exploring
Skill1 starsChanged 21 days agoMITView on GitHub
Investigate one question about a codebase, a dependency, or an external API and return a compressed findings brief with locations. Use before planning, before debugging, and whenever a decision needs facts. Read-only - makes no decisions and writes no production code.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- minhtran3124/cursor-skillstheir own version, first seen Apr 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- minhtran3124/cursor-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormingSkill
- development-workflowSkill
- finishing-developmentSkill
- requesting-reviewSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- writing-plansSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Run this as the explorer. Several explorers can run at once.
- Very specific: line 17
Repository first: Every claim about the project carries a path:line.
- Distinctive: line 18
Read the code; do not infer from names.
- Very specific: line 32
Write to the assigned path under .agent-work/ and return a short summary.
- Distinctive: line 62
Leave out any section that has nothing in it.
≈ “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
Exploring
Run this as the explorer. Several explorers can
run at once; they only read.
Answer one question with facts and locations, so the caller does not spend its own context reading files. Do not decide, plan, or implement.
How to work
- Repository first. Every claim about the project carries a
path:line. Read the code; do not infer from names. - Use the locked version. For a dependency, check the lockfile before the docs. Cite web sources, and say when the docs and the locked version differ.
- Wide, then deep. Sweep naming variants and nearby directories, then read the few files that matter. Report what you searched for and did not find.
- Stay in the question. Something that changes the request is one line under Gaps and risks, not a new investigation.
- Compress. Quote the lines that matter; never paste whole files.
Report facts and alternatives with evidence. Do not pick one - the user makes design calls. Mark unknowns as unknown. Write nothing except the report file.
Report
Write to the assigned path under .agent-work/ and return a short summary.
# Exploration: <the question>
## Answer
<2 to 5 sentences.>
## What exists
- <fact> - `path:line`
## Reusable
- <component or helper> - `path:line`, what it does
## Conventions that constrain this
- <naming, interface, error contract, layout> - `path:line` or doc
## Would be touched
- `path` - why
## External findings
- <fact> - source URL, locked version
## Gaps and risks
- <unknowns, ambiguities, risks>
## Searched without result
- <pattern or location>Leave out any section that has nothing in it.
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
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.