← ClaudeAtlas

wise-grilllisted

Deep-research ANY underspecified subject — a tracker ticket (Jira, Linear, GitHub, …), a doc link (Confluence, Notion, RFC, Google Doc), or a free-form prompt / question — across every reachable source: the subject's own comments + screenshots, linked docs, Slack discussions, Google Drive, design files, the codebase and its git history. It classifies the input first, builds a normalized understanding of what the subject actually means, gap-checks the evidence, then forks by type: a ready-to-implement `PLAN-<ref>.md`, a `BLUEPRINT-<ref>.md` with targeted questions (per-person for tickets / docs, asked inline for prompts), or — for a pure question — a researched `ANSWER-<ref>.md`. Re-run with answers to upgrade a blueprint into the plan. Invoked as `/wise-grill` (bare alias) or `/wise:wise-grill` (canonical). Use when the user says "grill this ticket", "grill me", "grill this doc", "what does this ticket actually mean", "research this ticket", "build context around PROJ-123", "research this topic and plan it",
e1024kb/wise-claude · ★ 4 · AI & Automation · score 80
Install: claude install-skill e1024kb/wise-claude
# /wise-grill — understand an underspecified subject, then plan it, answer it, or grill the right people Before asking any user question, read and follow the [question lifecycle](../../references/workflow-host-control.md#keep-asynchronous-questions-open). Keep asynchronous prompts open until answered; this rule does not authorize questions in autonomous or otherwise prompt-free procedures. ## Why this skill exists The reasoning behind a piece of work rarely lives where the work is stated. "Fix the export timeout" may mean "raise a config value" — decided in a 40-message Slack thread the ticket never links; a spec page may assume vocabulary only its author's team shares; a one-line prompt may hide three unstated decisions. `/wise-grill` is the step **before** anything is built on such input: it classifies what it was given, researches everything reachable, states what the subject actually means, and forks — a plan when the evidence supports one, a researched answer when the input was a question, or a blueprint whose questions are addressed to whoever can close each gap (a specific person from the evidence, or the user when nobody else can answer). Facts get researched; only decisions get asked. ## Arguments `$ARGUMENTS` — the **subject** plus optional guidance: - A **URL or bare ticket id** first (`https://acme.atlassian.net/browse/PROJ-1`, `PROJ-123`, `#678`, a Confluence / Notion / Google-Docs link, a path to an existing `BLUEPRINT-*.md`) — everything after the fir