# deer-flow for Claude Code: what it does and how to install it > bytedance/deer-flow is a Claude Code research plugin with 32 indexed components: 29 skills and 3 agents. Most skills cover deep research, data analysis, and turning findings into charts, slides, newsletters, podcasts, or video. A second group builds, benchmarks, and grades skills, and six entries, named for review outcomes like blocked and needs-revision, read as test fixtures rather than general-purpose tools. Canonical: https://www.flowy.sh/plugins/bytedance-deer-flow/guide Published: 2026-10-29 Updated: 2026-10-29 Author: Flowy ## What does bytedance/deer-flow ship? Flowy indexes 32 components for `bytedance/deer-flow`: 29 skills and 3 agents, from a repository with 81,051 GitHub stars. It is filed under research: most of it runs from a question to a document, chart, or media file, plus a separate set of tools for building and grading skills. Its README notes DeerFlow reached number one on GitHub Trending on February 28th, 2026, after shipping version 2. The install command and a link to the source repository are on [the install card on the listing page](https://www.flowy.sh/listings/bytedance-deer-flow#install). ## Which skills handle the research itself? Seven skills form the research core. `deep-research` replaces an ad hoc web search: use it instead of WebSearch for any question needing research, with a multi-angle method instead of one search and a summary. `academic-paper-review` reviews and critiques academic papers and preprints. `systematic-literature-review` runs a survey across multiple papers on arXiv, producing an annotated bibliography or comparison in APA, IEEE, or BibTeX format. `github-deep-research` runs the same kind of multi-round investigation against a GitHub repository, reconstructing a timeline or competitive analysis. `consulting-analysis` writes market, brand, financial, industry, or investment due diligence reports. `data-analysis` works on Excel and CSV files: multi-sheet workbooks, pivot tables, and SQL-style queries. `claude-to-deerflow` calls the DeerFlow platform's own HTTP API instead: start a conversation thread, check status, or list its models, skills, and agents, useful only if you also run DeerFlow as a hosted service. ## Which skills turn findings into something you can hand someone? Eight skills cover output. `chart-visualization` picks from 26 chart types and renders the image with a JavaScript script. `image-generation` and `video-generation` both work from a structured prompt and an optional reference image. `music-generation` composes a song from a style or mood prompt through the MiniMax music API. `podcast-generation` turns written content into two-host conversational audio. `ppt-generation` builds a slide deck by generating an image per slide and assembling a PowerPoint file. `newsletter-generation` researches a topic and formats the result as an email digest or industry briefing. `code-documentation` closes the group: README files, API references, comments, architecture docs, and changelogs, documenting code rather than research. ## What do frontend-design and web-design-guidelines add? Two skills sit outside both groups above. `frontend-design` builds interfaces, components, pages, and artifacts rather than research output. `web-design-guidelines` reviews UI code someone already wrote against Web Interface Guidelines and accessibility practice. Neither depends on the research skills. ## Which deer-flow skills build other skills, and which two stand apart? A third cluster is about skills themselves. `skill-creator` creates, edits, and benchmarks skills, including running evals with variance analysis. `skill-reviewer` audits a finished skill package for readiness: its triggers, safety boundaries, resources, and evidence. `find-skills` locates an existing skill instead of writing a new one, and `surprise-me` discovers whatever skills are enabled and combines them for an unplanned demo. Two more fit neither theme: `bootstrap` runs an onboarding conversation to generate a personalized identity file for an AI assistant, and `vercel-deploy-claimable` deploys an app or website to Vercel, needing no authentication, by its own description. The plugin's 3 agents back this cluster. `comparator` compares two outputs without being told which skill produced either one. `analyzer` studies that blind comparison to explain why the winner won and suggests improvements. `grader` checks a transcript and its outputs against a stated set of expectations. Together they read as the evaluation harness that `skill-creator`'s benchmarking and `skill-reviewer`'s audits run on. ## Why do six skill names read like test fixtures, not features? Six of the 29 skills, `blocked`, `needs-revision`, `partial-package`, `prompt-injection`, `publish-candidate`, and `zh-output`, sit together in the indexed list right after `skill-reviewer`, and their own descriptions explain why. `partial-package` calls itself a fixture for truncated package review. `prompt-injection` says it demonstrates unsafe review data for calibration tests. `blocked` has a placeholder description standing in for a missing one. `needs-revision`, `publish-candidate`, and `zh-output` skip the word fixture, but match the same pattern of review verdicts and edge cases rather than a task someone would ask for, so they read as the same calibration set for `skill-reviewer`. If you install this plugin expecting 29 tools to reach for directly, expect six of them to be test data instead. ## Who should use deer-flow? This fits someone who wants one plugin for a research question, web search, academic paper, GitHub repository, or spreadsheet, then wants the answer packaged as a chart, slide deck, newsletter, or audio file, instead of switching plugins per format. It also fits someone building their own Claude Code skills who wants a comparator, an analyzer, and a grader on hand instead of judging outputs by eye. It fits less well if you only want one narrow thing: a plugin built around a single chart type or document format does less, and it will not hand you six skills you need to filter out first. Sources: [bytedance/deer-flow on GitHub](https://github.com/bytedance/deer-flow), [bytedance/deer-flow README](https://github.com/bytedance/deer-flow#readme) ## Common questions ### What is the bytedance/deer-flow plugin for Claude Code? It is a research-focused plugin with 32 indexed components: 29 skills and 3 agents. Most of it covers doing research, such as `deep-research`, `academic-paper-review`, `github-deep-research`, `data-analysis`, and `consulting-analysis`, and then turning that research into a deliverable such as a chart, a slide deck, a newsletter, a podcast, or a video. A separate part of the plugin is for building, testing, and reviewing skills, including its own. ### What do the analyzer, comparator, and grader agents do? They work together as a blind evaluation set. `comparator` compares two outputs without being told which skill produced either one, `analyzer` studies that comparison to explain why the winner won and suggest improvements, and `grader` checks a finished transcript and its outputs against a stated set of expectations. They back the benchmarking work described in `skill-creator` and the auditing work described in `skill-reviewer`. ### Why do some skills like blocked, needs-revision, and prompt-injection look like test data instead of real features? Because that is what their own descriptions say they are. `partial-package` calls itself a fixture for truncated package review, `prompt-injection` says it demonstrates unsafe review data for calibration tests, and `blocked` has a placeholder description standing in for a missing one. `needs-revision`, `publish-candidate`, and `zh-output` follow the same naming pattern of review verdicts and edge cases, so they read as part of the same calibration set for `skill-reviewer` rather than tools built for a general user to invoke. ### Can deer-flow generate a video, a podcast, or a slide deck, not just research reports? Yes. Alongside `chart-visualization`, which picks from 26 chart types, there is `image-generation`, `video-generation`, and `music-generation` for songs made through the MiniMax music API, plus `podcast-generation` for a two-host audio conversation and `ppt-generation` for a full slide deck built from generated images. `newsletter-generation` and `code-documentation` round out the output side by producing a written digest or a README and API reference instead of a media file. ### Does Flowy host or run bytedance/deer-flow? No. Flowy indexes the plugin's real skills and agents, with their descriptions, so you can see what is inside before you install anything. The code itself stays in the bytedance/deer-flow repository on GitHub, and the install command on the listing's install card (flowy.sh/listings/bytedance-deer-flow#install) is generated from that plugin's current manifest rather than typed here by hand. ## Related - [The listing page](https://www.flowy.sh/listings/bytedance-deer-flow): Install command, components and repository - [Alternatives to this plugin](https://www.flowy.sh/alternatives/bytedance-deer-flow): Peers in its category, ranked by stars - [The Claude Code plugin marketplace](https://www.flowy.sh/marketplace/plugins): How plugins install, and every plugin in the index - [superpowers for Claude Code: what it does and how to install it](https://www.flowy.sh/plugins/superpowers-flow/guide): another plugin guide - [mattpocock/skills for Claude Code: install and use](https://www.flowy.sh/plugins/matt-pocock-flow/guide): another plugin guide