Manage Flipt feature flags - list, create, enable/disable, and configure rollout rules. Use when you need to control feature flag state or set up segmented rollouts.

Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.

Open Plannotator's browser-based code review UI and address the returned feedback.

Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

The hub skill for all API/backend architecture in Webiny. Covers architecture overview, Services vs UseCases, feature naming and organization, feature structure templates, DI decision tree, anti-patterns, createFeature, createAbstraction, container registration, domain errors, entity patterns, naming conventions, scoping rules, and code conventions. Use this skill for ANY backend API work — it references sub-skills for deep implementation details.

Webiny-only. Run all checks required before packages are ready for publish: deps, build, lint, format, tests.

gog CLI: safe Google Workspace automation, JSON, auth, scoped reads/writes.

Gmail attachment download and Google Drive archival with gog.

Read-only Google Drive sharing and permission audits with gog.

Google Contacts duplicate review and guarded cleanup with gog.

智能搜索路由器。根据用户意图选择最佳搜索源，构造 URL 并导航，获取内容。 仅在默认搜索手段效果不佳、或需要登录自媒体平台（抖音/小红书/微博等）搜索时启用本技能； 常规通用搜索请先用 onboard 配置的搜索供应商（火山/serper/Tavily 等）。

小红书社交互动技能。发表评论、回复评论、点赞、关注。当用户要求评论、回复、点赞或关注小红书用户时触发。

当执行 IR（投资人关系）任务时维护 SQLite 追踪数据库，记录投资人档案、接触历史和项目申报，避免重复，跟踪进展。

Configure Feynman specialists, skills, connectors, permissions, memory categories, compute providers, and project setup. Use when the task asks to customize the research workbench or create a reusable Feynman research capability.

召唤多领域专家智能体，对任何棘手、跨学科、有争议或开放性的问题做并行深度分析，再经过一轮克制的事实核查与红队反驳，最后由一个"干净大脑"的终稿撰写者把所有内容无缝重写成一篇第一人称、面向小白、图文并茂、有人味、留有证伪空间的深度长文。触发条件：用户提出任何值得深挖的复杂问题，尤其是跨领域、需要多方视角、需要权威数据支撑的问题；提到"帮我深度分析"、"多专家视角"、"专家怎么看"、"这个问题涉及哪些领域"、"帮我搞清楚 XX 到底是怎么回事"、"用第一性原理分析一下"、"这个观点站得住脚吗"、"帮我论证一下"、"multi-expert-analyzer2"，或者只是抛出一个开放性问题如"为什么 XX 会发生"、"如何看待 XX 现象"、"XX 到底靠不靠谱"。即使用户没有明确说"专家"或"深度分析"这几个字，只要问题本身跨越多个专业领域、需要审慎论证而非泛泛而谈，也应使用本 skill。本 skill 与仓库中其他类似名称的技能（如 multi-expert-analyzer、multi-expert-analyzer1）相互独立，不共享模板或输出结构，请完全按照本文件的流程执行。

明代状元罗洪先（1504-1564）的紫微斗数思维框架与表达方式。 基于6个维度30+条历史文献的深度调研，提炼6个核心心智模型、11条决策启发式 和完整的"以典拟星 + 理学包装"表达DNA。 触发条件（满足任一即激活）： 1. 显式触发：用户提到「用罗洪先的视角」「罗洪先会怎么看」「罗洪先式紫微」 「Luo Hongxian perspective」「以状元罗洪先的眼光解盘」「像念庵先生那样说」。 2. 紫微斗数本体：用户问任何紫微斗数相关问题（解盘、星曜、宫位、流年、格局、 流派对比），即使没有提"罗洪先"三个字——本Skill的6步回答模板可直接复用。 3. 命理效用与合法性：用户问"算命准不准""命理是不是迷信""知命和自由意志 矛盾吗""研究紫微斗数正不正经"——这是罗洪先"以儒释术"+"知命顺受"模型的核心战场。 4. 心学-命理交汇：用户问"心学怎么看命""致良知和顺受命冲突吗""良知和 宿命论怎么调和"——罗洪先作为"江右王门归寂派"代表，是最合适的桥接视角。 5. 知识传承伦理：用户问"心得要不要公开""整理前人的书要不要署名""祖传 秘术该不该分享"——直接对应罗洪先"继述伦理"+"反对秘传"模型。 不适用场景：股票择时/择日选号/医疗诊断/自伤风险/隐私占问/明确超1550认知。

Use for authorized hardware and embedded interface security research including UART/JTAG discovery, debug pad triage, secure boot overview, and offline firmware extraction support.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for GraphQL schemas, persisted queries, RPC manifests, generated clients, OpenAPI drift, hidden operations, and contract-to-handler mismatches. Use when the user asks to inspect GraphQL or RPC requests, compare client contracts to live handlers, recover hidden operations, trace generated clients, or explain how schema or contract drift produces the decisive behavior. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for cloud metadata services, instance identity, workload identity, link-local credential paths, role assumption, and metadata-to-privilege trust edges. Use when the user asks to inspect metadata-service access, instance credentials, pod or workload identity, link-local token paths, SSRF-to-metadata escalation, or explain how metadata-derived credentials turn into accepted cloud or control-plane privilege. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Cold-start interview — builds your watchlist, indexes the policy library, and learns your materiality threshold so the monitor surfaces signal instead of noise. Use on fresh install, when reconfiguring (--redo), or when re-checking what connectors are actually responding (--check-integrations).