ARS academic-paper `abstract-only` mode — bilingual abstract + keywords
ARS /ars-cache-invalidate — drop cached verification entries for a citation key
ARS academic-paper `citation-check` mode — citation error report
ARS academic-paper `disclosure` mode — venue-specific AI-usage statement
ARS academic-paper `format-convert` mode — convert to LaTeX / DOCX / PDF / Markdown
Transforms research findings into polished APA 7.0 academic reports; activated in Phase 4 and Phase 6
Designs the methodological blueprint; selects research paradigm, method, data strategy, and analytical framework
Integrates findings across sources, resolves evidence conflicts, and maps knowledge gaps
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy.
12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.
Generate SVG presentation slides for research progress reports from research log entries, then optionally export to PPTX. Use when the user wants to make slides, create a presentation, or produce a visual report from experiment logs. Triggers on "make slides", "create presentation", "report slides", "generate deck", "export to pptx". Reads docs/research_log/ entries, proposes a slide outline for user confirmation, then generates files. Suggest /research-log add first if new experiments have not been logged yet.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
I built research-lab-skills as a Claude Code skill suite covering the full academic research lifecycle — from daily experiment journals and progress presentations to systematic literature review, paper writing, and peer review simulation. It integrates two complementary toolsets:
research-log, report-slides, research-mode) — experiment journals, progress slides, session mode routingdeep-research, academic-paper, academic-paper-reviewer, academic-pipeline) — literature review, paper writing, peer review, full-pipeline orchestrationSee the detailed sections below for each skill.
Research labs spend enormous amounts of time making slides for weekly meetings. The problem isn't slide design — most presentation tools handle that fine. The problem is they have no idea what belongs in this week's slides. You end up staring at a blank deck, trying to remember what you actually did.
That's why I built the research journal mechanism first. When you log your experiments in a structured format, the AI already knows what ran this week, what failed, what the numbers look like, and what needs to be communicated. The slides are a natural output of that record — not a separate task on top of your research.
The same problem runs deeper. The daily process of research — the experiments that didn't pan out, the architectural pivots, the decisions made between runs — vanishes long before the paper gets written. By the time you're writing the methodology section, you're reconstructing from memory what you actually did and why. The formal output pipeline often starts from scratch, disconnected from the months of work that produced the insight.
This suite keeps the thread intact. Your journal records the why behind every decision; the lab-meeting slides come from those logs; the methodology section comes from those logs too. The session modes (exp → explore → publish) track which phase of research you're in and route you to the right tools automatically.
Nothing gets lost between the bench and the bibliography.
| Skill | Command | Purpose |
|---|---|---|
research-log | /research-log | Structured experiment journal (daily logs, amendments, index) |
report-slides | /report-slides | SVG + PPTX progress presentations from journal entries |
research-mode | /mode | Session mode routing (exp / daily / explore / report / publish) |
deep-research | /ars-full, /ars-lit-review, … | 13-agent research team with Socratic mode, PRISMA, fact-check |
academic-paper | /ars-plan, /ars-outline, … | 12-agent paper writing with citation verification |
academic-paper-reviewer | /ars-review, /ars-re-review | Multi-perspective peer review (EIC + 3 reviewers + DA) |
academic-pipeline | /ars-pipeline | Full 10-stage pipeline orchestrator |
These skills are not a feature list — they're a workflow. Each one was designed for a specific phase of research and hands off naturally to the next.
Phase 1 — Daily experiment work (/mode exp)
/mode exp # start an experiment session
/research-log add # log today's work (quick: 3 questions; full: 9 sections)
/report-slides # turn this week's journal into a progress presentation
/mode end # draft the next entry from today's git diff
The journal's follows: field links experiments into a traceable timeline. amended: records post-hoc corrections. slide_decks: updates automatically when slides are generated. These entries are the raw material for your methodology section when you eventually write the paper — capturing not just what worked, but why you tried it and what failed first.
Phase 2 — Literature exploration (/mode explore)
/mode explore
/ars-lit-review "your topic" # 13-agent literature review with PRISMA support
/ars-socratic # Socratic dialogue to sharpen your research question
/mode end # extract RQ + key findings into the log
Phase 3 — Writing and publication (/mode publish)
npx claudepluginhub starpig1129/research-lab-skills --plugin lab-toolsMulti-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Memory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.