Explore
MCP servers and skills: search, filter by where they run, and compare.
napgithub
LocalContext hygiene — compress, prune, archive .squad/ state
OfficialSkillMIT★ 5.4k in collectionNo key
ai-consultantsmatteoscurati
MCP servers and skills: search, filter by where they run, and compare.
Context hygiene — compress, prune, archive .squad/ state
OfficialSkillMIT★ 5.4k in collectionNo key
Multi-model AI deliberation system querying 12 AI consultants (Gemini, Codex, Claude, Mistral, Ollama, etc.) in parallel. Features unique personas, confidence scoring, multi-agent debate, weighted syn
SkillMIT★ 8No key
A Claude Code skill for hard decisions. Seven personality agents argue it out, vote, and hand you one verdict.
SkillMIT★ 4Few starsNo key
The multi-agent coding loop that covers every angle — one model builds, independent AI models review it from every direction, tests decide, you hold the final gate. Privacy-enforced, anti-drift, self-
SkillMIT★ 4Few starsNo key
Squadcard for AI agents: organise your weekly football game from Claude Code or Codex (MCP server, plugin and skill).
Hosted by authorMIT★ 1Few starsNo key
Summon 16 personality-type agents to debate any topic, review code, or stress-test ideas (Claude Code plugin)
SkillMIT★ 5No key
Public assembly where AI agents debate proposals, vote with sealed ranked ballots and reach binding decisions. MCP server, Agent Skills, Claude Code / Cursor / Gemini / Codex / OpenClaw manifests.
Hosted by authorApache-2.0Few starsNo key
Put a decision in front of a boardroom of seven AI advisor personas. A Claude skill: three rounds of debate, a chair who treats unanimity as a warning, and a verdict with dissent and a PDF. Works in C
SkillMITFew starsNo key
A Claude Code skill that forces grounded research + a cheapest-falsifying test before Claude commits to any consequential claim. Red-team your own belief.
SkillMIT★ 1Few starsNo key
Claude Code skill: a multi-model council that works out what you actually asked and answers without being a yes-man (or a reflexive no-man)
SkillMITFew starsNo key
Claude Code skill (/designed): Apple-grade web pages that fit one screen, plus an effects book you vote on before any animation is wired in. Design system, fluid sizing, fx.js effects library, verific
SkillMITFew starsNo key
Claude Code plugin that reflects on your sessions in the background and promotes recurring lessons into skills, hooks, rules and agents, with a human review step.
SkillMITFew starsNo key
Agent + étiquette: a small house of well-mannered agent skills for the skills.sh ecosystem.
SkillMITFew starsNo key
🏛️ Claude Council — a Claude skill where 80 legendary minds (Buffett, Munger, Musk, Jobs, Einstein, Chanakya…) debate your decision in character and a High Council hands you one verdict. Claude Code,
SkillMITFew starsNo key
MCP server where AI agents debate in a shared room until they agree on a styleguide, a rule or a decision. Your agents, your subscriptions, one agreed artifact.
SkillMITFew starsNo key
Tiered, surface-scaled multi-reviewer code review for git diffs via the OpenAI Codex CLI (multi-agent fan-out, JSON findings)
SkillMITFew starsNo key
A Claude agent skill that scores your hackathon or competition entry the way a judge actually scores it.
SkillMITFew starsNo key
Evidence-based expert council for Claude Code: parallel cited web research first, then a large panel of independent personas, adversarial objectors, and a clear synthesis.
SkillMITFew starsNo key
Claude Code skill that makes any model (Sonnet 5 / Opus 4.8) operate with Fable-class discipline - task-adaptive practice routing, verify loops, agent orchestration, adversarial self-checks, outcome-f
SkillMITFew starsNo key
Agent Skills for the full B2B sales cycle: prospecting, company research, decision-makers, cold outreach, qualification. Battle-tested, with worked examples. Russian-language skill bodies, English doc
SkillCC-BY-4.0Few starsNo key
Multi-persona design review skill for Claude Code. 4 UX/UI designer personas review in parallel, then vote on each other's findings to surface the highest-impact changes. gstack-flavored but standalon
SkillMITFew starsNo key
11 evidence-backed process-discipline skills for Claude Code — Fable 5 working disciplines transplanted onto Opus, blind A/B validated
SkillMITFew starsNo key
Who stands behind it
