智能体
Agent 规划、多步流程与编排
turn-into-skill
BuilderIO
Capture a proven thread or workflow as a reusable Agent-Native skill and save it as a personal or organization resource. Use when a user invokes /turn-into-skill or asks to save a workflow for reuse.
sub-agents
shinpr
Run agent definitions as sub-agents. Use when the user names an agent or sub-agent to run, references an agent definition, or delegates a task to an agent.
consult-outside-expert
basecamp
Get a second opinion via Codex MCP. Use for stress-testing ideas, getting fresh perspective, steelmanning arguments, or iteratively refining work through expert back-and-forth. Invoke for ANY request involving external review, feedback, or consultation.
install-md
basecamp
Create install.md files optimized for AI agent execution. Use for ANY question about install.md files or request to create/review installation documentation for autonomous agent use.
find-skills
vercel-labs
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
my-skill
pymc-labs
"A skill"
firecrawl-build-search
firecrawl
Integrate Firecrawl /search into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.
red-team-tactics
Sekolah76
"Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting."
security-research-guardrail
Sekolah76
Independent control layer for security-research agents — prevent unsafe actions, unsupported claims, scope violations, evidence contamination, target impact, and premature reporting.
supply-chain-risk-auditor
Sekolah76
"Identifies dependencies at heightened risk of exploitation or takeover. Use when assessing supply chain attack surface, evaluating dependency health, or scoping security engagements."
variant-discovery
Sekolah76
Systematically search an authorized codebase or protocol for additional manifestations of a confirmed root cause while preventing duplicate inflation and preserving independent verification requirements.
deeptools
K-Dense-AI
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
agent-memory-mcp
benjaminasterA
"A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions)."
agent-evaluation
benjaminasterA
"Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring\u2014where even top agents achieve less than 50% on re..."
e2e
vellum-ai
Run end-to-end tests via the CI workflow.
workflows
vellum-ai
Delegate a big or high-stakes job to a fleet of parallel subagents, orchestrated deterministically; runs unattended and reports back
daily-briefing
vellum-ai
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at any time.
stock-deep-analysis
belos-street
"提供个股深度分析，包括基本面分析、估值分析、技术面辅助、风险评估。当用户询问个股分析、股票投资建议、财务数据时调用此技能。"
grilling
mattpocock
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
handoff
mattpocock
Compact the current conversation into a handoff document for another agent to pick up.
anthropic-architect
jamesrochabrun
Determine the best Anthropic architecture for your project by analyzing requirements and recommending the optimal combination of Skills, Agents, Prompts, and SDK primitives.
design-an-interface
mattpocock
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
update-docs
marin-community
Update durable docs when explicitly requested or when current work changes behavior, exposes stale instructions, establishes an operational pattern, or yields reusable research guidance.
file-issue
marin-community
File a GitHub issue only when explicitly requested or delegated by another selected workflow; do not create issues merely because a problem was found.