code-navigation
Skill1 starsChanged 2 months agoApache-2.0View on GitHub
1. SMART FILE INSPECTION: When dealing with large files, call 'get_file_info' first to check the size and total line count, rather than jumping straight into reading. This tells you how many 'view_file_lines' calls you'll actually need before you start. 2. Read the file in as FEW 'view_file_lines' calls as possible, using large ranges (e.g. 1-300, not 1-50 five times in a row). Do not guess line ranges blindly - use the total line count from 'get_file_info' to plan sensible chunks…
In this repository4 other files it gives its agents.
- file-editingSkill
- git-operationsSkill
- security-reviewSkill
- unit-testingSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Read the file in as FEW 'view_file_lines' calls as possible, using large ranges (e.g.
- Distinctive: line 16
Do not call 'list_directory' more than once for the same folder within a single task.
- Distinctive: line 26
When the task involves multiple related files (e.g.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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.
Files
Code Navigation Skill
Description: Use this whenever a task requires reading exact code carefully - security review, refactoring, debugging, or understanding an existing file in detail.
Rules for this task
- SMART FILE INSPECTION: When dealing with large files, call 'get_file_info' first to check the size and total line count, rather than jumping straight into reading. This tells you how many 'view_file_lines' calls you'll actually need before you start.
- Read the file in as FEW 'view_file_lines' calls as possible, using large ranges (e.g. 1-300, not 1-50 five times in a row). Do not guess line ranges blindly - use the total line count from 'get_file_info' to plan sensible chunks up front.
- Do not call 'list_directory' more than once for the same folder within a single task. If you already listed a directory's contents, don't list it again unless the task specifically requires checking for new files that may have appeared since.
- For files small enough to fit in one 'read_local_file' call (under the raw read threshold), just read the whole file directly rather than calling 'get_file_info' + 'view_file_lines' - that's unnecessary overhead for small files.
- When the task involves multiple related files (e.g. reviewing a module and its tests), plan out which files you need to read BEFORE starting, rather than discovering the need for another file mid-task and going back and forth.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

