All authors
Claude Skills by wjgoarxiv
github.com/wjgoarxiv61 skills2 installs60 views
- Lit HumanizerRevise model-written prose so it fits the reader, preserves meaning, and removes only clear drafting residue.Votes: 0GitHub stars: 4
- AutoconferenceRun a root-owned, budgeted Claude Code research conference; routes core, analyze, debate, plan, resume, ship, and survey modes.Votes: 0GitHub stars: 2
- AutoresearchRun a budgeted Claude Code research family after plan and authority approval; routes core, debug, fix, learn, plan, predict, reason, scenario, security, and ship modes.Votes: 0GitHub stars: 2
- Browser DriveDrive 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 explicit browser work; not for explaining how the web works, and not for verifying a rendered surface, which is visual-qa.Votes: 0GitHub stars: 2
- Comment CheckerComment hygiene workflow adapted for LitClaude: keep comments useful, remove stale narration, and preserve intent-bearing notes.Votes: 0GitHub stars: 2
- DebuggingSystematic 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, lock with a failing test, fix minimally, QA the real surface, scrub artifacts. The actual HOW lives in `references/` — open them. Triggers: 'debug this', 'why is X not working', 'hanging', 'attach a d...Votes: 0GitHub stars: 2
- Deep InterviewSocratic 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 when the user says "interview me", "ask me everything", "don't assume", or "deep interview".Votes: 0GitHub stars: 2
- Frontend Ui UxBuild and inspect authorized interfaces; clarify material choices and keep reviews read-only.Votes: 0GitHub stars: 2
- Lit Burnoff Filelit-burnoff-file: Removes AI-generated code smells from a SINGLE file while preserving functionality. For multiple files, run per file in parallel.Votes: 0GitHub stars: 2
- Lit Burnofflit-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 quality gates and a critical review. Covers 10 slop categories including performance equivalences, needless abstraction, and oversized modules. Use when the user asks to \"remove slop\", \"clean AI...Votes: 0GitHub stars: 2
- Lit Codelit-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.Votes: 0GitHub stars: 2
- Lit Commitlit-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 unless the user asks for git work.Votes: 0GitHub stars: 2
- Lit ComprehendBuild 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 or needs to reason with a substantial change. Propose the scope and wait whenever the target had to be inferred.Votes: 0GitHub stars: 2
- Lit Cruciblelit-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.Votes: 0GitHub stars: 2
- Lit Diagram DrawerCreate 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 pages belong to frontend-ui-ux; plots of measured scientific data belong to lit-scientific-visualization.Votes: 0GitHub stars: 2
- Lit DocxProduce a finished Word document (.docx) — report, 보고서, 기획서, 제안서, plan, memo or journal manuscript — from a request, notes or source files, with Korean-first Pretendard typography (korean-generic), a plain styled profile, or Elsevier/ACS/IEEE/Nature publisher styling; convert DOCX or PDF to clean Markdown, edit an existing .docx in place, render PDF, and gate the result with integrity, prose-lint and design checks plus rendered pages. Use it whenever the deliverable is a document file (워드, do...Votes: 0GitHub stars: 2
- Lit Handoff🔥 lit-handoff — Claude-native continuation packet creation using the complete, immutable bundled handoff source.Votes: 0GitHub stars: 2
- Lit HumanizerRewrite model-written English or Korean prose to fit its audience and genre while preserving the user's meaning, voice, facts, and uncertainty.Votes: 0GitHub stars: 2
- Lit Initlit-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 unfamiliar repo. Adapted for the Claude Code host: discovery via background explore subagents + the LSP tool, parallel generation via Dynamic workflow.Votes: 0GitHub stars: 2
- Lit LoopEvidence-bound LitClaude execution loop with goal/workflow/worktree bootstrap, RED->GREEN tests, manual QA artifacts, cleanup receipts, and continuation ledgers.Votes: 0GitHub stars: 2
- Lit PlanStrategic LitClaude planner for decision-complete plans with goal/workflow/worktree guidance, tests, manual QA, cleanup, and publish guardrails.Votes: 0GitHub stars: 2
- Lit PptxBuild a finished PowerPoint deck (.pptx) from a request, notes or source files — Markdown slide source compiled through designed templates (AZURE-PRO blue and white by default, plus A2Z and plain 4:3 variants, or one learned from the user's own deck), native editable charts and KPI cards, Pretendard fonts embedded, a QA gate for overflow, contrast, sparse or table-only slides and blanks, rendered-page review and a 정/반/합 improvement loop. Use it whenever someone wants slides, a deck, a present...Votes: 0GitHub stars: 2
- Lit RecapRead-only LitClaude session recap: summarize completed work, in-progress work, blockers, evidence paths, and next steps from durable litgoal state plus current-session context.Votes: 0GitHub stars: 2
- Lit Scientific Visualization🔥 lit-scientific-visualization — Claude-native publication figure workflow backed by the complete immutable scientific-visualization payload.Votes: 0GitHub stars: 2
- Lit Teamlit-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, team state, or team cleanup. Not for a single one-shot delegation; use a plain subagent for that.Votes: 0GitHub stars: 2
- Lit Typographic MotionFilm director for a finished short film from a one-line request — writes a treatment first (idea, audience, format, beats, a drawn subject, copy, sound), then takes the stage path for films that show things (a model-authored HTML/SVG/Canvas/WebGL page captured frame by frame by the bundled deterministic renderer, 16:9 or 9:16) or the type path for films whose words are the film (kinetic type, lyric or quote video, title sequence, through the bundled WebGL2 type engine), with a generated sound...Votes: 0GitHub stars: 2
- LitgoalDurable LitClaude goal orchestration with CLI-backed state, explicit success criteria, evidence ledgers, checkpoints, steering, quality gates, and cleanup receipts.Votes: 0GitHub stars: 2
- LitresearchMaximum-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 runs or adversarial review, and prepare a source-grounded answer with natural references. Includes resilient public-source retrieval lanes with validator-first evidence checks and route traces. Activa...Votes: 0GitHub stars: 2
- LitworkLitClaude 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 per atomic unit, and drives PIN -> RED -> GREEN -> SURFACE -> CLEAN per success criterion, pairing every criterion with a real Manual-QA channel artifact and a cleanup receipt. Tests alone never pr...Votes: 0GitHub stars: 2
- Lsp SetupConfigure 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 (basedpyright vs pyright vs ruff), or add a language to plugins/litclaude/.lsp.json. Routes by file extension to references/<language>/README.md for the server choice, per-OS install commands, the .l...Votes: 0GitHub stars: 2
- LspClaude Code language-server workflow for diagnostics, definitions, references, rename safety, and post-edit checks.Votes: 0GitHub stars: 2
- Readme StudioCreate factual project READMEs with inspected covers, outlined typography and local motion; review requests stay read-only.Votes: 0GitHub stars: 2
- RefactorBehavior-preserving refactor workflow adapted for LitClaude: characterize first, split safely, preserve public contracts, and verify through tests plus real surface evidence.Votes: 0GitHub stars: 2
- Review WorkClaude-native 5-lane LitClaude review orchestrator with findings-first output, evidence artifacts, manual QA, security/provenance review, real-surface readiness, aggregation rules, and cleanup receipts.Votes: 0GitHub stars: 2
- RulesClaude Code project-rule loading discipline for LitClaude session context, prompt hooks, post-edit checks, and repo-local guidance.Votes: 0GitHub stars: 2
- Start WorkExecute a checked plan file with LitClaude Boulder state, top-level checkbox discipline, goal/workflow/worktree bootstrap, evidence ledgers, and cleanup receipts.Votes: 0GitHub stars: 2
- Structural SearchSearch 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. Verifies the structural engine's identity before trusting it, and degrades to labelled textual search or a named blocker rather than pretending.Votes: 0GitHub stars: 2
- Visual QaVerify an observable interface with material evidence, or return an exact blocked capability receipt; load detailed LitClaude guidance lazily.Votes: 0GitHub stars: 2
- WikifyMaintain a task-local Claude Code wiki and reviewed product-local knowledge with inert sources and explicit locality.Votes: 0GitHub stars: 2
- AutoconferenceMulti-agent research conference that spawns parallel autoresearchers with symposium sharing, adversarial peer review, and insight synthesis. Reads a conference.md, orchestrates N researchers in structured rounds, and produces a synthesized result combining the best findings. TRIGGER when: user mentions "autoconference" or "conference" with research context; user wants multiple researchers competing or collaborating; user wants parallel autoresearch with peer review; user mentions "conference....Votes: 0GitHub stars: 2
- AnalyzePost-conference analysis — compares researcher trajectories, identifies failure modes, extracts transferable insights, and produces an insight taxonomy. TRIGGER when: user wants to analyze conference results, understand what happened, extract learnings from a completed conference. DO NOT TRIGGER when: user wants to run a conference (use autoconference) or ship results (use ship).Votes: 0GitHub stars: 2
- AutoconferenceCore conference loop — spawns N parallel autoresearchers, runs 4-phase rounds (independent research, poster session, peer review, knowledge transfer), and produces synthesized results combining the best findings.Votes: 0GitHub stars: 2
- DebateAdversarial 2-researcher debate mode. One researcher argues Position A (pro), the other argues Position B (con). Structured rounds with an Opus judge. TRIGGER when: user wants a debate, adversarial evaluation, pro/con analysis, wants to test opposing viewpoints. DO NOT TRIGGER when: user wants collaborative multi-researcher conference (use autoconference).Votes: 0GitHub stars: 2
- Plan8-step interactive wizard that produces a fully configured conference.md file. TRIGGER when: user wants to set up a new conference, plan a conference, create conference.md. DO NOT TRIGGER when: user wants to run an existing conference (use autoconference).Votes: 0GitHub stars: 2
- ResumeResume an interrupted autoconference from its last checkpoint. Reads conference_events.jsonl to find last completed phase and resumes. TRIGGER when: user wants to resume/continue a conference, conference was interrupted. DO NOT TRIGGER when: user wants to start a new conference (use autoconference or plan).Votes: 0GitHub stars: 2
- Ship8-phase pipeline to convert conference results into paper-ready output. Formats, verifies, and packages conference findings for publication. TRIGGER when: user wants to ship/publish/format conference results, create a paper/report/blog post from conference output. DO NOT TRIGGER when: user wants to run a conference (use autoconference).Votes: 0GitHub stars: 2
- SurveySystematic multi-database literature survey. 3 researchers cover non-overlapping sources (databases, time periods, or methodologies) with citation-chain knowledge transfer. TRIGGER when: user wants a literature survey, systematic review, paper survey, wants to cover multiple databases or time periods. DO NOT TRIGGER when: user wants to optimize a metric (use autoconference) or read a single paper (use scientific-reading).Votes: 0GitHub stars: 2
- AutoresearchAutonomous research and experimentation toolkit with 10 commands. Core loop inspired by Karpathy's autoresearch — generalizes to any domain with mechanical evaluation, overnight persistence, and zero dependencies. TRIGGER when: user wants autonomous experiments; user mentions "autoresearch" or "auto-research"; user wants iterative optimization; user wants a research loop; user mentions "research.md"; user wants to iterate until some condition; user wants to optimize code, prompts, configs, or...Votes: 0GitHub stars: 2
- AutoresearchCore autonomous research loop. Reads research.md, proposes hypotheses, runs experiments, evaluates results mechanically, keeps improvements, discards failures, and iterates until the target metric is achieved or the iteration budget is exhausted. TRIGGER when: user invokes "autoresearch" (no subcommand); research.md exists; user wants the 5-stage loop; user wants iterative optimization overnight.Votes: 0GitHub stars: 2
- DebugScientific bug hunting using falsifiable hypotheses. Forms hypotheses, designs falsifying tests, eliminates candidates systematically, and logs the full investigation trail in a structured debug/ folder. TRIGGER when: user has a bug to investigate scientifically; user wants systematic root-cause analysis; user says "debug", "investigate", "root cause", "why is this failing"; user invokes /autoresearch:debug. DO NOT TRIGGER when: user wants to optimize a metric (use /autoresearch); user wants ...Votes: 0GitHub stars: 2