skills.rest
Shtian
ShtianCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

why

Investigate design rationale behind code by querying git history and MCP evidence sources in parallel.

4|1|Updated Dec 16, 2023
Search Tags:#investigation#mcp#design rationale#git history#postmortem#evidence synthesis#code archaeology
One-click install
npx skills add https://github.com/Shtian/AuthentiClash --skill why-shtian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: why
Source: https://github.com/Shtian/AuthentiClash/tree/main/.claude/skills/why
Command: npx skills add https://github.com/Shtian/AuthentiClash --skill why-shtian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Code rarely explains why it exists. This Skill answers "why does X work this way" questions by tracing design rationale, tradeoffs, and motivating constraints across historical evidence instead of guessing from the code itself. ## Core Features & Use Cases - Parallel Evidence Investigation: Spawns one investigator per evidence category (source control, issue tracker, docs, chat, observability, error tracking, analytics warehouse) based on available MCP servers. - Confidence-Tiered Synthesis: Classifies every claim as Direct, Supported, Inferred, Speculative, or Unknown, with citations and an explicit "What We Don't Know" section. - Use Case: Ask "why is this API response clamped at 100 items?" and receive a cited answer drawing on the original PR, linked tickets, monitoring thresholds, and any contradicting evidence. ## Quick Start Ask why a specific function, threshold, or pattern in the current codebase was designed the way it was.

Frequently Asked Questions about why

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find out why code was written a certain way?▼

Ask a why question about the target code and the Skill anchors it via git blame and log, then spawns parallel investigators across source control, tickets, docs, chat, and telemetry. A synthesizer returns a cited, confidence-tiered answer.

What evidence sources does a code rationale investigation use?▼

It covers seven categories: git and GitHub PRs, issue trackers like Linear or Jira, long-form docs like Notion or Confluence, team chat like Slack, observability like Datadog, error tracking like Sentry, and analytics warehouses like Databricks.

Does the why skill work without MCP servers configured?▼

Yes, but with reduced coverage. Source control investigation via git and gh always runs, while categories without a matching MCP are documented as gaps in the Sources Consulted section rather than silently skipped.

How does it handle uncertain or missing historical evidence?▼

Claims are tiered as Direct, Supported, Inferred, Speculative, or Unknown, with hedged phrasing for inferences. Missing evidence is reported explicitly with the exact searches performed, never filled with confident guesses.

When should I use why instead of asking how code works?▼

Use why for design rationale, tradeoffs, and motivating constraints behind code. Use the companion how skill for runtime behavior and mechanics, since why deliberately avoids inferring intent from the code itself.

Related Skills

Explore More Software Engineering Skills→
mastra-aimastra-ai
27.6k

understand-issue

Investigate GitHub issues by tracing code history and architecture to diagnose root causes.

Official
Advanced
Z1-TestZ1-Test

change-maintenance-specification

Generate structured change specification documents for feature modifications.

Official
Advanced
liujiayi3703liujiayi3703

how-it-works

Explain Claude Code's memory injection and session context retention.

Community
Basic
udecodeudecode
1.2k

drafting-pr

Create and update GitHub draft pull requests with conventional commits.

Official
Intermediate