Revisit dashboard — one scan of everything you parked to re-check later, across every skill's memory. Reads out/*/tracker.md and the other memory files skills leave behind (ideate PARK "revive when", verdict/scout revisit-when triggers, refactor WATCH candidates, learn spaced-repetition due dates, jobfit roles to re-check) and surfaces what's due now: date-based items past their date, trigger-based items whose condition may have fired. Renders one prioritized "due to re-check" list in chat — grouped by skill, most overdue first — quoting the exact tracker line and its revive trigger so you can act or defer. Strictly read-only: it never edits a tracker or fires the follow-up skill; it points, you decide. Use for "what do I need to revisit", "what's due to re-check", "anything parked worth reviving", "show my revisit queue" — e.g. "/revisit", "/revisit ideate".
Structured idea generation for a project or a blank-slate problem — ideas worth pursuing, not the first one that sticks. Grounds in the current repo (AGENTS.md/README) or a freeform problem, then diverges across named lenses (adjacent user, removed constraint, inversion, and more) so a run yields range, not ten variations of one idea. Fights premature convergence — nothing judged until the divergence quota is met — then verdicts each idea EXPLORE/PARK/DROP, where DROP is cheap. EXPLORE items become seeds for priorart (is it novel?) or feature (build it); verdicts persist in out/ideate/tracker.md so repeat runs open with what's new. Keyless. Use to generate, brainstorm, or explore ideas or new directions for a project or problem — e.g. "/ideate", "/ideate <topic>", "brainstorm features for X". For whether an idea already exists use priorart; for competitor features use scout; for choosing between named options use verdict.
Scaffold a new skillhub skill, or repair one that drifted, across all four registration surfaces in one motion — folder, README table row, marketplace plugin, and trigger evals — then prove it with validate-skills.py. User-invoked.
End-of-session shipping gate — "prove it works, then ship it." Runs an evidence checklist (full test suite, lint/typecheck, build, and actually running the change — output quoted, never asserted), then a fresh-context two-stage review by a sub-agent that sees only the diff and the spec: spec-compliance first, correctness second, style never — joined by a cross-model second opinion when a codex/gemini CLI is installed. Flags fake-green tripwires (edited or deleted tests, new TODOs or skips, hardcoded expectations) and ends with a verdict — SHIP, FIX FIRST, or NEEDS HUMAN — before drafting the commit/PR for the user's approval. Use at the end of any coding session or when the user asks "is this done", "ready to ship?", "/done", "wrap this up", "review and commit this". It is the closing step of both feature and bugfix, but works standalone on any uncommitted or branch diff.
Prior-art check before you build — does this idea already exist? Takes a project/tool/library idea, reframes it in the vocabularies different communities would use, searches where builders publish (code registries, Show HN, arXiv), traces each match one dependency-layer down to the real incumbent, and returns a locator-backed landscape plus exactly one verdict: Build / Fork X / Contribute to Y / Use Z / Investigate first. Checked ideas persist in out/priorart/checked.md, so re-checking one opens with what changed. Keyless. Use for "does something like X already exist", "has anyone built this", "am I reinventing the wheel", "check prior art before I build" — e.g. "/priorart <idea>". For your existing project vs its peers use scout; for choosing between named options use verdict.
Job-fit evaluation and discovery for job seekers — "find roles that fit me" and "should I apply to this one?" DISCOVER searches job boards for openings matching your profile; EVALUATE takes job URLs/descriptions you provide. Both research compensation, company signal, and posting legitimacy in parallel, score each role A–F, and emit a ranked decision brief with tailored CV-bullet suggestions. Evaluated roles persist in out/jobfit/tracker.md so repeat runs skip what you passed on. Keyless and human-in-the-loop: it never applies for you. Use to find matching jobs, triage postings, decide whether a role is worth applying to, or tailor a CV to a JD — e.g. "find jobs that fit my CV", "/jobfit <url>", "score these roles against my CV". For community buzz on a company use pulse.
End-to-end feature workflow around the agent — spec by interview, a plan of 2–5-minute tasks, test-first execution with checkpoint commits, then an evidence-gated finish. Effort-scaled: a one-sentence diff skips straight to implementation; a real feature gets spec.md → plan.md → task-by-task TDD, with all state in out/dev/<change>/ so any later session resumes at the first unchecked task. Human-in-the-loop: the spec and the plan are approved (and editable) before any code is written, and nothing ships without the done gate. Use when the user wants to build, add, or implement a feature or start non-trivial coding work — e.g. "/feature add rate limiting", "implement X", "build a Y that Z", "resume the <change> feature". For fixing something broken use bugfix; for just the end-of-session shipping gate use done; for this whole loop end-to-end without approval stops, suggest the user run /autopilot (explicit invocation only).
Personalized tutor with memory across sessions — "teach me X, at my pace." Builds a syllabus with a pass rubric per unit, teaches one unit per session: a recall quiz on what's due (date-based spaced repetition), examples matched to your background, and an active-recall check graded against the rubric with confidence tags. Progress and weak spots persist in out/learn/<topic>.md, so sessions resume and re-drill what was missed; fact-sensitive content is verified by web search, not memory. Keyless. Use to learn or study a topic — e.g. "/learn rust ownership", "teach me kubernetes", "quiz me on X", "continue the SQL lessons"; "/learn" alone lists topics in progress. For community buzz use pulse; for choosing between technologies use verdict.