litclaude

Plugin litclaude from marketplace litfamily in wjgoarxiv/litfamily. Commands read from the repo's manifest — 4 days ago.

Skills (42)

• autoconference

  Run a root-owned, budgeted Claude Code research conference; routes core, analyze, debate, plan, resume, ship, and survey modes.

• autoresearch

  Run a budgeted Claude Code research family after plan and authority approval; routes core, debug, fix, learn, plan, predict, reason, scenario, security, and ship modes.

• browser-drive

  Drive a real browser to navigate, fill, click, and extract when the answer only exists in a running page. Probes for the external driver and reports its identity before acting, and returns a named blocker rather than silently substituting a fetch, a guess, or a different automation path. Use for exp

• comment-checker

  Comment hygiene workflow adapted for LitClaude: keep comments useful, remove stale narration, and preserve intent-bearing notes.

• debugging

  Systematic Claude Code debugging workflow adapted for LitClaude: reproduce, localize, explain root cause, patch minimally, and verify the real failing surface. Runs a hypothesis-driven loop — form ≥3 hypotheses, investigate, escalate to an oracle triple after 2 failed rounds, confirm root cause, loc

• deep-interview

  Socratic deep-interview loop that turns a vague idea into an execution-ready spec, using a quantitative ambiguity score to gate when requirements are clear enough to build. Use this BEFORE planning or implementation whenever a request is broad, underspecified, or missing acceptance criteria — or whe

• frontend-ui-ux

  Build and inspect authorized interfaces; clarify material choices and keep reviews read-only.

• lit-adhd

  Cross-session briefing for this repo after a break: one card per recent Claude session (status, goal, real progress, done, next), a roadmap timeline, and one next step to continue with `go`. Alias: lit-rewind.

• lit-brainstorm

  Open-ended idea generation for asks like "what could we do", "give me options", "name this" or "brainstorm". Diverge into many genuinely different options through several lenses, cluster and score them against stated criteria, converge on a short list with trade-offs, then hand the pick to deep-inte

• lit-burnoff-file

  lit-burnoff-file: Removes AI-generated code smells from a SINGLE file while preserving functionality. For multiple files, run per file in parallel.

• lit-burnoff

  lit-burnoff: Cleanup workflow for AI-generated bloat, vague wording, fake certainty, overbroad abstractions, and unsupported claims across a bounded set of LitClaude files. Locks behavior with regression/characterization tests FIRST, then runs a categorized, risk-ordered cleanup, then verifies with

• lit-code

  lit-code: Strict Claude Code implementation discipline adapted for LitClaude: TDD, typed boundaries, parse-once input, small files, real integration checks, and no silent lint/type escapes.

• lit-commit

  lit-commit: MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits

• lit-comprehend

  Build a self-contained explainer that makes agent-written work understandable: anchor on what the user already knew, explain the intuition before code, walk the change in conceptual order, offer a micro-world when useful, and close with a quiz. Use this when the user explicitly asks for an explainer

• lit-crucible

  lit-crucible: Claude Code-native adversarial pre-planning skill that clarifies the brief, pressure-tests risks through independent lanes, and hands surviving constraints to /litclaude:lit-plan without implementation.

• lit-diagram-drawer

  Create clear, accessible, Korean-ready diagrams for architecture, workflows, systems, data models, timelines, and conceptual charts, then verify and export them for slides and documents. Use it when a reader will understand the subject faster from a diagram than from prose or a table. Interface page

• lit-docx

  Produce a finished Word document (.docx) — report, 보고서, 기획서, 제안서, plan, manual, memo or journal manuscript — from a request, notes or source files, in a design direction the skill chooses for the content (six tonalities — Report, Brief, Manual, Proposal, Memo, Journal — with covers, callouts, sideba

• lit-handoff

  🔥 lit-handoff — Claude-native continuation packet creation using the complete, immutable bundled handoff source.

• lit-hijack

  Port the know-how in someone else's published work (X posts and long articles, threads, GitHub repos, gists, blog posts, PDFs, video transcripts) into your own skill or system, clean-room. Captures sources with provenance, distils the mechanisms, gates the licence, finds the gaps with file:line evid

• lit-humanizer

  Rewrite model-written English or Korean prose to fit its audience and genre while preserving the user's meaning, voice, facts, and uncertainty.

• lit-init

  lit-init: Initialize a hierarchical AGENTS.md knowledge base for a repository — a root AGENTS.md plus complexity-scored subdirectory files. Use when the user wants to bootstrap or refresh project knowledge for Claude Code, onboard a codebase, generate AGENTS.md/CLAUDE.md guidance, or map an unfamili

• lit-loop

  Evidence-bound LitClaude execution loop with goal/workflow/worktree bootstrap, RED->GREEN tests, manual QA artifacts, cleanup receipts, and continuation ledgers.

• lit-plan

  Strategic LitClaude planner for decision-complete plans with goal/workflow/worktree guidance, tests, manual QA, cleanup, and publish guardrails.

• lit-pptx

  Build a finished PowerPoint deck (.pptx) from a request, notes or source files — first a design direction chosen for the audience and content (thirteen tonalities with their own palette, type, title treatments and layout families; legacy AZURE and plain 4:3 templates, or one learned from the user's

• lit-recap

  Read-only LitClaude session recap: summarize completed work, in-progress work, blockers, evidence paths, and next steps from durable litgoal state plus current-session context.

• lit-schematic

  Draw a physical schematic of equipment or an apparatus — a detailed P&ID with ISA-5.1 tags and control loops, a PFD or equipment layout, an isometric cutaway of a vessel or exchanger, or a journal figure of an experimental setup — as editable SVG with PDF and 600 dpi PNG (a cutaway also as an intera

• lit-scientific-visualization

  🔥 lit-scientific-visualization — Claude-native publication figure workflow backed by the complete immutable scientific-visualization payload.

• lit-team

  lit-team: Coordinate two or more cooperating LitClaude workers behind a durable local team packet \u2014 member briefs with non-overlapping ownership, evidence-bearing reports, and an archive receipt. Use when the user asks for team mode, a team of agents, coordinated parallel work, member briefs, t

• lit-typographic-motion

  Film director for a finished short film from a one-line request, made the same way every time — a treatment first (idea, audience, beats as shots, a drawn subject, copy, sound) in one of four house styles the user picks or fixed rules choose, then a storyboard board round the user can see before the

• litgoal

  Set and keep the finish line. Durable LitClaude goal orchestration with CLI-backed state, explicit success criteria, evidence ledgers, checkpoints, steering, quality gates, and cleanup receipts; lit-loop and start-work run toward the goal it holds.

• litresearch

  Maximum-saturation LitClaude research orchestrator for Claude Code: decompose a research/search/query demand into atomic sub-questions, fan out parallel retrieval swarms via the Workflow tool and litclaude: subagents, recursively chase every lead to convergence, verify contested claims with code run

• litwork

  LitClaude delivery-execution discipline for shipping verified work end-to-end. Use when the user types `litwork`, or asks to ship, implement, finish, land, or fix something with proof rather than a summary. Triages the change set LIGHT or HEAVY, opens a durable notepad, registers one TodoWrite step

• lsp-setup

  Configure a Language Server (LSP) for a specific language so Claude Code tooling — diagnostics, go-to-definition, find-references, rename — works in LitClaude. Use when you need to set up or install a language server, fix 'no LSP server configured' / 'server not installed', choose between servers (b

• lsp

  Claude Code language-server workflow for diagnostics, definitions, references, rename safety, and post-edit checks.

• readme-studio

  Create factual project READMEs with inspected covers, outlined typography and local motion; review requests stay read-only.

• refactor

  Behavior-preserving refactor workflow adapted for LitClaude: characterize first, split safely, preserve public contracts, and verify through tests plus real surface evidence.

• review-work

  Claude-native LitClaude review in two named modes. Plan review checks a plan before start-work (complete, ordered, verifiable); work review runs five lanes over a diff, branch or PR after lit-loop or start-work. It auto-picks from what exists, takes lit review plan or lit review work, and reports fi

• rules

  Claude Code project-rule loading discipline for LitClaude session context, prompt hooks, post-edit checks, and repo-local guidance.

• start-work

  Execute a checked plan file with LitClaude Boulder state, top-level checkbox discipline, goal/workflow/worktree bootstrap, evidence ledgers, and cleanup receipts.

• structural-search

  Search or rewrite source by syntax shape rather than matching bytes — locate calls, declarations, imports, and control flow by their tree structure, then preview and apply codemods safely. Use when a text search would over- or under-match because the target is a code construct, not a string. Verifie

• visual-qa

  Check an interface that is already built: exercise its states at several viewport sizes, capture screenshots, and report visible breakage with that evidence, or name exactly what blocked the check. Use after a page or screen exists; building or restyling it belongs to frontend-ui-ux.

• wikify

  Maintain a task-local Claude Code wiki and reviewed product-local knowledge with inert sources and explicit locality.

Slash commands (23)

• /litclaude:autoconference

  Route one root-owned, budgeted Claude Code autoconference family mode.

• /litclaude:autoresearch

  Run a bounded experiment loop under an approved budget: one change per iteration, judged against a declared metric, benchmark or evaluator, then kept or reverted on that result. Use when a score must improve through repeated measured attempts; also routes debug, fix, learn, plan, predict, reason, sc

• /litclaude:deep-interview

  Clarify broad or underspecified work before planning or implementation.

• /litclaude:init-deep

  Invoke lit-init.

• /litclaude:korean-ai-slop-remover

  Compatibility redirect for the renamed lit-humanizer skill.

• /litclaude:lit-adhd

  Cross-session briefing: what each recent session asked, did and waits on, roadmap gauges, one next step.

• /litclaude:lit-brainstorm

  Brainstorm options for an open question, converge on a scored short list, then hand the pick to deep-interview or lit-plan.

• /litclaude:lit-comprehend

  Build a self-contained explainer that makes agent-written work understandable — intuition, literate walkthrough, a useful micro-world, and a quiz.

• /litclaude:lit-handoff

  Create or refresh a verified LitClaude continuation packet from the complete bundled handoff source.

• /litclaude:lit-hijack

  Port the mechanisms of someone else's published know-how (posts, articles, repos, PDFs, transcripts) into your own skill or system, clean-room, with provenance, a licence gate and parity proof.

• /litclaude:lit-humanizer

  Rewrite a Korean or English draft so it reads in the writer's own voice instead of templated model prose, keeping its meaning, facts, numbers and uncertainty. Use when asked to polish, de-template or make a paragraph, report or message sound less generic.

• /litclaude:lit-init

  Map an unfamiliar or newly inherited repository and leave sparse AGENTS.md guidance so later sessions start oriented. Use when onboarding a codebase, getting oriented in a repo, or refreshing its agent guidance.

• /litclaude:lit-korean

  Compatibility redirect for the renamed Korean and English prose skill.

• /litclaude:lit-loop

  Run LitClaude lit-loop discipline with goal and Dynamic workflow bootstrap.

• /litclaude:lit-plan

  Turn a request or settled decisions into a decision-complete implementation plan before code: ordered steps, exact files, tests and acceptance checks. Use when asked to plan, scope or break down work, including plan-then-build requests.

• /litclaude:lit-recap

  Read-only session recap from the litgoal ledger, durable state, and current-session context.

• /litclaude:lit-rewind

  Alias of lit-adhd: cross-session briefing with progress gauges and one next step.

• /litclaude:lit-scientific-visualization

  Create and verify a publication-ready figure with the bundled LitClaude scientific visualization capability.

• /litclaude:litgoal

  Manage LitClaude litgoal ledger and durable goal state.

• /litclaude:litresearch

  Research a question across sources: find prior work and how others solve it, follow each lead to primary sources, check disputed claims, and return a referenced synthesis or recommendation. Use for surveys, prior-art and landscape questions; a one-fact lookup needs no skill.

• /litclaude:review-work

  Review a patch, diff, branch or open change set in five lanes (scope, tests and evidence, package, security, real-surface readiness) and report findings first with file:line references. Use when someone asks whether changes are correct, risky or safe to merge; fixes come after the findings.

• /litclaude:start-work

  Execute a checked plan with LitClaude start-work discipline.

• /litclaude:wikify

  Route task-local Claude Code wiki work and reviewed local knowledge operations.

Subagents (11)

• korean-prose-editor

  Edits Korean prose for naturalness while preserving meaning.

• korean-style-analyzer

  Analyzes Korean prose for machine-written texture and revision targets.

• librarian-researcher

  Researches official docs and pinned source references.

• lit-executor

  Executes one checked plan task at a time with tests and evidence.

• lit-planner

  Creates decision-complete Claude Code work plans without product-code edits.

• lit-verifier

  Verifies implementation against objective, evidence, and guardrails.

• meaning-preservation-auditor

  Audits Korean revisions for meaning preservation and factual drift.

• native-flow-reviewer

  Reviews Korean revisions for natural flow and native readability.

• polish-orchestrator

  Coordinates strict Korean prose polish decisions and final summary.

• qa-runner

  Runs real QA scenarios and captures artifacts plus cleanup receipts.

• quality-reviewer

  Reviews changed files for defects, maintainability, and safety.

MCP servers (1)

• litclaude

  runs: node ${CLAUDE_PLUGIN_ROOT}/bin/litclaude-mcp.js

Hooks (9)

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" session-start

• UserPromptSubmit

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" user-prompt-submit

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" pre-tool-use

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" post-tool-use

• PostToolUseFailure

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" post-tool-use-failure

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" stop

• SubagentStart

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" subagent-start

• SubagentStop

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" subagent-stop

• SessionEnd

  node "${CLAUDE_PLUGIN_ROOT}/bin/litclaude-hook.js" session-end

Language servers (1)

• typescript

Similar plugins