agentleFS
Sign inStart free
xingtu1996xingtu1996/dsh-xingtu-skills/AGENTS.md

dsh-xingtu-skills

AGENTS.md2 starsChanged 2 months agoMITView on GitHub

The file

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

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

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Write acceptance criteria and an SDD spec before nontrivial implementation.

    line 14
  2. Distinctive:

    Use isolated branches and reviewable Draft PRs.

    line 15
  3. Very specific:

    Run safe checks and record actual commands, CI links and results.

    line 16
  4. Common:

    Never disclose private Vault material, secrets, personal data or private customer content.

    line 17

≈ “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

AGENTS.md — dsh-xingtu-skills

Project-specific instructions

Read README.md and any directory-level agent instructions before edits. This is a DeepSeek Harness plugin packaging skills mirrored from xingtu-skills. Check upstream skill counts, file parity, package metadata and install scripts before publication. Do not auto-publish npm packages or run install hooks without reviewing their side effects.

Shared assets and scope

Delivery and evidence

  1. Inspect source of truth, repository-specific constraints and actual tests.
  2. Write acceptance criteria and an SDD spec before nontrivial implementation.
  3. Use isolated branches and reviewable Draft PRs; do not merge, publish, change license or visibility without approval.
  4. Run safe checks and record actual commands, CI links and results; mark unrun checks NOT_RUN.
  5. Never disclose private Vault material, secrets, personal data or private customer content. Preserve a rollback commit.

Codex 本地仓库工作流程

  • 标准工程目录为行途工作区的 github/dsh-xingtu-skills/。开始任务先在此处核对 Git 根目录、工作区状态、origin、分支/上游和同目标 PR；默认在此本地工作树操作，不另建 /tmp Clone。
  • 按“本地修改 → 适用检查 → 隔离分支 commit → push → 核验本地、远端分支和 PR head SHA”交付；仅在 SHA 一致、PR 文件清单包含改动且工作区干净时报告已同步。
  • 已有同目标 PR 时优先续用其分支并核查 base/head 和 changed files，避免重复开 PR；不得自动合并、发布包或运行未经审查的安装钩子。
  • 标准 Clone 不可用或远端异常时保留现场并说明证据；临时 Clone 仅作为说明原因后的例外，并确保改动回到标准工程目录。

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