coding-explain-problem
Skill1 starsChanged 3 months agoMITView on GitHub
Explain coding problems, code behavior, review findings, architecture, or proposed changes in plain language. Use when the user asks what code does, why it exists, why a bug occurs, how existing behavior differs from a current change, or requests an explanation suitable for someone new to a codebase.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ask-claudeSkill
- battery-statsSkill
- coding-audit-assumptionsSkill
- coding-consult-designSkill
- handoffSkill
- ntd-tasksSkill
- one-by-oneSkill
- record-macos-windowSkill
- show-meSkill
- tallySkill
- video-analysisSkill
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 13
Use one concrete example with realistic input and output when it helps.
- Distinctive: line 18
Avoid buzzwords and unexplained architecture terms.
- Distinctive: line 19
Keep the first explanation concise, but include enough context to explain why the code exists.
≈ “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
Explain coding problems
Assume the user is new to the codebase unless they say otherwise.
- Lead with the plain-language answer.
- Separate existing behavior from behavior added or changed by the current task or pull request.
- Explain the runtime flow in short steps.
- Use one concrete example with realistic input and output when it helps.
- Define project-specific terms on first use.
- State when the issue applies and when it does not.
- Separate confirmed code facts from assumptions.
- End with the smallest reasonable fix and what remains unchanged.
- Avoid buzzwords and unexplained architecture terms.
- Keep the first explanation concise, but include enough context to explain why the code exists.
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.