Skip to content
Solid State

Solid
State

A skill is packaged judgment.
The marketplace: sourced, licensed, no fake installs.

324
skills
10
originals
314
listings
10
agents
Solid State Original · System
Ship Kit. A system, not a pile of skills.
Six skills, one orchestrator, one shared memory. $99 once.
Get the kit →

Featured

Skill Provenance
by Solid State
Vet a third-party agent skill before you install or run it. Checks provenance, license, pinning, hidden or injected instructions, dependency/supply-chain risks, and dangerous capabilities — then returns RUN / REVIEW / DO NOT RUN.
Free
SpaceX Daily Briefing
by Solid State
A daily investor-grade briefing on SpaceX (now public as SPCX, merged with xAI). Live X + web search across the stock, Starlink, and the xAI/Grok AI segment — with Nasdaq/Yahoo analyst targets, SEC filings, and Kalshi prediction-market odds — distilled into a tight, price-moving, sourced brief.
Free
Niche Hunter
by Solid State
Surface profitable affiliate sub-niches scored by commission rate, SERP gap, trend slope, and content difficulty.
Free
AI Tool Compare
by Solid State
Fair, structured 1v1 comparison between two AI tools. Pricing, features, real-world performance, switching cost, who-it's-for.
Free
Hyper-Rational Brief
by Solid State
Solid State's signature voice applied to research briefs. Anti-buzzword filter, evidence-graded claims, no corporate residue.
Free
Skill Auditor
by Solid State
Pre-publish audit for ClawHub skills. Nine checks, one verdict: READY or FIX FIRST. Pass the security scan on the first upload.
Free
Paper Scout
by Solid State
Find and verify real research papers through a keyless index — no login or API key from a normal IP. Search by topic or method, map a field's citation graph, pull the in-body passages that prove a claim, or scan GitHub for engineering prior art. Grounds every answer in papers the index actually returns — never invents titles or arXiv IDs.
Free
Ship Kit
by Solid State
A system, not a pile of skills. Six skills + orchestrator + shared project memory: validate, position, audit (write-mode), launch. $99 once.
$99
fable-ready
by Solid State
Write-mode readiness audit for Claude Fable 5. Scans CLAUDE.md + skills + configs for the five documented breakage families, patches what you approve, stamps a dated FABLE-READY verdict. $49 once.
$49
AI SEO Kit
by Solid State
Answer and generative engine optimization (AEO / GEO). Nine skills make a site legible to AI engines: audit, patch, verify — dated verdicts, every output re-checkable, zero API keys. $149 once.
$149

Agents — ranked by catalog coverage

All agents →
OpenClaw (open source) · OSS
OpenClaw
Open-source, cross-platform personal AI assistant. macOS, Linux, Windows. Extensible through skills and tools, with ClawHub as its public skill registry.
323 skills
NVIDIA
NemoClaw
NVIDIA's sandboxed agent runtime. Runs agents in isolated environments with controlled tool access. Solid State's own agent runs on it.
323 skills
Nous Research · OSS
Hermes Agent
The self-improving agent from Nous Research. Built-in learning loop: it creates skills from experience, improves them during use, and remembers across sessions. Runs local, Docker, SSH, or serverless (Daytona, Modal), and talks through 20+ messaging platforms.
320 skills
Anthropic
Claude Code
Anthropic's agentic coding tool. Runs in the terminal with full project context, executes commands, edits across files. Skills are a first-class primitive: folders with a SKILL.md that Claude loads when the task matches.
319 skills
1.OpenClawOpenClaw (open source) · Terminal · Desktop · OSS323 skills2.NemoClawNVIDIA · Terminal · Cloud323 skills3.Hermes AgentNous Research · Terminal · Desktop · Cloud · OSS320 skills4.Claude CodeAnthropic · Terminal · IDE319 skills5.GrokxAI · Desktop · Terminal319 skills6.AntigravityGoogle · IDE · Cloud319 skills7.CodexOpenAI · Terminal · IDE · OSS319 skills8.CursorCursor (Anysphere) · IDE319 skills9.OpenCodeOpen source · Terminal · IDE · Desktop · OSS319 skills10.ClineCline (open source) · Extension · OSS319 skills
10 runtimes · 5 open source · counts = catalog skills that run on each runtime. No usage numbers we haven't measured.

Top skills by category — skills.sh installs

Top EngineeringView all →
1.Find Skillsvercel-labs/skills1.7M installs2.Vercel React Best Practicesvercel-labs/agent-skills435K installs3.Web Design Guidelinesvercel-labs/agent-skills351K installs4.Azure Deploymicrosoft/azure-skills328K installs5.Agent Browservercel-labs/agent-browser322K installs
Top MarketingView all →
1.Microsoft Foundrymicrosoft/azure-skills330K installs2.Azure AImicrosoft/azure-skills328K installs3.Azure Deploymicrosoft/azure-skills328K installs4.Azure Preparemicrosoft/azure-skills328K installs5.Azure Diagnosticsmicrosoft/azure-skills328K installs
Top ProductivityView all →
1.Lark Doclarksuite/cli179K installs2.Lark Baselarksuite/cli179K installs3.Lark IMlarksuite/cli178K installs4.Lark Drivelarksuite/cli178K installs5.Lark Sharedlarksuite/cli178K installs
Top Design & UIView all →
1.Frontend Designanthropics/skills474K installs2.Web Design Guidelinesvercel-labs/agent-skills351K installs3.UI UX Pro Maxnextlevelbuilder/ui-ux-pro-max-skill189K installs4.Sleek Design Mobile Appssleekdotdesign/agent-skills182K installs5.Lark Doclarksuite/cli179K installs
Install counts are real — skills.sh public telemetry. Skills without telemetry don't rank.

More