Individual skill
agentsop-repo-map
Symbol-level code context for LLM coder-agents: tree-sitter extracts symbols, PageRank ranks them over the cross-file reference graph, and the top class/function signatures are fed to the LLM as a token-budgeted read-only map (not RAG, no vector index, human-auditable). Use when an agent must locate the right files in a large/multi-file repo, when builds/refreshes/scopes a repo-map, or when "model edits the wrong file" needs fixing.
skills/agentsop-repo-map/SKILL.md
Source commit cf4376869e5f23f82404c3021a2a1315dfca318d
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Instructions only
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 465
- Repository last updated
- Oct 24, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skill Repository topic
- skill-creation Repository topic
- ai-agent Repository topic
- llm-agent Repository topic
- skill-engineering Repository topic
- skill-generation Repository topic
- skill-pipeline Repository topic
- skill-construction Repository topic
- agent-skills Repository topic
- skill-acquisition Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
README.mddoc · 2,009 bytesSKILL.mdcore · 24,540 bytesintermediate/operation_candidates.jsonasset · 4,988 bytesreferences/R1-source-evidence.mddoc · 5,430 bytesreferences/R2-cross-tool-comparison.mddoc · 6,430 bytes
Read excerpt
# Repo-Map — 让 LLM 在大仓库里找到正确文件
> 一句话:**`tree-sitter` 抽取符号 → 在跨文件引用图上跑 PageRank → 按 token 预算把最重要的 class/function 签名作为只读地图塞进上下文**。它不是 RAG、不维护向量索引、可被人审。Aider 用同样的机制在 SWE-Bench Lite 上把"正确文件命中率"打到 **70.3%** [aider.chat/2024/05/22/swe-bench-lite.html]。
这是一个**工具技能**(tool skill),不绑定 Aider;任何 coder-agent harness 只要能给 LLM 喂上下文,都可以接入或自建 repo-map。
## 1. 何时激活本技能
下列任一条件成立时,将"构建/刷新/使用 repo-map"作为该会话的标准动作:
- 任务涉及 **多文件编辑** 或 **跨文件影响分析**(rename、抽函数、改 API 签名、加 hook 点)。
- 仓库 ≥ ~20 个源文件,或 LLM 无法靠记忆/猜测找到正确目标。
- 你不想(或不能)维护 embedding 索引:环境无 GPU、不允许出仓数据、PR 评审需可追溯证据。
- 你想给 LLM **可审计的导航地图**(vs. 黑盒向量检索)。`/map` 一样的 dump 必须能给人看。
- 多文件编辑后 LLM 反复改错文件、编造路径、SEARCH/REPLACE 找不到目标——典型的"没地图就乱走"信号。