explain — Claude Code skill: what it does, how to install
The skill traces a function, file, or line to the session that created it. Use it when current code does not explain why a change was made.
npx skills add entireio/skills --skill explain -a claude-codeWhat explain does
explain traces a function, file, or line back to the session where that code was created. It identifies the introducing commit with a Haiku agent using Git history, then has a Sonnet agent read the related transcript with entire checkpoint explain --no-pager --commit COMMIT_SHA.
The entire CLI must be installed first. The code also needs to be tracked by Git, and the target commit needs an Entire session transcript. Without the entire command, the skill stops before tracing the code; uncommitted changes cannot be followed through commit history. It is available for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.
What it helps with
- trace why a function was introduced
- recover the requirements behind a file
- find the reason for a line change
- connect a commit to its coding session
Example prompts for the agent
- Use the
explainskill on theparseConfigfunction and find why it was added. - Run
explainforsrc/auth.tsand describe the requirements that led to this file. - Use
explainto investigate why line 42 changed insrc/api.ts.
How to install explain
1Skills CLI (Vercel)
npx skills add entireio/skills --skill explain -a claude-code2Manually: put the files in place
~/.claude/skills/explain/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/explain/
1Skills CLI (Vercel)
npx skills add entireio/skills --skill explain -a codex2Manually: put the files in place
.agents/skills/explain/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add entireio/skills --skill explain -a cursor2Manually: put the files in place
.cursor/skills/explain/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install entireio/skills explain2Manually: put the files in place
.github/skills/explain/SKILL.md1Skills CLI (Vercel)
npx skills add entireio/skills --skill explain -a gemini-cli2Platform CLI
gemini skills install https://github.com/entireio/skills --path skills/explainManually: put the files in place
.devin/skills/explain/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add entireio/skills --skill explain -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about explain
How do I install explain in Claude Code?
Run npx skills add entireio/skills --skill explain -a claude-code, then check ~/.claude/skills/explain/SKILL.md.
What does the explain skill do?
It finds the commit that introduced a function, file, or line, then reads the linked Entire session transcript to explain the code’s intent.
What does explain need to work?
You need the entire CLI, Git-tracked code, and an Entire transcript for the target commit. Uncommitted code cannot be traced through commit history.
Source text
SKILL.md · MIT
--- name: explain description: Explains the intent behind source code by finding original session transcripts. Use explain with a function, file, or line of code to understand why it exists. argument-hint: <function, file, or line> --- # Explain Intent Explain the intent behind source code by tracing it back to the original conversation where it was created. Works with: - **Functions** — Why does this function exist? What problem was it solving? - **Files** — What's the purpose of this file? What requirements drove its creation? - **Line changes** — Why was this specific line added or modified? ## Response Format Begin the first response to this skill invocation with the line: `Entire Explain:` followed by a blank line, then the content. - Apply the header to the **first response of the invocation only.** Do not re-print it on follow-up turns within the same invocation (e.g. after the user answers a clarifying question). - Do **not** include the header on error or early-exit responses (e.g. "Entire CLI is required but not installed", "this file is not tracked by git", "no session transcript was found for this commit"). The header's presence should signal that the skill ran and produced real output. ## Process 1. Verify the `entire` CLI is installed by running `entire version`. - If the command is not found, stop and tell the user: "The Entire CLI is required but not installed. Install it from https://entire.io/docs/cli and try again." 2. Use a Haiku agent to identify the commit that introduced the code via git blame or git log. - If the file is not tracked by git, stop and tell the user: "This file is not tracked by git, so I can't trace its history." - If git blame returns no useful result (e.g., the code is uncommitted), stop and tell the user: "This code hasn't been committed yet, so there's no history to trace." 3. Use a Sonnet agent to read the session transcript via `entire checkpoint explain --no-pager --commit COMMIT_SHA`. - If the command fails or returns no transcript, stop and tell the user: "No session transcript was found for this commit. It may have been created outside of an Entire session (e.g., a manual commit)."
© entireio · MIT · entireio/skills
