Research

Use when a Claude Code session ends or is declared finished, a friction needs fixing, a reusable learning needs capturing, local memory needs promoting upward, or for cross-session audits — detect friction AND learnings, route each to the right destination, and gate 'done'. Triggers: /retro, /retro done, 'retrospective', 'capture this learning', 'fix this skill', 'promote memory', 'audit', 'alles erledigt'.

Opens a deliverable, such as a talk, course module, paper, book chapter, or referee report, for AI-assisted work across sessions. Interviews the author until the manifest is written, then scaffolds deliverable.yml, append-only HANDOFF.md, a numbered planning/ wiki with index and open questions, inbox/ for dictated braindumps, gitignored checks/, and the house deck template for talks. Use when the user says "open a deliverable", "set up this talk/paper/module for the pipeline", "make a manifes...

Reviews a whole deliverable, such as a talk, course module, paper, chapter, or referee report, against its manifest without rewriting. Runs a deterministic gate for build, citations, numbers, facts, and leaks, then stops on failure. It assigns a cheap finder to each section, runs a strong-model whole-work pass, and adjudicates into checks/<date>/findings.json and report.md with anchors, severities, and honest NOT-CHECKED coverage within a dollar budget. Use when the user says "lint the delive...

Turns raw captures, dictated braindumps in a deliverable’s inbox/, or recent macwhspr dictation-log entries into proposed planning-wiki changes, shown as a unified diff for author acceptance or rejection. Classifies every capture line as a decision, evidence claim, question, task, or dropped item with a reason, and traces it to its source. Uncertain names and citations remain UNRESOLVED. Applies decisions only with explicit assent. Use when the user says "intake", "absorb my notes", "process ...

Opens a deliverable, such as a talk, course module, paper, book chapter, or referee report, for AI-assisted work across sessions. Interviews the author until the manifest is written, then scaffolds deliverable.yml, append-only HANDOFF.md, a numbered planning/ wiki with index and open questions, inbox/ for dictated braindumps, gitignored checks/, and the house deck template for talks. Use when the user says "open a deliverable", "set up this talk/paper/module for the pipeline", "make a manifes...

Reviews a whole deliverable, such as a talk, course module, paper, chapter, or referee report, against its manifest without rewriting. Runs a deterministic gate for build, citations, numbers, facts, and leaks, then stops on failure. It assigns a cheap finder to each section, runs a strong-model whole-work pass, and adjudicates into checks/<date>/findings.json and report.md with anchors, severities, and honest NOT-CHECKED coverage within a dollar budget. Use when the user says "lint the delive...

Turns raw captures, dictated braindumps in a deliverable’s inbox/, or recent macwhspr dictation-log entries into proposed planning-wiki changes, shown as a unified diff for author acceptance or rejection. Classifies every capture line as a decision, evidence claim, question, task, or dropped item with a reason, and traces it to its source. Uncertain names and citations remain UNRESOLVED. Applies decisions only with explicit assent. Use when the user says "intake", "absorb my notes", "process ...

Podcast knowledge workflows powered by Podwise CLI: search podcasts and episodes by keyword, monitor followed shows for new releases, find popular episodes, ask questions and extract insights from transcript content, process Podwise episode URLs, YouTube videos, Xiaoyuzhou links, and local audio or video files to retrieve transcripts, summaries, chapters, Q&A, mind maps, highlights, and keywords — plus catch up on your backlog, refine your listening taste, generate weekly recaps, export episo...

Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle. Use when complex tasks require multiple agents working in parallel with intelligent result synthesis.

Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle. Use when complex tasks require multiple agents working in parallel with intelligent result synthesis.

Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle. Use when complex tasks require multiple agents working in parallel with intelligent result synthesis.

Distilled from production-proven coordinator patterns. Transforms sequential agent chains into intelligent parallel orchestration.

Advanced multi-agent coordination with parallel dispatch and synthesis.

Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle. Use when complex tasks require multiple agents working in parallel with intelligent result synthesis.

Systematically document research findings, competitive analysis, market trends, and user insights in Notion. Build searchable research repository for data-driven decisions.

Collaborative writing partner that assists with research, outlining, drafting, citations, and iterative feedback. Helps writers create high-quality content while maintaining their unique voice and style.

Skill to query and update a mistake notebook to memorize mistake. Use this skill when: 1. Encountered a severe problem, needs to recall for historical problem solving experience 2. After fixed a severe mistake with a clear solution valuable to be recorded 3. User requested 'Do not make this mistake again'

Analyzes upstream fork PR changes and ports selected items into the local branch. Use when checking upstream PRs, porting upstream changes, or planning selective upstream integration.

Implementer - fetches a GitHub issue, builds an implementation plan, then implements using TDD. Use when: implement, build this, code this, add this feature, TDD, test first, red green refactor, pick a task, next task, dev.

AI 论文速读 Skill：三档深度（裸读 / 引导 / 精读）+ 页码级 Provenance 防幻觉 + 多篇对比。 触发词：论文速读、读这篇论文、抓核心观点、论文对比、多篇对比、与我研究方向的关联、 第几页提到 X、这篇论文的数据集怎么构造的、论文精读、 paper summary、summarize this paper、compare these papers、literature skim、extract methodology。 不做：论文检索、文献管理、论文翻译、扫描件 OCR、论文写作 / 降重。

Structured deep research workflow with human-in-the-loop control. Use /research to generate research outline, /research-deep for parallel web search across items, /research-report to compile markdown reports. Supports academic research, benchmark research, technology selection, market analysis, and due diligence. Triggers: 'deep research', 'research topic', 'benchmark comparison', 'technology survey', 'market analysis'. Requires: WebSearch capability.

Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.

自来水内容洞察挖掘｜从一批用户自发产出的优质内容（UGC/自来水）中做跨样本归纳，提炼出团队可规模化复用的内容方法论，并评估「自然流样本用于商业投放」的衰减与风险。当用户说"整理了一批用户自发晒的爆款想提炼方法论""想知道自来水为什么火、我们能不能复制""要给达人写投放 Brief"时使用。适用于任意行业与任意内容平台，面向品牌方、代运营与小团队。

跨领域专利迁移：源领域方法+目标领域基线，5维可行性打分（技术/新颖性/创造性/实用性/商业价值），低于60分不硬写。当需要将一个领域的技术方法迁移到另一个领域申请专利时调用。