wjgoarxiv
- 102 skills
- 0 followers
- 167 repo stars
- 5 days ago last updated
- ▌ Lit Scientific Visualization · wjgoarxiv bundleMake a publication-ready figure from measured data: chart form, units, colorblind-safe color, export and visual check.
- ▌ Lit Typographic Motion · wjgoarxiv bundleFilm director for a finished short film from a one-line request, made the same way every time with house styles, a scaffold, a storyboard board round, an original layered score and a QA gate.
- ▌ Lit Brainstorm · wjgoarxiv bundleSpread out on ideas before choosing: technique rounds, clusters, a scored shortlist and a hand-off packet. Use when the solution space is open.
- ▌ Lit Comprehend · wjgoarxiv bundleBuilds one self-contained HTML explainer of agent-written work: intuition, literate walkthrough, a micro-world to poke, and a quiz. Use when someone must understand a change.
- ▌ Comment Checker · wjgoarxiv bundleAudit code comments in a diff or named files: keep intent and reasons, remove stale narration, fix misleading text.
- ▌ Lit Burnoff File · wjgoarxiv bundleStrip generated residue from exactly one file with behavior unchanged. Use for a single named file; a scope of many files goes to lit-burnoff.
- ▌ Structural Search · wjgoarxiv bundleFind or rewrite code by syntax shape with ast-grep: verify the engine, preview a codemod, apply it in bounds, label any text fallback.
- ▌ Lit Diagram Drawer · wjgoarxiv bundleDraw an architecture, workflow, data-model or timeline diagram as editable SVG, check it, and export PNG. Use when a picture explains faster than prose.
- ▌ Frontend UI UX · wjgoarxiv bundleBuild or restyle a UI: clear hierarchy, accessible contrast, responsive layout, browser-checked.
- ▌ Lit Schematic · wjgoarxiv bundleDraw a P&ID, PFD, equipment layout, journal apparatus figure or isometric cutaway as editable SVG with QA gate and 600 dpi PNG export. For real hardware and piping, not abstract diagrams.
- ▌ Readme Studio · wjgoarxiv bundleWrite or refresh a README from repository facts: purpose, install, quick start and commands that were run. Optional inspected cover.
- ▌ Autoconference 2 · wjgoarxiv bundleRun one budgeted research conference: parallel researcher children, adversarial review, synthesis; plus plan, resume, analyze, debate, survey and ship modes.
- ▌ Deep Interview · wjgoarxiv bundleAsk one focused question per round about a vague request, score the ambiguity, and write a spec that lit-plan can use. Use before planning broad work.
- ▌ Lit Commit · wjgoarxiv bundleGit work: atomic commits in the repo's own message style, staging, rebase and fixup, blame, bisect, log search.
- ▌ Lit Hijack · wjgoarxiv bundlePort someone else's published technique into your own skill or system, clean-room: capture with provenance, licence gate, source-free spec, isolated build, parity proof, provenance report.
- ▌ Start Work · wjgoarxiv bundleExecute an approved plans/<slug>.md row by row: failing proof first, evidence per row, tick the row, final review gate. Use after lit-plan.
- ▌ Lit Burnoff · wjgoarxiv bundleStrip generated bloat from a bounded scope of files after locking their behavior with tests. Use to deslop a diff, folder or file list; one file goes to lit-burnoff-file.
- ▌ Lit Handoff · wjgoarxiv bundleWrite a verified continuation packet to .litgravity/handoff/latest.md: state, what was done and checked, what is left, and exact resume commands.
- ▌ Litresearch · wjgoarxiv bundleResearches a question across sources down to primary evidence (prior art, landscapes, disputed claims) and returns a referenced synthesis. A one-fact lookup needs no skill.
- ▌ Review Work · wjgoarxiv bundleReview a plan before work or a diff after it in five lanes, findings first with file:line anchors. Use when asked if a plan, change or branch is right or safe.
- ▌ Autoresearch 2 · wjgoarxiv bundleRuns a bounded experiment loop under an approved budget: one change per iteration, scored by a declared metric or evaluator, kept or reverted, logged; ten modes.
- ▌ Lit Crucible · wjgoarxiv bundlePressure-test a brief before planning: independent risk lanes, ranked failure modes and the constraints that survive. Use for risky or hard-to-undo work.
- ▌ Browser Drive · wjgoarxiv bundleDrive a real browser to navigate, fill, click and extract from live pages, or name the blocker.
- ▌ Lit Humanizer · wjgoarxiv bundleRewrites Korean or English prose so it reads in the writer's own voice for its reader, keeping meaning, facts, numbers and uncertainty. Use to polish or de-template text.
- ▌ Lit Team · wjgoarxiv bundleCoordinate two or more child agents behind a durable team packet: owned slices, evidence reports, archive receipt. Use for team mode, not a single delegation.
- ▌ Refactor · wjgoarxiv bundleRestructure code with behavior unchanged: pin it with tests, move in small verified steps, keep public contracts.
- ▌ Debugging · wjgoarxiv bundleFix a bug: reproduce it, test several hypotheses, isolate the cause, lock it with a failing test, then verify on the real surface.
- ▌ Lit Recap · wjgoarxiv bundleRead-only recap of where the work stands: goals, plan rows, ledger, evidence, blockers and the next safe step, from .litgravity/ and plans/.
- ▌ Lsp Setup · wjgoarxiv bundleFallback setup for language servers and checker CLIs on agy: detect what a project needs, print per-OS install commands, verify a real diagnostics roundtrip.
- ▌ Visual QA · wjgoarxiv bundleCheck a built UI in a real browser at several widths: states, screenshots, visible breakage.
- ▌ Lit DOCX · wjgoarxiv bundleMake a Word .docx report, proposal, manual, memo or manuscript from a request or sources in a chosen design direction, or convert DOCX/PDF to Markdown, gated and render-checked. Needs Python 3.10+.
- ▌ Lit Init · wjgoarxiv bundleMap an unfamiliar repository once and leave sparse AGENTS.md files: layout, commands, gates and traps. Use when onboarding a codebase or refreshing its agent guidance.
- ▌ Lit Loop · wjgoarxiv bundleBare lit default: take a task from request to verified PASS or named BLOCKED, with criteria, tests first, real-surface proof and a ledger.
- ▌ Lit Plan · wjgoarxiv bundlePlan before code: write a decision-complete plans/<slug>.md with tasks, files, tests and checks. Use for planning, scoping and plan-then-build requests.
- ▌ Lit PPTX · wjgoarxiv bundleMake a .pptx slide deck from a request or sources in a chosen design direction, gate it mechanically, then look at every rendered page. Needs Python 3.10+.
- ▌ Lsp · wjgoarxiv bundleFallback diagnostics and code navigation for agy: drive checker CLIs (tsc, pyright, ruff, gopls, cargo) through run_command before and after edits.
- ▌ Rules · wjgoarxiv bundleExplain which rules, AGENTS.md files and skills agy loads, in what order, and how to settle conflicts. Use when guidance seems ignored or two sources disagree.
- ▌ Wikify · wjgoarxiv bundleKeeps a reviewed, source-cited task wiki under .litgravity/wiki: init, ingest, query, save, lint, and capture or review knowledge claims.
- ▌ Litgoal · wjgoarxiv bundleSet, check or close a durable goal in .litgravity/goals with criteria, status and evidence. Use when work must outlive this conversation.
- ▌ Litwork · wjgoarxiv bundleShip one contained change with proof: size it, failing test first, make it pass, check the real surface, clean up. Use to implement, fix or land work.
- ▌ Lit Adhd · wjgoarxiv bundleCross-session KPI board for recent agy sessions: the one thing to do now and what to type, done and remaining milestones, reminders. Alias: lit-rewind.
- ▌ Lit Code · wjgoarxiv bundleShapes every code edit: build-decision gate, language references first, tests before code, input parsed once, typed seams, files under 250 pure LOC, clean lint and types.
- ▌ PDF 2 · wjgoarxivComprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When the LLM (Claude, ChatGPT, Gemini, or others) needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
- ▌ Autoresearch Ship · wjgoarxiv bundleUniversal shipping workflow: 8-phase linear pipeline from verification to deploy. Reads type-checklists.md to select the right checklist for the artifact type. The ONLY pause is Phase 7 (user confirmation before irreversible deploy/publish). TRIGGER when: user wants to ship, release, publish, or deploy something; user asks "is this ready to ship?"; user wants a pre-release checklist; user wants to publish a package, CLI, API, web app, ML model, skill, docs site, infrastructure, or research paper; user invokes /autoresearch:ship. DO NOT TRIGGER when: user wants iterative development (use autoresearch); user wants to debug errors (use autoresearch:fix); user just wants a code review.
- ▌ Handoff · wjgoarxiv bundleCreates or updates a resolved HANDOFF.md continuation document that captures progress, findings, and remaining work so a fresh agent can continue without context loss. TRIGGER when: the current agent cannot complete a task and needs to pass it to a new agent, context window is nearly full, user explicitly requests a handoff, or the skill is invoked as bare `handoff`. DO NOT TRIGGER when: the task is normal ongoing work with no agent transition needed.
- ▌ Comsol Mph Analyzer · wjgoarxiv bundleCOMSOL Multiphysics toolkit for .mph model analysis, input preparation, mesh/geometry editing, and MCP connectivity. Use when (1) user provides a .mph file and wants to understand its contents, (2) preparing simulation inputs or parameter sweeps, (3) modifying .mph parameters without COMSOL, (4) generating Java API code from .mph models, (5) editing mphtxt mesh or STL geometry files (translate, rotate, scale, mirror), (6) converting STL to COMSOL mphtxt format, (7) checking COMSOL installation and MCP readiness, (8) setting up COMSOL MCP server for Claude control. Triggers on: .mph files, COMSOL model, analyze mph, parameter sweep, comsolbatch, mesh editing, STL editing, mphtxt, COMSOL MCP, simulation inputs.
- ▌ LLM Wikify · wjgoarxiv bundleConvert the current working directory into a task-local LLM-maintained wiki. Use when the user wants to organize project knowledge, ingest files or URLs into a local markdown wiki, bootstrap a wiki structure in-place, maintain an existing mini wiki, or build a repo-scoped knowledge base instead of a giant global vault. Also use when scientific papers, PDFs, TeX bundles, bibliographies, or research corpora should be ingested into a maintained local wiki with provenance and citations, subject to extraction quality and available metadata. Trigger on phrases like "wiki this repo", "ingest raw/", "build a local wiki", "maintain this knowledge base", "turn this directory into an LLM wiki", or when repeated project knowledge needs to compound across sessions. DO NOT TRIGGER when: the user only wants a one-shot summary, a global PKM redesign, or generic markdown cleanup with no persistent wiki intent.
- ▌ Frontend Design · wjgoarxiv bundleAward-winning frontend design skill producing hand-crafted, human-quality interfaces. Generates landing pages, dashboards, web apps, components, and posters with distinctive typography, bold color systems, intentional motion, and spatial compositions that look designed by an expensive agency — NOT generic AI output. Use this skill whenever the user wants a landing page, dashboard, web app, component, poster, or any frontend UI. Also use when user asks for "beautiful", "premium", "award-winning", "stunning", or "polished" frontend; wants HTML/CSS/React/Vue/Svelte UI; mentions "design" with frontend context; wants to build a website; says "make it look good" or "make it pretty"; asks for UI that doesn't look like AI generated it; mentions "anti-slop" or "no AI aesthetic"; wants to "beautify", "style", or "redesign" an existing UI; asks for a "modern", "professional", or "polished" website — even if they don't explicitly mention design quality. Make sure to use this skill for ANY frontend creation task. DO NOT T
- ▌ Ovito MCP · wjgoarxivDrive the ovito-mcp MCP server to analyze MD trajectories and clathrate-hydrate structures headlessly via OVITO in-process. TRIGGER when: the user mentions OVITO, GROMACS (.gro/.xtc/.trr), LAMMPS (dump/data), trajectory analysis, RDF, coordination, CNA/PTM/structure identification, clathrate hydrates, cage identification (sI/sII/sH), F3/F4 order parameters, hydrogen-bond networks, cage occupancy, or headless molecular rendering. DO NOT TRIGGER when: the user is working with PyMOL, VMD, or a pure-Python script with no OVITO dependency; the ovito-mcp server is not registered in the MCP config; or the request is a general MD question requiring no tool calls.
- ▌ XLSX · wjgoarxiv bundleCreates, edits, and analyzes spreadsheet files (.xlsx, .xlsm, .csv) with formulas, formatting, data analysis, and visualization. TRIGGER when: user needs to create or modify a spreadsheet, run formula-based calculations, analyze tabular data, or build financial models in Excel/CSV format. DO NOT TRIGGER when: user is working with PDF documents — use the pdf skill instead.
- ▌ Publisher DOCX Skill · wjgoarxiv bundleConverts bidirectionally between DOCX/PDF and Markdown, edits existing DOCX files programmatically, or prepares a journal-ready manuscript. TRIGGER when: user needs DOCX↔Markdown conversion, wants to create a styled Word document from Markdown, needs to batch-edit/modify an existing DOCX file, or wants to produce a publisher-styled manuscript (e.g. Elsevier, ACS, IEEE, Nature, or a Korean generic profile). DO NOT TRIGGER when: user only needs to convert non-DOCX formats (images, HTML, etc.) to Markdown — use markitdown instead.
- ▌ Youtube Digest · wjgoarxiv bundleExtracts transcripts from YouTube videos and produces structured digests with TL;DR, key takeaways, core assertions with timestamps, topic timeline, and notable quotes. Builds on markitdown's raw transcript extraction by adding LLM-driven analysis and structured output. TRIGGER when: user pastes a YouTube URL and wants a summary, digest, or analysis of the video content; user asks "what is this video about"; user wants key points or takeaways from a YouTube video; user wants to decide whether a video is worth watching; user asks to summarize a YouTube talk, lecture, podcast, or interview; user wants structured notes from a video; user asks to digest or break down a YouTube video; user mentions a YouTube link and asks for insights. DO NOT TRIGGER when: user just wants the raw transcript text without analysis (use markitdown); user wants to download the video file; user wants to convert a local video or audio file to text.
- ▌ Autoconference Skill · wjgoarxiv bundleMulti-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.md"; user wants research synthesis from multiple approaches; user wants adversarial evaluation of research results. DO NOT TRIGGER when: user wants a single autoresearch loop (use autoresearch-skill); user wants a simple one-shot answer; user wants to read a single paper.
- ▌ Autoconference Plan · wjgoarxiv8-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).
- ▌ Autoconference Ship · wjgoarxiv8-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).
- ▌ Autoconference Debate · wjgoarxivAdversarial 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).
- ▌ Autoconference Resume · wjgoarxivResume 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).
- ▌ Autoconference Survey · wjgoarxivSystematic 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).
- ▌ Autoconference Analyze · wjgoarxivPost-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).
- ▌ Autoconference · wjgoarxiv bundleCore 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.
- ▌ Swarm · wjgoarxiv bundleUse native Copilot CLI scheduling for two or more independent subtasks, with self-contained delegation packets, host-enforced read-only policy, isolated git worktrees for writers, skeptical integration, and explicit failure and cleanup handling.
- ▌ Csw Git · wjgoarxiv bundlePerform conservative Git status, commit, history, rebase, and recovery work with explicit mode selection, atomic scope, conflict evidence, and non-destructive recovery paths.
- ▌ Csw Lsp · wjgoarxiv bundleConfigure, diagnose, and prove language-server support through Copilot CLI native LSP surfaces, including root discovery, semantic operations, and graceful failure cases.
- ▌ Csw Init · wjgoarxiv bundleBuild a concise hierarchical AGENTS.md knowledge base from measured repository structure, verified commands, ownership boundaries, complexity scoring, and deduplicated local guidance.
- ▌ Csw Loop · wjgoarxiv bundleActivate when the user types `csw`, prefixes a task with `csw`, or asks to run the full loop; bind observable criteria and drive them through planning, test-first work, real-surface QA, review, cleanup, and machine-receipt completion.
- ▌ Csw Plan · wjgoarxiv bundleUse before non-trivial implementation to explore the real repository, resolve material ambiguity, create one decision-complete plan with observable criteria and rollback, review it adversarially, and stop at explicit user approval.
- ▌ Csw Work · wjgoarxiv bundleExecute an explicitly approved plan to evidence-gated completion through durable checkpoints, test-first changes, real-surface QA, review, failure recovery, rollback, cleanup receipts, and current machine evidence.
- ▌ Csw Deslop · wjgoarxiv bundleRemove mechanical and AI-generated code smells from a bound diff while locking behavior, preserving intentional safeguards, and applying an evidence-based review rubric.
- ▌ Csw Review · wjgoarxiv bundleRun a binding, all-or-nothing review for broad, risky, shared, security-sensitive, or release-facing work across compliance, code quality, real manual QA, evidence integrity, security, and scope fidelity.
- ▌ Csw Frontend · wjgoarxiv bundleDesign and implement polished, accessible interfaces through design-system audit, task-centered hierarchy, complete interaction states, responsive behavior, and fresh visual evidence.
- ▌ Csw Refactor · wjgoarxiv bundleRestructure code without unintended behavior change through an explicit intent gate, dependency codemap, characterization tests, reversible checkpoints, and real-surface comparison.
- ▌ Csw Debugging · wjgoarxiv bundleDiagnose runtime failures with reproducible observations, competing hypotheses, runtime-aware probes, causal root-cause proof, regression tests, and real-surface verification.
- ▌ Csw Interview · wjgoarxiv bundleTurn ambiguous product or technical intent into a decision-complete brief through evidence-first intake, weighted ambiguity tracking, one-question rounds, challenge modes, and explicit handoff boundaries.
- ▌ Csw Visual QA · wjgoarxiv bundleVerify web and terminal interfaces with fresh scenario captures, interaction and accessibility checks, reference-aware review, and explicit evidence-backed verdicts.
- ▌ Csw Programming · wjgoarxiv bundleImplement production code with repository-native tooling, test-first behavior, typed boundaries, compact architecture, language-specific guidance, and real-surface verification.
- ▌ Antigravity Swarm · wjgoarxiv bundleInstalls and uses Antigravity CLI ASW skills, hooks, diagnostics, and swarm workflow guidance.
- ▌ Asw · wjgoarxivAntigravity Swarm execution loop for evidence-driven implementation with tests, subagents, hooks, and manual QA.
- ▌
- ▌ Asw Goal · wjgoarxivDurable Antigravity Swarm goal orchestration with explicit success criteria, evidence ledger, manual QA channels, and completion audit.
- ▌ Asw Loop · wjgoarxivAntigravity Swarm Loop executes RED to GREEN to real-surface QA with cleanup receipts.
- ▌ Asw Plan · wjgoarxivAntigravity Swarm Plan creates a decision-complete plan before large or ambiguous work.
- ▌ Asw Debug · wjgoarxivHypothesis-driven Antigravity Swarm debugging for crashes, hangs, wrong output, and runtime drift.
- ▌
- ▌ Asw UI UX · wjgoarxivProduct-aware frontend and README presentation guidance for Antigravity Swarm work.
- ▌ Asw Review · wjgoarxivAntigravity Swarm review skill for diff, evidence, hook, package, docs, installer, and real-surface QA inspection.
- ▌ Asw Cleanup · wjgoarxivRemove AI-looking clutter and temporary artifacts without changing behavior.
- ▌ Asw Refactor · wjgoarxivBehavior-preserving Antigravity Swarm refactoring with characterization, impact mapping, diagnostics, and real-surface verification.
- ▌ Asw Start Work · wjgoarxivExecute an ASW plan after asw-plan, with subagents, verification, real-surface QA, continuation state, and cleanup receipts.
- ▌ Asw Programming · wjgoarxivStrict Antigravity implementation discipline for Python, TypeScript, JavaScript, Go, and Rust work.
- ▌
- ▌ Asw Remove AI Slops · wjgoarxivRemove AI-looking code smells from branch changes or explicit files. Lock behavior with regression tests first, run categorized cleanup in bounded Antigravity lanes, then verify with quality gates.
- ▌ Autoresearch Learn · wjgoarxivFeedback-driven self-improvement protocol for autoresearch-skill. Converts failed runs, confusing transcripts, bad outputs, or user feedback into a bounded improvement plan, an eval scenario, and a patch checklist without executing the patch automatically. TRIGGER when: user says the skill failed, wants to improve autoresearch-skill, provides feedback on confusing behavior, asks to turn a failure into an eval, or invokes /autoresearch:learn. DO NOT TRIGGER when: the user wants to run an optimization loop (use /autoresearch), fix code errors (use /autoresearch:fix), or ship a finished artifact (use /autoresearch:ship).
- ▌ Autoresearch Reason · wjgoarxivAdversarial multi-round reasoning with blind-judge panel to reach rigorous conclusions. TRIGGER when: user wants rigorous reasoning or argument evaluation; user wants a decision analyzed from multiple angles; user wants devil's advocate critique; user asks "what are the strongest arguments for/against"; user wants a structured debate; user wants to avoid groupthink or anchoring; user invokes /autoresearch:reason. DO NOT TRIGGER when: user wants a simple recommendation; user wants a quick summary; user wants factual lookup; user just wants pros/cons without adversarial pressure.
- ▌ Autoresearch Predict · wjgoarxiv bundleMulti-perspective deliberation engine. Gathers independent positions from diverse personas, runs cross-examination and rebuttal rounds, detects herd behavior, and synthesizes a neutral judge verdict with confidence levels. TRIGGER when: user wants multi-perspective prediction, forecasting, scenario analysis, decision analysis, "what will happen if", "should we", "predict the outcome of", structured devil's advocacy, or any question benefiting from adversarial deliberation.
- ▌ Autoresearch Scenario · wjgoarxiv bundle12-dimension scenario exploration across user-specified domain modes. TRIGGER when: user wants to explore scenarios, edge cases, or what-if analysis; user asks "what could go wrong"; user wants failure mode analysis; user asks about best/worst case outcomes; user wants to stress-test a plan, design, or system; user mentions "scenario analysis" or "scenario planning"; user invokes /autoresearch:scenario. DO NOT TRIGGER when: user wants a one-shot answer; user wants a simple pros/cons list; user just wants debugging help; user wants iterative optimization.
- ▌ Autoresearch Security · wjgoarxiv bundleIterative security audit engine. Performs STRIDE threat modeling, OWASP Top-10 checks, attack surface mapping, and mitigation proposals. Loops until coverage target is reached or budget is exhausted. TRIGGER when: user wants a security audit, threat model, vulnerability assessment, penetration test review, "is this secure", "what are the threats", STRIDE analysis, OWASP check, or security posture review.
- ▌ Autoresearch · wjgoarxiv bundleCore 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.
- ▌ PDF · wjgoarxivComprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When the LLM (Claude, ChatGPT, Gemini, or others) needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
- ▌ Autoresearch Skill · wjgoarxiv bundleAutonomous 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 parameters iteratively; user invokes any /autoresearch:* subcommand. DO NOT TRIGGER when: user wants a one-shot answer; user wants manual step-by-step guidance; user just wants to read a single paper; user wants a simple web search.
- ▌ Autoresearch Fix · wjgoarxivIterative error-crusher loop that auto-stops at 0 errors. Cascade-aware: fixes dependency errors before their dependents. Refuses anti-patterns that hide errors instead of fixing them. TRIGGER when: user has errors or failures to fix iteratively; user asks to "fix all errors"; user has a failing test suite; user has compilation errors; user has linter errors; user wants systematic error elimination; user invokes /autoresearch:fix. DO NOT TRIGGER when: user wants a one-shot fix for a single obvious bug; user wants debugging guidance only; user wants code review without fixing.