Token导航 LogoToken导航

Agent Skill · 研究检索

lore-commits(传说提交)

lore-commits 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

lore-commits 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 63,891。

总安装 309周安装 13GitHub Stars 7下载 108核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:lore-commits(传说提交)
来源仓库:https://github.com/tmdgusya/lora
仓库路径:skills/lore-commits
安装命令:
npx skills add https://github.com/tmdgusya/lora --skill lore-commits
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/tmdgusya/lora --skill lore-commits

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

lore-commits 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。适用于研究检索类任务,如信息搜集、资料筛选和线索整理,尤其适合需要自动化处理重复性搜索的场景。

通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和实际维护状态后再使用。使用前应检查是否会触发联网、命令执行或文件读写操作,避免在不安全环境中运行。建议结合原始 README 和仓库内容进一步核验具体用法和功能边界。

来源仓库内路径:skills/lore-commits

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/tmdgusya/lora --skill lore-commits;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

lore-commits 怎么安装?

在终端执行 npx skills add https://github.com/tmdgusya/lora --skill lore-commits。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

lore-commits 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

lore-commits 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

lore-commits 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

lore-commits 用的人多吗?

公开数据是累计安装 309 次,近一周安装 13 次,下载 108 次,GitHub 7 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

lore-commits 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
lore-commits

传说提交 · 本页

3097接触敏感数据未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Lore Commits

Overview

Every commit destroys decision context. You considered alternatives, evaluated tradeoffs, and chose one approach — but only the final diff survives. Lore reclaims this lost knowledge by encoding it as git trailers in commit messages.

Core principle: A commit is not a label for a diff — it's an atomic unit of institutional knowledge. Use git's native trailer format so decisions are machine-queryable, not buried in prose.

When to Use

  • Any commit where you made non-obvious decisions
  • When you rejected alternative approaches
  • When external constraints shaped your implementation
  • When future modifiers need warnings about fragile assumptions
  • When test coverage has known gaps

When NOT to use: Trivial changes (typo fixes, formatting) where no real decisions were made.

The Format

<imperative summary line>

<optional body explaining the change>

Constraint: <external constraint that shaped this decision>
Rejected: <alternative> | <reason it was rejected>
Confidence: <high | medium | low>
Scope-risk: <narrow | moderate | broad>
Reversibility: <clean | moderate | difficult>
Directive: <warning or instruction for future modifiers>
Tested: <what was verified>
Not-tested: <known coverage gaps>
Related: <commit hash or description of related commit>

All trailers are optional. Include only those that carry signal for this specific commit.

Trailer Vocabulary

TrailerPurposeExample
Constraint:External limit that shaped the decisionAuth service does not support token introspection
Rejected:Alternative considered and why it was dropped. Use `` to separate alternative from reason
Confidence:How sure you are this is right: high, medium, lowhigh
Scope-risk:Blast radius: narrow, moderate, broadnarrow
Reversibility:How easy to undo: clean, moderate, difficultclean
Directive:Warning to future modifiers — what NOT to do or what to check firstDo not narrow 4xx handling without verifying upstream behavior
Tested:What was verified and howSingle expired token refresh (unit)
Not-tested:Known gaps in verificationAuth service cold-start > 500ms behavior
Related:Linked commits forming a decision chainabc1234 (initial auth interceptor)

You can repeat trailers (multiple Constraint:, multiple Rejected:, etc.).

You can extend the vocabulary with custom trailers when needed (e.g., Deadline:, Stakeholder:, Migration:).

Complete Example

Prevent silent session drops during long-running operations

The auth service returns inconsistent status codes on token
expiry, so the interceptor catches all 4xx responses and
triggers an inline refresh.

Constraint: Auth service does not support token introspection
Constraint: Must not add latency to non-expired-token paths
Rejected: Extend token TTL to 24h | security policy violation
Rejected: Background refresh on timer | race condition
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Error handling is intentionally broad (all 4xx)
  -- do not narrow without verifying upstream behavior
Tested: Single expired token refresh (unit)
Not-tested: Auth service cold-start > 500ms behavior

Why Git Trailers (Not Prose)

Agents naturally capture decision context as prose paragraphs. The problem: prose is not queryable.

Git trailers are a native git feature. Queryable with standard git tools:

# Query all constraints affecting a file
git log --all --grep="^Constraint:" -- path/to/file.ts

# Find all rejected approaches
git log --all --grep="^Rejected:" -- path/to/file.ts

# Find directives (warnings for future modifiers)
git log --all --grep="^Directive:" -- path/to/file.ts

# Check what's not tested
git log --all --grep="^Not-tested:" -- path/to/file.ts

This turns your git history into a queryable decision database at zero infrastructure cost.

Agent Workflow

When modifying code, before committing:

  1. Harvest context — What constraints did you face? What alternatives did you reject?
  2. Write the summary line — Imperative, focused on *why* not *what*
  3. Add body if the *how* needs explanation
  4. Append trailers — One per decision fact. Only include trailers that carry signal.
  5. Self-check — Would a future agent modifying this code benefit from knowing this?

Common Mistakes

MistakeFix
Writing trailers as prose paragraphsUse Key: value format on separate lines
Putting trailers before the bodyTrailers must come after the body, separated by a blank line
Omitting the reason in Rejected:Always use `alternative
Adding trailers to trivial commitsOnly add when real decisions were made
Duplicating diff content in trailersTrailers capture what's NOT in the diff — the why, not the what
Using Confidence: yesUse the scale: high, medium, low

平台分布

Claude

35.01%
按下载量换算38

Codex

34.65%
按下载量换算37

Cursor

17.83%
按下载量换算19

Gemini CLI

10.32%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills