Investigate design rationale behind code by querying seven evidence sources in parallel.
npx skills add https://github.com/jnyross/pstack-muse --skill why-jnyross
Please help me install this Agent Skill. Skill: why Source: https://github.com/jnyross/pstack-muse/tree/main/skills/why Command: npx skills add https://github.com/jnyross/pstack-muse --skill why-jnyross
High-intent search queries and answers about installing and using this skill.
Anchor the investigation with git blame and git log on the target lines, then search PR discussions, tickets, docs, chat threads, and telemetry in parallel. This Skill automates that workflow and returns a cited, confidence-calibrated answer.
The how skill explains what code does and how it works at runtime. The why skill explains the forces that shaped it: design rationale, business constraints, rejected alternatives, and incident history.
Only git and gh are guaranteed; the other six categories (Linear, Notion, Slack, Datadog, Sentry, Databricks or equivalents) are discovered at runtime. Missing MCPs are reported as explicit coverage gaps rather than silently skipped.
Yes, it proceeds with whatever sources are available and documents unsearched categories in the Sources Consulted section. Null results and unavailable sources are treated as first-class evidence about how the decision was recorded.
Historical evidence is fragmentary and sometimes contradictory, so every claim is tiered as Direct, Supported, Inferred, Speculative, or Unknown. Hedged phrasing is enforced so users can distinguish cited facts from interpretation.
amanpal3Searches codebases with keywords before reading targeted file sections to reduce context usage.
li3pPlan internal code refactoring while preserving public API signatures.
ncy08Map Claude Code's internal architecture to locate modules and understand data flow.
sparkfabrikCreates Architecture Decision Records using adr-tools or manual templates.
