智能体
Agent 规划、多步流程与编排
run-report
bdfinst
Report one orchestrated run's timeline — per-state dwell time, rejection count, hook denials/bypasses grouped by cause, and cost — joined from boundary-events.jsonl, cost-metering.jsonl, and workflow-states.jsonl for a given session_id (default: most recent). Use when the user asks "how did that run go", "show the run report", "/run-report", or wants a single view of a /ship//autoship//build run instead of cross-referencing streams by hand.
gpt-researcher
assafelovic
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations. Use this skill when helping developers understand, extend, debug, or integrate with GPT Researcher - including adding features, understanding the architecture, working with the API, customizing research workflows, adding new retrievers, integrating MCP data sources, or troubleshooting research pipelines.
style-editing
Agenta-AI
Apply Joseph Williams' clarity principles when writing or editing prose. Use when drafting technical or business writing, diagnosing unclear sentences, rewriting passive or abstract prose, or any time the user references Williams, "Style: Lessons in Clarity and Grace," or "Style: The Basics of Clarity and Grace."
langchain-chains
a5c-ai
LangChain chain composition including SequentialChain, RouterChain, and LCEL patterns
plan-update
react
Use when you need to update a plan document with deep research across all compiler passes. Launches parallel subagents to analyze how a topic affects every compiler phase, then consolidates findings into the plan doc.
testing-heterogeneous-agents
lobehub
'Manually runs the live LobeHub official-provider compatibility matrix across Claude Code, Codex, Grok Build, Kimi Code, Pi, and TRAE when explicitly invoked by the user.'
llm-generation
lobehub
'LobeHub application-level LLM generation conventions. Use when adding or changing prompts, generateObject/generateText calls, structured output schemas, generation model selection, prompt versions, llm_generation_tracing scenarios, or tests for AI-generated business content. Do not use for provider adapter internals or agent execution snapshots.'
deeptools
jimmc414
"NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization."
skill-creator
prowler-cloud
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
agentmail
agentmail-to
Give AI agents their own email inboxes using the AgentMail API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, handling attachments, organizing with labels, creating drafts for human approval, or setting up real-time notifications via webhooks/websockets. Supports multi-tenant isolation with pods.
uipath-troubleshoot
UiPath
"UiPath causal investigation across every product, runtime, and activity package. Use when the primary outcome is an explanation, diagnosis, or root cause for undesirable existing behavior: faults, hangs, regressions, slowdowns, access loss, unexpected state changes, wrong or empty results, silent no-ops, or raw errors. Diagnostic intent outranks surface ownership for runtime behavior; invoke even when the prompt names only a job, folder, queue item, connector, connection, activity, trace, flow, agent, or other resource and another UiPath skill supplies inspection commands. Correlates runtime, configuration, history, and source evidence to find the originating fault and fix. Also covers UiPath Assistant desktop-app failures from a shared diagnostic archive (combined.log, Robot.log). For operating resources without causal investigation→uipath-platform; for applying a known source fix→the artifact owner; for build-time/CLI faults of a local artifact (pack, build, validate, bindings)→the artifact's skill."
uipath-maestro-case
UiPath
"TRIGGER for authoring UiPath Maestro Case plans as <Name>.case.ts with the reference-mode TypeScript builder SDK (@uipath/maestro-builder-sdk/case), compiling to caseplan.json, and running the uip maestro case check/compile/validate loop. Covers stages, tasks, rules, bindings, published-resource references, and brownfield decompile/edit/recompile. Flow builder authoring → uipath-maestro-flow; structural-core BPMN → uipath-maestro-bpmn. DO NOT TRIGGER for C#/XAML automation → uipath-rpa."
skill-creator
Gentleman-Programming
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
skill-creator
Gentleman-Programming
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
agent-md-refactor
pedronauck
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
contribute-to-slopdotcash
SlopDotCash
Fixes and proves real defects in Slop (SlopDotCash/slopdotcash) inside the approved MVP. Use for a reproduced bug or approved MVP gap in security, identity, scoring, verification, vault, funding, or settlement; excludes UI and copy changes, new features, coverage farming, and mock-only proof.
Azure Service Bus
markus41
Deep expertise in Azure Service Bus operations with deterministic runbooks, fail-fast context validation, and redacted output requirements.
Azure Backup Recovery
markus41
Deep expertise in Azure Backup Recovery operations with deterministic runbooks, fail-fast context validation, and redacted output requirements.
troubleshoot
Chachamaru127
"Diagnosis and repair guide for errors and failures including CI. Use when user mentions something broken, errors, it doesn't work, CI failures, CIが落ちた, build errors, test failures, or pipeline issues. Do NOT load for: successful builds, new feature implementation, or reviews."
breezing
Chachamaru127
"楽勝で流す。Agent Teamsで完全自走、寝てる間にゴール。Use when user mentions '/breezing', agent teams, team execution, full auto completion, multi-agent workflow, 'チームで完走', 'チームで全部'. Do NOT load for: single tasks, reviews, setup, or /work (direct implementation)."
sync-status
Chachamaru127
"進捗とPlans.mdを現実に同期。『今どこ？』がすぐわかる現在地確認。Use when user mentions '/sync-status', progress check, where am I at, or sync Plans.md. Do NOT load for: casual 'how is it going' chat, informal progress questions."
subagent-creator
tech-leads-club
Guide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent, specialized agent, verifier, debugger, or orchestrator that requires isolated context and deep specialization. Works with any agent that supports subagent delegation. Triggers on "create subagent", "new agent", "specialized assistant", "create verifier".
workflow-guide
Chachamaru127
"Cursor ↔ Claude Code 2-Agentワークフローのガイダンスを提供。Use when user asks about workflow, collaboration, or process. Do NOT load for: implementation work, workflow setup, or executing handoffs."
breezing
Chachamaru127
"楽勝で流す。Agent Teamsで完全自走、寝てる間にゴール。Use when user mentions '/breezing', agent teams, team execution, full auto completion, multi-agent workflow, 'チームで完走', 'チームで全部'. Do NOT load for: single tasks, reviews, setup, or /work (direct implementation)."