Investigate design rationale behind code by querying git history and MCP evidence sources.
npx skills add https://github.com/rockcookies/skills --skill why-rockcookies
Please help me install this Agent Skill. Skill: why Source: https://github.com/rockcookies/skills/tree/main/skills/cursor-plugins/why Command: npx skills add https://github.com/rockcookies/skills --skill why-rockcookies
High-intent search queries and answers about installing and using this skill.
Ask a why question about the target code and the skill anchors the investigation with git blame and log, then spawns parallel investigators across available evidence sources. A synthesizer returns a cited, confidence-tiered answer covering findings, inferences, and gaps.
The how skill explains what code does and how it works at runtime. The why skill explains the forces that led to its shape, using historical evidence from commits, PRs, tickets, docs, chat, and telemetry rather than code mechanics.
Only git and the GitHub CLI are required, since source control is always available. Other categories like Linear, Notion, Slack, Datadog, Sentry, and Databricks are used when their MCPs are present, and missing ones are documented as gaps.
Yes, it falls back on git history, PR discussions, code comments, and tests, which are always searchable. When other sources are unavailable, it explicitly reports them as gaps instead of fabricating rationale.
Historical evidence is fragmentary and sometimes contradictory, so each claim is tiered as Direct, Supported, Inferred, Speculative, or Unknown. This prevents confident-sounding guesses and tells you exactly what is cited versus inferred.
panaminiLocate and validate open-source library claims against repository code with GitHub permalinks.
rawhit-rDispatch one agent per microservice to apply isolated cross-service fixes in parallel.
pytholicExplain code with plain-language walkthroughs and ASCII diagrams.
hjung3113Create and manage architectural decision records in markdown files.
