agentleFS
steven123397steven123397/nexuskit-skills/AGENTS.md

nexuskit-skills

AGENTS.md1 starsChanged 6 days agoMITView on GitHub

本仓库是 NexusKit 技能开发目录。v0.4.0 起技能位于 skills/ 平铺目录:主体为 vendored 的 addyosmani/agent-skills 简体中文版(技能名保留原样),nk-* 前缀目录为自有扩展(从 archive/v0.3.x-nk-skills 分支择优提回中)。客户端以 Claude Code 插件为主体(.claude-plugin/ 清单,仓库即单插件市场),仓库不是实时加载源。 任务跟踪已由 Linear 切换到 beads(仓库内 .beads/,见下方「项目约定」),存量票尚未迁入。迁移完成前,v0.4.0 的任务与进度仍以 docs/plans/2026-10-29-v0.4.0-osmani-vendor-plan.md 的工作表为准,从 Git/PR 核对实际改动;需要背景、历史理由或经验时检索 OpenViking。术语见 CONCEPTS.md,上游通用术语的统一译法见 context.md,重要设计见 docs/adr/,来源对应见 docs/skill-sources.md。 旧 docs/solutions/ 与发想、讨论材料已按 STE-13 迁移:背景与经验归 OpenViking,正式决定归 docs/adr/,发布证据保留在 docs/plans/ 与 docs/releases/;更早的审查记录已删除,Git 历史可查。不恢复 current 或重复交接文档。 This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands. Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git…

  • Installs packages
  • Commits and pushes

The file

Show its rules and text

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

13 rules. About 0 are common, 4 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

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

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

    Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists

    line 54
  2. Very specific:

    Run bd prime for detailed command reference and session close protocol

    line 55
  3. Very specific:

    Use bd remember for persistent knowledge — do NOT use MEMORY.md files

    line 56
  4. Very specific:

    Conservative (default): Use bd for task tracking. Do not run git commits, git pushes, or Dolt remote sync unless explicitly asked.

    line 64
  5. Very specific:

    Minimal: Keep tool instruction files as pointers to bd prime.

    line 65
  6. Distinctive:

    Team-maintainer: Only when the repository explicitly opts in, agents may close beads, run quality gates, commit, and push as part of …

    line 66
  7. Distinctive:

    File issues for remaining work: - Create beads for anything that needs follow-up

    line 72
  8. Distinctive:

    Do not commit or push without clear authority from the active profile or the current user request.

    line 90
  9. Distinctive:

    If a required sync or push is blocked, stop and report the exact command and error.

    line 91
  10. Very specific:

    Use Beads (bd) for durable task tracking in repositories that include it.

    line 97
  11. Very specific:

    Use bd for all task tracking.

    line 111
  12. Very specific:

    Run bd prime when Beads context is missing or stale.

    line 112
  13. Very specific:

    Keep persistent project memory in Beads via bd remember.

    line 113

≈ “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

本仓库是 NexusKit 技能开发目录。v0.4.0 起技能位于 skills/ 平铺目录:主体为 vendored 的 addyosmani/agent-skills 简体中文版(技能名保留原样),nk-* 前缀目录为自有扩展(从 archive/v0.3.x-nk-skills 分支择优提回中)。客户端以 Claude Code 插件为主体(.claude-plugin/ 清单,仓库即单插件市场),仓库不是实时加载源。

工作入口

任务跟踪已由 Linear 切换到 beads(仓库内 .beads/,见下方「项目约定」),存量票尚未迁入。迁移完成前,v0.4.0 的任务与进度仍以 docs/plans/2026-10-29-v0.4.0-osmani-vendor-plan.md 的工作表为准,从 Git/PR 核对实际改动;需要背景、历史理由或经验时检索 OpenViking。术语见 CONCEPTS.md,上游通用术语的统一译法见 context.md,重要设计见 docs/adr/,来源对应见 docs/skill-sources.md。

旧 docs/solutions/ 与发想、讨论材料已按 STE-13 迁移:背景与经验归 OpenViking,正式决定归 docs/adr/,发布证据保留在 docs/plans/ 与 docs/releases/;更早的审查记录已删除,Git 历史可查。不恢复 current 或重复交接文档。

技能组织

  • 上游技能以 vendor 方式引入并保持可同步:改动走小修小补,改动点记录于计划文档的逐技能审阅表;不做大型重写,不与上游无谓分叉。同步源为 .upstream/addyosmani-agent-skills-zh(本地克隆,已 gitignore),它自身跟踪上游 addyosmani/agent-skills。
  • SKILL.md 放完整主流程,模板、提示词、脚本等按实际需要就近放置。跨技能调用公开入口,不读取其他技能的私有文件。仓库级共享检查清单位于 references/(整包分发,不存在单技能安装断链问题)。
  • nk 旧技能不设 legacy 副本:整体封存于 archive/v0.3.x-nk-skills 分支,提回时逐个裁定(提回 / 不提回 / 并入),结果记录于计划文档的提回裁定表。新增技能以 .gitkeep 保留目录,不创建可安装的空壳。
  • frontmatter 的 description 采用上游英文原文(作者按触发率调校过,译文属二次加工);正文可用中文。修改来源对应时更新 skill-sources,说明具体部分来自何处,不记进度、日期或验证流水账。

修改与验证

  • 默认直接在主分支开发与提交,不再为每项工作新建分支;只有需要并行写入、原型隔离或高风险试验时才开分支或工作树。工作树默认放在仓库同级 <项目名>-worktrees/<用途>;优先沿用宿主管理方式,并明确绝对路径、分支与用途。发布仍走 PR 或版本 tag 的既有流程。
  • 保留其他会话的未提交工作。成果承接后及时清理闲置工作树,清理前核对活跃使用者、未提交及忽略文件,不删除原工作目录或其他任务资源。
  • 技能或基础检查修改后运行 python tests/run_checks.py;检查器修改另跑 python -m unittest discover -s tests -p "test_*.py"。首次安装依赖用 python -m pip install -r tests/requirements.txt。
  • nk-wizard 提回后,其模板修改执行 bash -n skills/nk-wizard/assets/template.sh。CI 覆盖 Windows/Linux,版本 tag 还检查版本号和 release notes。
  • 检查覆盖链接、技能引用、大小、分发与 frontmatter;机械检查不证明真实客户端执行效果。使用仓库的 YAML 校验器,不为通过外部 skill-creator 校验器删掉合法字段。
  • 提交按仓库历史的 conventional commits 惯例手动执行。没有明确提交安排时保留可审阅改动,不把骨架搭建当成整轮技能完成。
  • 新建技能目录不创建加载链接。即时试用需手动重装本地插件;临时 junction 用 PowerShell 创建,删除 junction 用 [IO.Directory]::Delete(),不递归删除目标。

项目约定

  • idea:docs/ideas/,一个想法一个文件
  • 决策记录:docs/adr/,编号递增,不删旧
  • 规格:SPEC.md;外部工具:无
  • task:beads,仓库内 .beads/(bd init 初始化),beads 为唯一来源;不再用 tasks/plan.md + tasks/todo.md
  • issue 图:references/issue-graph.md
  • 子智能体模型:派发时显式传 model —— code-reviewer、security-auditor 用 opus;doubt-challenger、test-engineer、web-performance-auditor 用 sonnet
  • 以上文件在第一次真正产出时创建,不预建空目录
<!-- BEGIN BEADS INTEGRATION v:1 profile:minimal hash:46cd31e7 -->

Beads Issue Tracker

This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --claim  # Claim work
bd close <id>         # Complete work

Rules

  • Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists
  • Run bd prime for detailed command reference and session close protocol
  • Use bd remember for persistent knowledge — do NOT use MEMORY.md files

Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git remote; .beads/issues.jsonl is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/core-concepts/sync-concepts.md for details and anti-patterns.

Agent Context Profiles

The managed Beads block is task-tracking guidance, not permission to override repository, user, or orchestrator instructions.

  • Conservative (default): Use bd for task tracking. Do not run git commits, git pushes, or Dolt remote sync unless explicitly asked. At handoff, report changed files, validation, and suggested next commands.
  • Minimal: Keep tool instruction files as pointers to bd prime; use the same conservative git policy unless active instructions say otherwise.
  • Team-maintainer: Only when the repository explicitly opts in, agents may close beads, run quality gates, commit, and push as part of session close. A current "do not commit" or "do not push" instruction still wins.

Session Completion

This protocol applies when ending a Beads implementation workflow. It is subordinate to explicit user, repository, and orchestrator instructions.

  1. File issues for remaining work - Create beads for anything that needs follow-up
  2. Run quality gates (if code changed) - Tests, linters, builds
  3. Update issue status - Close finished work, update in-progress items
  4. Handle git/sync by active profile:
    # Conservative/minimal/default: report status and proposed commands; wait for approval.
    git status
    
    # Team-maintainer opt-in only, unless current instructions forbid it:
    git pull --rebase
    bd dolt push
    git push
    git status
  5. Hand off - Summarize changes, validation, issue status, and any blocked sync/commit/push step

Critical rules:

  • Explicit user or orchestrator instructions override this Beads block.
  • Do not commit or push without clear authority from the active profile or the current user request.
  • If a required sync or push is blocked, stop and report the exact command and error.
<!-- END BEADS INTEGRATION --><!-- BEGIN BEADS CODEX SETUP: generated by bd setup codex -->

Beads Issue Tracker

Use Beads (bd) for durable task tracking in repositories that include it. Use the beads skill at .agents/skills/beads/SKILL.md (project install) or ~/.agents/skills/beads/SKILL.md (global install) for Beads workflow guidance, then use the bd CLI for issue operations.

Quick Reference

bd ready                # Find available work
bd show <id>            # View issue details
bd update <id> --claim  # Claim work
bd close <id>           # Complete work
bd prime                # Refresh Beads context

Rules

  • Use bd for all task tracking; do not create markdown TODO lists.
  • Run bd prime when Beads context is missing or stale. Codex 0.129.0+ can load Beads context automatically through native hooks; use /hooks to inspect or toggle them.
  • Keep persistent project memory in Beads via bd remember; do not create ad hoc memory files.

Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git remote; .beads/issues.jsonl is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/core-concepts/sync-concepts.md for details and anti-patterns.

<!-- END BEADS CODEX SETUP -->

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.