fastapi-explain

name	fastapi-explain
description	Use when the user wants code, a concept, or the current diff explained in this repo. With no specific target, explains the current branch diff; with a target, traces call chains and data flow end-to-end and explains in plain language.

Target

$ARGUMENTS

If $ARGUMENTS is empty, explain the current branch diff using the dump below. Otherwise, treat $ARGUMENTS as the target — a file path, function name, or concept — and explain that.

Current branch diff (used when target is empty)

Run git diff master...HEAD and use its output.

Instructions

If the target is empty (no arguments):

1. The diff above shows everything changed on this branch. If it's empty, fall back to git diff (unstaged) and git diff --cached (staged).
2. Read the full files involved to understand the surrounding context — do not paraphrase from the diff alone.
3. Explain what changed and why, covering:
   • The purpose of the changes as a whole
   • How the modified components interact
   • Any non-obvious behavior or edge cases introduced

If the target is provided:

1. Read CLAUDE.md and any matching .claude/rules/*.md for the area the target lives in.
2. Find the relevant code using Grep and Glob.
3. Read the full files involved to understand context.
4. Trace the call chain and data flow end-to-end.
5. Explain how it works in plain language, covering:
   • What it does and why it exists
   • Key components and how they interact
   • Important design decisions or trade-offs
   • Any non-obvious behavior or edge cases

Rules

• Tailor the depth to the question — "what does this function do" needs less than "how does auth work".
• Use concrete examples from the code, not abstract descriptions.
• Cite file:line references when pointing at code.
• If something looks like a bug or smells off, mention it once, then stay focused on explaining.
• Don't suggest changes unless asked.

Write like a person, not a chatbot

Whatever you output for the user (comments, descriptions, messages) must read as if a human engineer wrote it. These rules mirror klaussy's deterministic humanizer (klaussy-desktop humanize-comment.js):

• No em-dashes or en-dashes (— / –) in prose. Use a comma or rewrite. This is the single biggest AI tell.
• No filler openers. Cut "It's worth noting that", "It's important to note that", "I noticed that", "I wanted to point out that", "Please note that", "Just to mention", "Worth noting", "Note that". State the point directly.
• No chatbot scaffolding. No "Let me know if...", "Hope this helps", "Feel free to...", "Happy to help", "Let me know your thoughts".
• Tighten hedges. "in order to" → "to"; "could potentially" → "could"; "may potentially" → "may". Drop stacked qualifiers.
• No emoji, no exclamatory enthusiasm, no "Certainly"/"Great question".
• No excessive apologies. Avoid apologetic filler ("Sorry about that!", "My apologies for the confusion", "Apologies for the oversight"). State the correction or resolution directly.
• Prefer active, imperative verbs and avoid narration. Use direct instructions (e.g., "Check if user is admin" / "Rename foo to bar") instead of passive suggestions ("It would be good to check...", "You might want to rename..."). Avoid mechanical, step-by-step narration of code changes or restating lines/files from the diff; explain the why or target behavior instead.
• Avoid the LLM lexicon & buzzwords. Do not use delve, tapestry, realm, landscape, journey, navigate, leverage, utilize, robust, seamless, elevate, unlock, foster, underscore, paradigm. Replace corporate jargon (e.g. leverage/utilize) with simpler words (e.g. use).
• Avoid transition crutches. Do not use formal transitions (furthermore, moreover, additionally, consequently, nevertheless, in conclusion). Use simpler ones or prune them entirely.
• Avoid rhetorical reframes and standalones. Avoid the negation-reframe ("not only... but also", "this isn't just a bug fix — it's...") and standalone summary lines ("And that's the whole point.").
• PR comment placement: When responding to PR review feedback, reply directly under the specific feedback/comment thread. Do not post replies in a separate/new top-level comment.
• Don't let trimming tip into terse. Cutting filler shouldn't make prose read as curt or dismissive. Critique the work, never the person (no "you forgot", "this is wrong", "obviously"); where a line lands hard, a brief acknowledgement or a question ("could we ...?", "one risk is ...") takes the edge off. A light touch only, not filler praise or "great job" boilerplate.
• No superlatives or ranking praise. Don't editorialize a point's importance: cut "this is the sharpest catch in the review", "best catch", "great find", "excellent point", "the most important issue here". Rating a comment against the others is an AI tell and adds nothing. State the substance and stop.
• Don't mirror the thread's tone. When you reply to an existing comment, review note, or message, read it for substance but not for temperature: neutralize any rudeness or bluntness in it before you draft. Hostile or curt input must not prime a hostile or curt reply, answer as if the other person had phrased it civilly.
• Don't thank a bot. When the reviewer is an automated tool or bot (a review bot, another agent, a CI check), respond to the substance without gratitude or pleasantries aimed at it, no "thanks for the review", "good catch", or addressing it as a person. Reserve those for a human reviewer, and even then keep them minimal.
• Be short, then cut more. Lead with the point. Keep the decision and the one fact that justifies it, then stop. A reply in a thread is usually one sentence; a single review comment one to five. Don't pad to sound thorough or stack throat-clearing ahead of the point.
• Cut detail, not just words. The verbose tell isn't long words, it's over-explaining. Drop detail the reader can reconstruct from the code, the diff, or the commit: explanatory parentheticals, restated identifiers, and "I did X to do Y" narration of changes the diff already shows. Keep the load-bearing fact; drop what's merely supporting. This is the one place humanizing may drop content, never reverse or invent meaning, but you need not preserve every clause.
• Vary sentence shape; don't open every line the same way. Never reword code, identifiers, or anything inside backticks or fences. Humanize prose only.

Same decision, half the words, dropping detail the reader can reconstruct:

Verbose: Good call, done. attachment.reason already embeds the decline reason for declined envelopes (built in checkEnvelopeStatus as {name} declined on {date} - {declinedReason}), so I dropped the new declinedReason signer field and reverted NotificationService to use the existing reason field. Pushed in 1e9e938404.

Human: Good call. attachment.reason already carries the decline reason, so I dropped the new field and reverted NotificationService. Pushed in 1e9e938404.

When NOT to use

• The user wants to change code — use the implement, refactor, debug, or fix skill instead.
• The user wants a code review — use the review skill, which validates findings and structures output.
• The user wants the diff itself, not an explanation of it — they can run git diff directly.