By Liohtml
Rigorous research & academic-writing pipelines — universal deep-research, multi-agent paper writing, peer-review simulation, and the full research orchestrator. Self-contained across the 4 research skills; some notes cite the upstream project's design docs for context only.
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.
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.
One opinionated, deduplicated marketplace of the best Claude Code skills — distilled from five community skill repos (109 skills → 39 keepers) and regrouped into four discipline plugins: engineering · product · design · research.
This is a curation, not original work. Every skill keeps its original author and license — see NOTICE.md and PROVENANCE.csv. It was assembled by a small team of specialist reviewers (engineer, product/marketing, UX, repo expert) with a devil's-advocate pass to cut redundancy.
| Plugin | Skills | License | Focus |
|---|---|---|---|
engineering | 16 | MIT | Spec → plan → build → test → debug → review → harden → ship |
product | 13 | MIT | Discovery, strategy, prioritization, PRDs, pricing, metrics |
design | 6 | MIT | Anti-slop frontend taste, image-to-code, redesign, UI engineering |
research | 4 | CC-BY-NC-4.0 | Deep research, academic writing, peer review |
⚠️ Mixed licensing.
engineering,product, anddesignare MIT (commercial use OK).researchis CC-BY-NC-4.0 — non-commercial only, isolated in its own plugin so it can be dropped cleanly. SeeNOTICE.md.
# Add this marketplace (from GitHub)
/plugin marketplace add Liohtml/ultimate-skills
# …or from a local clone
/plugin marketplace add /path/to/ultimate-skills
# Then install the plugins you want
/plugin install engineering@ultimate-skills
/plugin install product@ultimate-skills
/plugin install design@ultimate-skills
/plugin install research@ultimate-skills # CC-BY-NC — non-commercial
Each skill activates automatically when its trigger matches your task; you can also name it explicitly (e.g. "use the strategy-red-team skill on this PRD").
| Skill | What it does |
|---|---|
spec-driven-development | Write a spec before coding when requirements are unclear or work is significant. |
planning-and-task-breakdown | Break a spec into ordered, independently verifiable tasks. |
incremental-implementation | Ship multi-file changes as small, safe vertical slices. |
test-driven-development | Drive logic and bug-fixes with tests; prove code works. |
debugging-and-error-recovery | Systematic root-cause debugging when things break. |
code-review-and-quality | Multi-axis review with severity labels before merge. |
code-simplification | Refactor for clarity without changing behavior. |
security-and-hardening | Harden input handling, auth, storage, and integrations (incl. LLM). |
performance-optimization | Measure-first optimization, budgets, Core Web Vitals. |
api-and-interface-design | Stable, contract-first API and module-boundary design. |
git-workflow-and-versioning | Commits, branching, conflicts, bisect-driven debugging. |
ci-cd-and-automation | Quality-gated build/deploy pipelines and rollout/rollback. |
doubt-driven-development | In-flight fresh-context adversarial review of key decisions. |
documentation-and-adrs | ADRs, READMEs, and changelogs that record context. |
browser-testing-with-devtools | Verify behavior in a real browser via Chrome DevTools MCP. |
karpathy-guidelines | Lightweight behavioral rules to avoid common LLM-coding mistakes. |
| Skill | What it does |
|---|---|
strategy-red-team | Steelman then attack a PRD/roadmap's load-bearing assumptions. |
opportunity-solution-tree | Torres-style discovery: outcome → opportunities → solutions → experiments. |
prioritization-frameworks | 9 frameworks (RICE, ICE, Kano, MoSCoW…) with formulas and when-to-use. |
pre-mortem | Imagine the launch failed; triage Tigers / Paper Tigers / Elephants. |
create-prd | 8-section Product Requirements Document. |
pricing-strategy | Pricing models, value metric, Van Westendorp, experiments. |
ab-test-analysis | Significance, sample size, SRM, guardrails → ship/extend/stop. |
north-star-metric | Define the NSM + input-metric constellation by business game. |
value-proposition | 6-part JTBD value-proposition design. |
competitor-analysis | Research-driven competitive landscape and differentiation. |
interview-script | Mom-Test / JTBD customer-discovery interview script. |
user-personas | Research-grounded personas with JTBD, pains, gains. |
intended-vs-implemented | Audit the gap between intended behavior and shipped code. |
Product management skills — continuous discovery, strategy red-teaming, prioritization frameworks, PRDs, pricing, A/B analysis, positioning, and metrics.
Design & frontend-taste skills — brief-aware design direction, image-to-code, redesign audits, design-reference image generation, and production UI engineering.
Production-grade engineering skills for AI coding agents — spec, plan, build incrementally, test-drive, debug to root cause, review, harden, optimize, and ship.
npx claudepluginhub liohtml/ultimate-skills --plugin researchUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.