Directory
‹ Back to apps

litgrok

39 skills that take a request from plan to a tested change and a review, then write a handoff note the next session picks up. They also cover research with sources, debugging, Word and PowerPoint files, and Korean writing.

What’s inside

39 skills
  • SkillautoconferenceConvene bounded, independent subagent lanes for evidence-based deliberation, rebuttal, and synthesis.
  • SkillautoresearchRun a bounded research campaign with independent subagent lanes, evidence gates, and parent synthesis.
  • Skillbrowser-driveConduct a bounded web or browser task while respecting host permissions, sandbox network limits, and user-controlled state.
  • Skillcomment-checkerAudit code comments after bounded edits for accuracy, necessity, safety, and maintenance value, using the diff and current source context.
  • SkilldebuggingDiagnose a reproducible tool or program failure while preserving evidence, permissions, and sandbox boundaries.
  • Skilldeep-interviewResolve consequential ambiguity through a structured interview and an approval-gated plan before execution.
  • Skillfrontend-ui-uxBuild and inspect a working interface from a clear design request; clarify material ambiguity, or review without edits when requested.
  • Skilllit-brainstormOpen a question into many different options, group and score them against stated criteria, and converge to a short list the user picks from. Use for open asks such as what could we do, name ideas, or which direction. It proposes and never implements.
  • Skilllit-burnoff-fileClean generated prose patterns in one authorized file while preserving supported meaning and verifying the diff.
  • Skilllit-burnoffRemove generated-code clutter across an authorized change while preserving behavior, test coverage, and repository boundaries.
  • Skilllit-codeImplement a bounded code change with explicit requirements, permissions, sandbox limits, and observable verification.
  • Skilllit-commitPrepare scoped Git changes, inspect staging and history, and create a verified commit within explicit repository and publication boundaries.
  • Skilllit-comprehendBuild a bounded, evidence-linked understanding of a requested scope before consequential work begins.
  • Skilllit-crucibleStress-test an approach through bounded read-only exploration, contradiction checks, and a synthesized planning handoff.
  • Skilllit-diagram-drawerCreate clear, accessible, Korean-ready diagrams for architecture, workflows, systems, data models, timelines, and quantitative relationships. Use for conceptual diagrams; use frontend-ui-ux for interfaces and lit-scientific-visualization for plots of measured data.
  • Skilllit-docxCreate, edit, lint, audit, and convert Word documents and reports. A design direction is chosen first (six restrained tonalities that differ in structure, or a named publisher profile) and named with two alternatives. Select for report, doc, docx, Word, 보고서, 리포트, 기획서, 제안서, 문서, 워드, including a bare lit request. Produce a styled DOCX from Markdown by default.
  • Skilllit-handoffPrepare a precise, secret-safe resume contract for continuing work in a later agent session.
  • Skilllit-humanizerRevise model-written prose so it fits the reader, preserves meaning, and removes only clear drafting residue.
  • Skilllit-initInitialize scoped project guidance by inspecting existing instruction surfaces, resolving conflicts, and verifying placement.
  • Skilllit-planBuild an approval-ready implementation plan from a concrete objective before editing.
  • Skilllit-pptxBuild, revise, validate, and render PowerPoint presentations from Markdown, choosing a design direction first (eight tonalities with their own palette, title treatments and layout families) and naming it with two alternatives. Select for slides, deck, presentation, PPT, pptx, 발표자료, 발표, 슬라이드, 덱, 피피티, including a bare lit request. Pretendard is bundled; legacy AZURE and BOILERPLATE templates only when named.
  • Skilllit-recapReconstruct a concise, evidence-backed account of earlier agent sessions.
  • Skilllit-scientific-visualizationUse when verified evidence must become a publication-ready scientific figure and caption backed by the packaged plotting corpus.
  • Skilllit-teamCoordinate independent work lanes with bounded task packets, clear ownership, and parent-owned integration and verification.
  • Skilllit-typographic-motionDirect a finished film (video, clip, motion graphics, lyric video, title sequence, 영상, 모션그래픽, 키네틱 타이포, 가사 영상) from a treatment, rendered by LitGrok's own type engine or stage capture and QA gate, or a silent, seamless README cover loop. Not for editing existing footage, interface background video, slide decks, scripts or thumbnails.
  • SkilllitgoalSet the finish line for a piece of work as one checkable objective with criteria, so work runs toward it. Shapes the objective and the native goal line; no goal runtime is claimed.
  • SkilllitgrokExplain the LitGrok skill, rule, hook-layout, and dependency-free npx installer payload, and what loads in Grok Bot and Cursor, without overstating live Grok Build behavior.
  • SkilllitresearchConduct bounded, source-traceable research with the host's search tools and documented MCP connections without overstating evidence.
  • SkilllitworkTurn a request into a bounded session checklist with honest receipts, backed by LitGrok's passive hooks and event ledger where they run.
  • Skilllsp-setupInspect a project's language-server visibility, from Grok Build's host inventory or the host's own language features, and report the bounded fallback when direct diagnostics are not exposed.
  • SkilllspUse language-server code intelligence for a bounded question: Grok Build's optional built-in LSP tool within its default-off boundary, or the host's own language features.
  • Skillreadme-studioCreate a factual README with an original or supplied cover, outlined bilingual typography, local motion and static delivery; review without edits when requested.
  • SkillrefactorRestructure an existing code path in an isolated git worktree while preserving behavior and repository state.
  • Skillreview-workReview a plan before work starts, or the finished work after it. Picks plan review or work review from what exists, or takes the mode you name, and reports evidence-ranked findings from read-only lanes.
  • SkillrulesInspect and explain the project guidance an agent host loads (AGENTS-family files, Grok Build rules), its precedence, trust state, and project-config boundary.
  • Skillstart-workExecute an approved plan with bounded ownership, verification, and isolated work when useful.
  • Skillstructural-searchInvestigate code structure with repository search, reads, and language-server code intelligence where the host offers it, without inventing operations.
  • Skillvisual-qaUse when a rendered interface or visual artifact needs screenshot-backed quality review.
  • SkillwikifyBuild or maintain a local, source-backed project knowledge map while keeping its state explicit under .grok/.