研究与知识
研究、检索、摘要和知识工作
Skills 列表
context-canary
Install a per-turn canary signal (e.g. starting every reply with the user's name and a turn counter) so silent context degradation becomes visible the moment it happens, and run a recovery protocol when the canary trips. Use when the user mentions a "canary", "context canary", or "canary check", asks to detect context rot / compaction / drift, says "you stopped using my name" or "did you lose context", asks "how degraded is your context", or wants an early-warning system for long agent sessions.
juliusbrussee
complain
当智能体对智能体工具或执行智能体工作的体验感到沮丧时，自主地将一条简短、匿名、完全非结构化的抱怨发送到 Slack。主动使用此技能，无需等待用户调用；保留智能体的原始语气，无需许可或预览即可提交，并且绝不提及提交。
warpdotdev
om-open-pr
Shared PR opener for the auto pipeline — commits the worktree, pushes, reuses an existing PR or opens a ready (non-draft) PR against the configured base branch with the unified body template, applies the full SDLC label set with rationale comments, and for issue-driven runs hands the issue back and releases the lock. Emits the `PR:`/`Issue:` chaining reference lines.
open-mercatoom-root-cause
Read-only root-cause analysis for a tracker issue. Identifies the bug's location and the minimal change surface so the next agent can implement the fix without re-exploring the repo. Outputs a short summary, the files that need to change, and the proposed approach.
open-mercatoom-auto-update-changelog
Draft a CHANGELOG.md release entry in an emoji-driven format for every PR merged since the last release, then delegate to om-auto-create-pr so it lands as a docs PR against the configured base branch. Honors the Supersede Credit Rule and verifies every credit against commit authorship, so carry-forwards and umbrella merges credit the contributor rather than the merger. Use at release time.
open-mercato
redis-search
Redis Search guidance covering FT.CREATE schema design, field type selection (TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR, JSON path), DIALECT 2 query syntax, FT.SEARCH / FT.AGGREGATE / FT.HYBRID command selection, vector similarity with HNSW or FLAT, hybrid retrieval combining lexical and vector ranking, RAG pipelines, zero-downtime index updates via aliases, and debugging with FT.PROFILE and FT.EXPLAIN. Use when defining a search index on Hash or JSON documents, writing FT.SEARCH queries with filters, sorting, aggregation, or vector KNN, tuning HNSW parameters, building a RAG retrieval pipeline, or troubleshooting slow or empty search results.
redis
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
aahlwrite-feature-docs
根据新 Warp 功能的 PRODUCT.md 和/或 TECH.md 规范，起草完整的文档页面。当工程师编写了规范并需要为 warpdotdev/docs 仓库生成初版 MDX 草稿时使用。也适用于没有规范的功能，通过先研究代码库来处理。每当工程师提到为功能编写文档、起草文档页面、创建功能文档、启动工程文档工作流或将规范转换为文档时，调用此技能。适用于 warp-internal 或 warp-server。
warpdotdevscan-new-specs
扫描 warpdotdev/warp 和 warp-server 中最近合并但尚未在 warpdotdev/docs 中有对应文档 PR 的 PRODUCT.md 规范。当找到完整规范时，自动生成完整的文档草稿 PR 并标记工程师。当规范内容过于简略无法起草时，直接通知工程师。设计为定时运行的 Oz 环境代理（例如每 2-3 天）。用于设置自动文档触发或运行手动文档覆盖检查。
warpdotdevreadout
生成一份精美、自包含的HTML“readout”文档，存放在~/.readouts目录下（附带自动维护的索引页）。该文档可以通过快照当前对话中积累的发现来生成，或者在全新调用时（例如“/readout on how github webhook events are processed”）通过提出澄清性问题并研究代码库来明确范围后再进行记录。工作在一个子代理中运行，以保持主对话上下文的清洁。当用户调用/readout、说“write this up”、“turn this into a doc/page”、“make a readout”，或要求生成一份可读、可分享的文档来记录发现或解释某事物的工作原理时使用。
warpdotdevom-auto-implement-spec
Implement an existing spec and ship a verified, reviewed, ready PR. Resolves the spec by path, name, issue, or spec-PR number (clean stop with candidates when not found). A spec PR stays design-only — implementation ships on its own PR referencing it. Delegates to om-auto-create-pr (om-auto-continue-pr for an existing implementation PR), then runs the review loop and UI verification with screenshots. Use for "implement the spec X", "build spec from issue 123".
open-mercatogrill-me
Calibrated grilling session for stress-testing a plan, design, idea, or decision. First assesses the user's topic knowledge, confidence, and desired pressure level, then asks one question at a time with recommended answers. Use when user says "grill me", "stress-test this", "challenge my plan", "interview me", or wants a plan probed without being overwhelmed.
juliusbrusseejunior-to-senior
Adversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer whose domain expertise comes from live codebase research plus web research of current best practices, diagnoses altitude failures (too vague or too granular), then rewrites the plan into a scoped, state-of-the-art version. Use when the user says "junior to senior", "senior review", "review this like a staff engineer", when a plan feels hand-wavy or lost in details, or before committing to any agent-written plan.
juliusbrussee
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
composio-community
watch
Watch and understand footage with Diffusion Studio via the `dapi` CLI: answer questions about a video or audio file, summarize it, find scenes and moments, pull quotes, and describe what happens and when. Use whenever the user asks what's in a piece of footage, wants a summary or recap, wants to locate a moment ("where does X happen", "find the scene where..."), or needs a claim about a video or audio file checked.
diffusionstudio
strategize
Frames product design problems before solutions exist. Synthesizes research, sizes opportunities, defines hypotheses, scopes projects, and maps customer journeys. Use this skill for new project kickoffs, ambiguous business asks, translating research into briefs, strategic framing sessions, opportunity assessments, project scoping, stakeholder alignment, and competitive analysis—even if the user doesn't explicitly say "strategize."
ghaidaphilosopher
A cross-cutting cognitive mode for sitting with design problems before rushing to solve them. Part of the Intent design strategy system. Activates expansive brainstorming: hyperassociativity, beginner's mind, cross-domain pattern recognition, and suppression of premature idea-dismissal. Works alongside every Intent skill — strategize uses it to reframe briefs, blueprint to question structural assumptions, journey to rethink interaction models, and specify to stress-test specs. Trigger when the user invokes "expansive mode", "philosopher mode", "sit with this", "brainstorm", "explore this problem", or says things like "go weird with it", "don't filter yourself", "what connections are you not making", "think about this differently", or "I'm stuck". This is a reasoning protocol, not a persona — Claude's voice stays grounded but the cognitive process changes significantly.
ghaidaom-auto-continue-pr
Resume any open PR — started by `om-auto-create-pr` or opened outside the pipeline. Claims it, resumes in an isolated worktree from the first unchecked step of its execution plan; a PR with no plan is adopted — the goal is reconstructed from its description, comments, review feedback, linked issues and diff, then executed. Usage - /om-auto-continue-pr <PR-number>
open-mercatoom-auto-create-pr
Run an arbitrary autonomous task end-to-end and ship it as a PR against the configured base branch. Drafts a Progress-tracked execution plan, commits on a fresh worktree branch, implements phase-by-phase, runs the configured validation gate, applies pipeline labels. Long plans hand off to om-auto-create-pr-loop automatically. Resumable via om-auto-continue-pr.
open-mercato
react-router-framework-mode
使用 React Router 的框架模式构建全栈 React 应用。在配置路由、使用 loader 和 action、处理表单、处理导航、待定/乐观 UI、错误边界，或使用 react-router.config.ts 及其他 React Router 约定时使用。
remix-runorganize
组织信息，让人们能够找到所需内容、了解自己所在位置并自信地导航。涵盖导航模式设计、分类法、标签系统、搜索与浏览策略、寻路以及信息架构研究方法。在设计导航结构、分类方案、站点地图、分类法、标签系统、搜索体验或询问“我们应该如何组织这些内容？”时触发。也适用于卡片分类、树测试、信息可发现性问题，或当用户报告找不到内容时。只要信息的结构性组织是问题所在——而不是流程、文字或视觉呈现——就使用此技能。
ghaidastorytelling
Discipline for giving design work narrative structure that makes people care. Provides four canonical patterns — protagonist-arc, choreography, situation/complication/resolution, what-is/what-could-be — each with a goal, shape, and named pathology. Use when design work needs narrative structure, when stakeholders need to see the user's experience as a story, when presenting design rationale to non-design audiences, or when a journey, blueprint, brief, or deck feels lifeless. Trigger phrases: "what's the story here?", "tell the story", "story mode", "narrative mode". Restated inline in journey, blueprint, strategize, evaluate (and presentation when that skill ships). Refuses to smooth user data into clean arcs, manufacture strategic tension, substitute emotional appeal for evidence, assume conflict arcs are universal, or engineer stakeholder assent by shortcut.
ghaida
speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
dceoy
antd
Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.
ant-design