convez.ai
Skill
Liohtml

ultimate-skills

Liohtml/ultimate-skills

Ver no GitHub
InicialPluginScore · de 0 a 100

A curated, deduplicated marketplace of the best Claude Code skills — engineering, product, design, research (39 skills from 5 community repos).

Instalação

$npx convez-ai Liohtml/ultimate-skills

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 1 mês
Versão
—
Issues abertas
15
Contribuidores
1

README

A tradução para o português deste README ainda está na fila.

Ultimate Skills

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.

What's inside

PluginSkillsLicenseFocus
engineering16MITSpec → plan → build → test → debug → review → harden → ship
product13MITDiscovery, strategy, prioritization, PRDs, pricing, metrics
design6MITAnti-slop frontend taste, image-to-code, redesign, UI engineering
research4CC-BY-NC-4.0Deep research, academic writing, peer review

⚠️ Mixed licensing. engineering, product, and design are MIT (commercial use OK). research is CC-BY-NC-4.0 — non-commercial only, isolated in its own plugin so it can be dropped cleanly. See NOTICE.md.

Install

# 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 catalog

engineering (MIT)

SkillWhat it does
spec-driven-developmentWrite a spec before coding when requirements are unclear or work is significant.
planning-and-task-breakdownBreak a spec into ordered, independently verifiable tasks.
incremental-implementationShip multi-file changes as small, safe vertical slices.
test-driven-developmentDrive logic and bug-fixes with tests; prove code works.
debugging-and-error-recoverySystematic root-cause debugging when things break.
code-review-and-qualityMulti-axis review with severity labels before merge.
code-simplificationRefactor for clarity without changing behavior.
security-and-hardeningHarden input handling, auth, storage, and integrations (incl. LLM).
performance-optimizationMeasure-first optimization, budgets, Core Web Vitals.
api-and-interface-designStable, contract-first API and module-boundary design.
git-workflow-and-versioningCommits, branching, conflicts, bisect-driven debugging.
ci-cd-and-automationQuality-gated build/deploy pipelines and rollout/rollback.
doubt-driven-developmentIn-flight fresh-context adversarial review of key decisions.
documentation-and-adrsADRs, READMEs, and changelogs that record context.
browser-testing-with-devtoolsVerify behavior in a real browser via Chrome DevTools MCP.
karpathy-guidelinesLightweight behavioral rules to avoid common LLM-coding mistakes.

product (MIT)

SkillWhat it does
strategy-red-teamSteelman then attack a PRD/roadmap's load-bearing assumptions.
opportunity-solution-treeTorres-style discovery: outcome → opportunities → solutions → experiments.
prioritization-frameworks9 frameworks (RICE, ICE, Kano, MoSCoW…) with formulas and when-to-use.
pre-mortemImagine the launch failed; triage Tigers / Paper Tigers / Elephants.
create-prd8-section Product Requirements Document.
pricing-strategyPricing models, value metric, Van Westendorp, experiments.
ab-test-analysisSignificance, sample size, SRM, guardrails → ship/extend/stop.
north-star-metricDefine the NSM + input-metric constellation by business game.
value-proposition6-part JTBD value-proposition design.
competitor-analysisResearch-driven competitive landscape and differentiation.
interview-scriptMom-Test / JTBD customer-discovery interview script.
user-personasResearch-grounded personas with JTBD, pains, gains.
intended-vs-implementedAudit the gap between intended behavior and shipped code.

design (MIT)

SkillWhat it does
design-taste-frontendBrief-aware, anti-slop design direction for greenfield UIs.
redesign-existing-projectsAudit an existing UI, strip generic AI patterns, upgrade to premium.
image-to-codeGenerate a design image first, analyze it, then implement to match.
imagegen-frontend-webProduce premium, conversion-aware website design-reference images.
industrial-brutalist-uiA distinct Swiss-terminal / brutalist aesthetic system.
frontend-ui-engineeringProduction UI: components, state, layout, WCAG-AA accessibility.

research (CC-BY-NC-4.0 — non-commercial)

SkillWhat it does
deep-researchUniversal multi-agent deep-research pipeline (7 modes).
academic-paper12-agent academic paper-writing pipeline (10 modes).
academic-paper-reviewer5-reviewer peer-review simulation.
academic-pipelineOrchestrator: research → write → integrity → review → revise.

Attribution & licensing

Curated from: agent-skills (Addy Osmani), pm-skills (Paweł Huryn), taste-skill (Leonxlnx), andrej-karpathy-skills (forrestchang / multica-ai), and academic-research-skills (Cheng-I Wu).

Full per-skill provenance: PROVENANCE.csv · Licenses: LICENSES/ · Details: NOTICE.md.

The curation, manifests, and docs are MIT. The research/ plugin is CC-BY-NC-4.0 and may not be used commercially.

Ver o original no GitHub

Bom para

Relacionados