies, matches them to tasks in ot...

Use when the user wants help running or growing their LinkedIn, asks what these LinkedIn skills can do, or asks for Link...

Use when finding relevant LinkedIn hiring or recruiting posts, enriching the hiring contact or company with sourced prof...

Write LinkedIn posts for Mick Pletcher's professional audience. Always trigger immediately when Mick says "linkedin post...

Write high-performing, authentic LinkedIn posts across any professional niche using research-backed hooks, proven post s...

Use when the user wants to post, publish or schedule a LinkedIn post, asks the agent to "post this for me", or asks whet...

通过 LinkFox 多维表格管理团队数据表、记录、附件、AI 图片任务和表格自动化关联。

LinkHub 세션 마무리. 문서 업데이트 분석, 후속 작업 제안, 학습 내용 정리.

Prepare, verify, publish, resume, or dry-run a LintLang release from merged main. Use for release readiness, version syn...

This skill should be used when the user asks to "provide liquidity", "create LP position", "add liquidity to pool", "bec...

List tasks from a root directory with optional filters. Supports filtering by staleness, validation state, lifecycle sta...

List all proactive background missions for the current user. Shows mission titles, schedules, statuses, and last run tim...

List all open (non-archived) tickets

Analyze and prioritize TODO items from TODOS.md. Use when planning work or deciding what to implement next.

List active GSD workspaces and their status

Golden path /listen — ingest all new signals: chronicle releases, Supabase feedback, DM exports, growth matches.

Act as a real-time multimodal music companion by listening to audio tracks and providing structural, stylistic, and lyri...

Literature: retrieve document-level scientific evidence from publications, clinical-trial registries, and patent sources...

Route and execute evidence-traceable literature research for papers, references, citations, DOI/metadata verification, Z...

Route literature tasks to PDF abstract extraction, Zotero screening, full-text reading, table export, WoS citation analy...

检索、筛选和综合科研文献，精读本地论文、翻译与核对引用，维护带来源和阅读锚点的 Literature 文献库。适用于文献调研、定向查证、论文精读、引文追踪和项目续读；按请求深度完成，不把局部问题扩成完整综述。

List project status - show open issues, recent PRs, commits, and current focus. Use when user types 'lll' or asks for pr...

Design human-visible, machine-readable website layers for AI assistants, RAG, and agentic search. Use this skill when th...

Shares KV cache from a common prefix (context+question) across multiple answer suffixes for efficient multi-choice scori...

Restructure Web-UI / human-triggered tasks into CLI + file-output loops the LLM can iterate alone, with structured logs...

Router skill for LLMQuant ETFs workflows. Use when the user needs ETF holdings, overlap, concentration, issuer snapshot,...

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

Implements safe error boundaries, cancellation and user recovery contracts; not telemetry pipelines or durable retry mac...

Implements structured diagnostics, correlation and justified metrics or traces; not incident investigation or a mandator...

Lightweight triage for the ln-* skill set. Use when unsure which ln skill to use next, starting work on something new, o...

Break a feature or project area into frontier items and update `memory/PLAN.md`. Re-run to retire completed work, reorde...

Throwaway design probe for logic, state models, UI variations, and affordances before production work. Use when the user...

Crystallize shared understanding into a reviewable spec, or update an existing one. Use when the problem needs a written...

Discover and read all architecture decision records applicable to the current scope, following repository guidance and n...

Lobster executes multi-step workflows with approval checkpoints. Use it when:

Use when a build must reach TestFlight without Xcode Cloud (quota, outage, CI not wired yet), or when a local `xcodebuil...

ルールをプロジェクトに最適化。郷に入っては郷に従え精神。Use when user mentions localizing rules, adapting rules to project, or customizing templates...

Agentic PRD batch: when user says 'process PRDs' or 'run batch from PRD folder'; implement per spec; update status; writ...

Record deferred ideas, to-dos, and reminders (with optional due date or 'whenever'); show due/overdue when user starts a...

Manage cron from a repo-local manifest: time triggers, on-boot-with-delay, sequenced tasks; create, remove, reorder, ins...

Decision tree / reverse prompt workflow - AI prompts user one question at a time with 4 options (A-D), preferred choice...

Pre-task workflow, certainty assessment, context load, document status, testing, Git checkpoints, document maintenance....

Capture front door. Logs 1..N observations as card files at docs/work/{ID}.md (BUG / DEBT / GAP), gateway-inline — no di...

Log conversation activity to today's daily note on demand. Use when wrapping up work, capturing decisions, or documentin...

Log entries to the current learning session. Use mid-session to save progress, capture concepts learned, or record corre...

Work a site's SEO and AI-visibility (GEO) backlog through the hosted LogNorm MCP server: audits, fixes, content, AI-answ...

Version 2.35.0 | PRD to Production | Zero Human Intervention > Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS B...

Protocol for reliable multi-hour task execution with automatic checkpointing, validation, and recovery

PRIMARY skill for clock-based session wakes via scheduleCallback. Use when the user asks for reminders, delays, or recur...

Load when the user asks for a repeating autonomous mode: "loop 10 30m <prompt>", "loop 99 6666 <prompt>", "work cycle af...

Systematically address AI and human review feedback on PR stacks. Triage issues, fix valid ones, respond to comments, re...

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them. Use whe...

Use when a long task has drifted into a frame the agent built for itself and stopped serving the owner's goal, even thou...

Use when an agent loop is about to be built or reviewed (fix until green, process a queue, keep a state healthy): is the...

Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal...

Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, ver...

Find, compare, adapt, and design bounded AI-agent feedback loops with explicit checks, stop rules, guardrails, and hando...

Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, a...

Define a platform-neutral bounded loop for standard or deep work using measurable acceptance criteria, verification, ret...

Set up recurring agent loops or cron tasks with the right pacing, idempotency, and stop conditions. Use for daily, weekl...

Use when a task involves integrating a backend with the Loops API or official SDK for contacts, events, lists, or transa...

Use when a task involves planning transactional or lifecycle email delivery through Loops with accurate event, consent,...

Search and ingest knowledge from Lore, a research repository with citations

Build compact Codex task context and avoid token blowups. Use when work spans large repos, repeated sessions, long logs,...

Produce a <YYYY-MM-DD>-naming-generation-spec.md for a business. Reads ASSESSMENT stage docs, extracts ICP, product, bra...

Inventory wrapper for the Antigravity awesome skills bundle. Use when evaluating that large bundle before selecting narr...

Guide architecture analysis and decision records. Use for ADRs, tradeoff review, boundaries, dependencies, data flow, an...

Inventory wrapper for Composio skills. Use when evaluating Composio tool integrations, OAuth scopes, and connected-accou...

Guide conversion-rate optimization patterns. Use for signup flows, landing pages, pricing pages, onboarding, experiments...

Guide email sequence planning and writing. Use for lifecycle, onboarding, nurture, launch, winback, and sales email sequ...

Guide GitHub Actions workflow authoring. Use for CI, release, scheduled jobs, permissions, caching, matrices, artifacts,...

Comprehensive OmniRoute administration and automation via Python tooling. Use for writes, imports, purges, services, pro...

Coordinate OmniRoute update workflows, including upstream skill discovery, consolidated LocalSetup coverage comparison,...

Coordinate OmniRoute update workflows, including upstream skill discovery, consolidated LocalSetup coverage comparison,...

Inventory wrapper for Paddle Billing agent skills. Use when planning Paddle checkout, subscriptions, webhooks, pricing,...

Guide Redis cache and data-structure patterns. Use for caching, semantic cache, search, clustering, connections, observa...

Security and safety (conservative), backup management, temporary file management, firewall management. Use for destructi...

Security and safety (conservative), backup management, temporary file management, firewall management. Use for backup co...

Guide Valyu search integration. Use for Valyu-powered deep search, retrieval workflows, source grounding, and API-key ha...