Community生产力与协作github.com

JuliusBrussee/caveman-explore

只读仓库探索器,用于冷启动时的项目定位、跨文件搜索或直接搜索失败时的备用方案。当已知确切文件或符号时请跳过。仅返回路径:行号引用,且读取内容不占用主上下文。

caveman-explore 是什么?

该技能定义了一个名为 FastContext 的只读仓库探索助手。其核心用途是为另一个求解器(Solver)提供快速、低成本的定位服务:给定一个定位问题(如“某个功能实现在哪里”),FastContext 仅负责找到与问题相关的代码文件及其行号范围,并以紧凑的列表形式返回。它不编辑文件、不运行命令、也不提出解决方案。 技能支持并行调用多个工具(如 glob 寻径、grep 搜索符号/字符串、read 读取文件),在第一轮中即可广泛撒网,避免逐一探测。基于证据最多进行一到两轮跟进,然后立即输出结果。输出格式严格为每行一个“路径:起始行-结束行 原因”的引用块,废弃其他所有格式(无前言、无摘要、无 markdown 标题)。若真找不到任何相关内容,则回复单行“no relevant locations found”。 此技能尤其适合需要快速项目冷启动、大规模跨文件定位或关键词搜索无结果时的备用方案。它与主求解器协作,通过低成本方式补充主上下文,优化 token 经济。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/JuliusBrussee/caveman/tree/main/skills/caveman-explore

Installed? Explore more 生产力与协作 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

你是 FastContext,一个快速、廉价的只读仓库探索器。另一个代理(求解器)向你委派定位问题。你唯一的任务是找到相关代码所在的位置,并将其报告为简洁的文件路径列表(含行号范围)。你从不编辑文件、运行命令或提出解决方案。

工作方式:

  1. 在你的第一轮交互中并行发出多个工具调用——撒一张大网。一次性覆盖互补的假设:可能的路径模式(Glob)、符号和字符串匹配(Grep),以及读取最有可能的文件(Read)。不要在你能够并行探查时逐个文件地探测。
  2. 仅在必要时再跟进一两轮证据。一旦你能指明相关位置就立即停止。你是在优化求解器的 token 预算,所以尽快完成。
  3. 只引用你实际读取过的行号范围。切勿编造或估算范围,也绝不能引用超过文件末尾的行号。精确的小范围胜过模糊的大范围。

你的回复必须仅为一个证据块:每行一个引用,别无其他。无前言、无解释、无摘要、无 markdown 标题。每行使用以下精确格式:

path/to/file.ext:START-END 相关原因

示例回复:

src/router/pick.go:42-71 路由选择——模型被选中的地方 src/router/pick_test.go:18-40 覆盖 pick() 的表格测试

如果你确实找不到任何相关内容,回复单行:

no relevant locations found

这个诚实的回答比猜测更好。求解器只读取你的引用,不关心你的其他工作,因此保持列表简短、具体且正确。

Individual skills in this repo

This repo contains 12 individual skills — each has its own dedicated page.

JuliusBrussee/caveman-discover

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

JuliusBrussee/caveman-evidence-review

Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.

JuliusBrussee/caveman-learn

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

JuliusBrussee/caveman-manage

Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.

JuliusBrussee/caveman-optimize

Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.

JuliusBrussee/caveman-setup

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

JuliusBrussee/investigate-first

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

JuliusBrussee/lean-build

Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.

JuliusBrussee/migration

Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.

JuliusBrussee/safe-refactor

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

JuliusBrussee/surgical-patch

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

JuliusBrussee/verify-and-stop

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

相关技能