智能体技能是一个包含指令、脚本和资源的文件夹，智能体按需加载。与 MCP 服务器不同，它不运行自己的进程，因此在上下文上更省，也更容易审查。
第 913–935 条，共 935 条
jerrod
Design system orchestration — bootstraps design-context.md from project scan, enforces design constraints during builds, runs unified design review. Trigger: 'design init', 'design review', 'set up design system', 'check design quality', 'sdlc:design'.
jerrod
Systematic root-cause debugging across Datadog logs/RUM/APM, Google Cloud logging, and the local codebase. Mirrors the gstack /investigate discipline (Iron Law, 3-strike rule, regression test, structured DEBUG REPORT) and routes per service. Optionally posts findings to Slack.
jerrod
Use this skill when the user wants a code review — before opening a PR, merging a branch, or shipping to production. Triggers on requests like \"review my code\", \"is this ready to merge\", \"check my work before I push\", \"run the quality gates\", or \"give me a second pair of eyes on this branch\". Runs automated quality gate scripts plus manual review for bugs, security, performance, test qua
jerrod
Execute plans with fresh subagents per task and two-stage review (spec compliance then code quality). Use over pair-build when tasks are independent, don't share files, and benefit from isolated context. Trigger: 'use subagents', 'dispatch workers', 'build with isolated agents'.
rainshed
A named research companion for academic/scientific projects. Triggered when user says 'research companion' or mentions the companion's custom name (registered in AGENTS.md after first use). On first use, asks the user to give the companion a name. Maintains layered persistent memory and collaboratively identifies next research steps.
LeePepe
Use for explicit teamwork orchestration requests (/teamwork:task, /teamwork:mapping-repo, or "use teamwork"). Delegates to team-lead for plan-led execution with gated review and verification.
MaTo8888
日本語翻訳：このファイルは make-interfaces-feel-better 用の日本語翻訳が必要です
sun2443
Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.
jbcrane13
Use when creating evals and judge checks for API QA agent reports.
sun2443
Interactive PDF viewer. Use when the user wants to open, show, or view a PDF and collaborate on it visually — annotate, highlight, stamp, fill form fields, place signature/initials, or review markup together. Not for summarization or text extraction (use native Read instead).
jerrod
Use this skill when the user wants to implement, build, or code items from an existing plan or checklist — phrases like \"implement the plan\", \"build the plan items\", \"start coding\", \"implement the remaining items\", or \"pair-build\". Takes a structured plan and executes each item with a writer+critic pair so builds pass gates on the first run. Trigger on any intent to go from plan to worki
Kevin0412
Apply this skill when the user requests concise English output, is writing docs, README, CONTRIBUTING.md, architecture notes, code comments, or any technical writing. Also apply for agent-to-agent instructions, CLI help text, and any English output where brevity and clarity matter. Trigger on concise English, brief docs, clean README, technical writing, or whenever the task is English documentatio
sun2443
Generate an onboarding checklist and first-week plan for a new hire. Use when someone has a start date coming up, building the pre-start task list (accounts, equipment, buddy), scheduling Day 1 and Week 1, or setting 30/60/90-day goals for a new team member.
sun2443
Research competitors and generate a positioning and messaging comparison with content gaps, opportunities, and threats. Use when building sales battlecards, when finding positioning gaps and messaging angles competitors haven't claimed, or when a competitor makes a move and you need to assess the impact.
sun2443
Full ICP-to-leads pipeline. Describe your ideal customer in plain English and get a ranked table of enriched decision-maker leads with emails and phone numbers.
Kevin0412
当用户要求以精炼现代书面语回复、降低token冗余、压缩口语化表达时触发。适用场景包括：技术文档写作、项目汇报、算法题解、README撰写、任何需要紧凑专业书面中文的输出。触发词包括"精炼书面语""书面语""压缩回复""去冗余""精简中文""书面风格"，或用户粘贴此系统提示词要求应用时。即便用户未明确提及，只要任务为中文技术写作或正式文档，亦应主动应用此风格。
dding-g
Practical TypeScript patterns. Activated when working with type inference, utility types, generics, type guards, or type narrowing.
MayR-Labs
Extracted Node.js / TypeScript standards from MayR Labs GEMINI.md
