agentleFS
Sign inStart free
bytedancebytedance/deer-flow/skills/AGENTS.md

deer-flow / skills

AGENTS.md85k starsChanged 5 months agoMITView on GitHub

public/ holds committed skills and custom/ holds local, gitignored skills. Tests for public skill scripts are in tests/skills/ at the repository root and run in Skill Review CI, independent of package review. - public/skill-reviewer/ is the built-in read-only reviewer. Its contracts are in contracts/skill_review/. Review data that the model sees is tag-neutralized, and raw payloads stay in tool artifacts. - CI waivers are in .github/skill-review-waivers.v1.json. Only the manifest from the trusted base revision can suppress a run, and a blocker…

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 3 mentionsMar 2026: 19 mentionsApr 2026: 2 mentionsMay 2026: 6 mentionsJun 2026: 11 mentionsJul 2026: 3 mentionsAug 2026: 8 mentionsSep 2026: 9 mentionsOct 2026: 22 mentionsNov 2026: 13 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the bytedance/deer-flow repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about bytedance/deer-flow

The biggest 5 of 105 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 105

Talked about on GitHub, YouTube, Bluesky, Hacker News and the web (105 times).

On GitHub · 50

45 more on GitHub

On YouTube · 23

18 more on YouTube

On Bluesky · 21

16 more on Bluesky

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    CI waivers are in .github/skill-review-waivers.v1.json: Only the manifest from the trusted base revision can suppress a run, and a …

    line 10
  2. Distinctive:

    Skill script tests run offline: Test a dependency fallback with the optional import unavailable, and mock the HTTP transport.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Skills (skills/)

public/ holds committed skills and custom/ holds local, gitignored skills. Tests for public skill scripts are in tests/skills/ at the repository root and run in Skill Review CI, independent of package review.

  • public/skill-reviewer/ is the built-in read-only reviewer. Its contracts are in contracts/skill_review/. Review data that the model sees is tag-neutralized, and raw payloads stay in tool artifacts.
  • CI waivers are in .github/skill-review-waivers.v1.json. Only the manifest from the trusted base revision can suppress a run, and a blocker finding cannot be waived.
  • Read SKILL.md as utf-8-sig and write text resources as utf-8. The platform locale is not reliable, and a leading BOM would become part of the content.
  • Skill script tests run offline. Test a dependency fallback with the optional import unavailable, and mock the HTTP transport.
  • A skill CLI exits non-zero on failure, with diagnostics on stderr and result URLs on stdout.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free