caveman
claudecodexUltra-compressed communication mode. Shortens prose while preserving technical terms, code, commands, and exact errors.
22 skills · 1 command · 3 agents · hooks
Claude Code and Codex plugins their authors filed under "productivity". All categories.
Ultra-compressed communication mode. Shortens prose while preserving technical terms, code, commands, and exact errors.
22 skills · 1 command · 3 agents · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Precision-tuned context engineering for Claude Code. Natural language to slash command mapping, modular development plans, and parallel workflow execution.
8 skills · 14 commands · 5 agents
Sort any inbox into ten stable categories, surface only what a human must answer, draft context-checked replies, brief the owner each morning, sweep backlogs, and export client-side filter rules. Never sends or deletes.
19 skills · 8 commands
Applies the orchestrator's model choice to each Claude Code subagent via PreToolUse, within your declared policy. Requires the downshift binary (install.sh or Releases).
10 skills · 1 command · 15 agents · hooks
Terse replies and compressed context.
22 skills · 1 command · 3 agents · hooks
Talk like caveman. Cut filler, keep technical details. Saves output tokens.
22 skills · 1 command · 3 agents · hooks
Mirrors JuliusBrussee/caveman so claude-factory can declare it as a same-marketplace dependency. Terse agent prose (fewer output tokens); code, commits, PRs and docs stay normal.
22 skills · 1 command · 3 agents · hooks
All 20 Lark/Feishu domain skills (Base, Calendar, Docs, Drive, Mail, Sheets, Task, Wiki, IM, Contacts, Event, Approval, Minutes, VC, Whiteboard, OpenAPI Explorer, Workflow, Skill Maker, Shared, Mail).
25 skills · 1 MCP server
/workflow で 5 問オンボーディング → Notion スキーマ設計・MCP 4 ツール連携・PII 検知・自動ルール化までを束ねる BELTA 業務エージェント。
15 skills · 10 commands · hooks
Agents Dev Kit — implement, review, pr-review, investigate, document, slack-post, pagesmith, scaffold-pagesmith-docs, diagramkit. Self-contained skills, custom agents, env-gated MCP servers. GitHub via gh CLI, git via git, SSH-only clones.
9 skills · 7 agents · 10 MCP servers
Evidence-driven scorecard engine for ideas, MVPs, and evolving projects. Scores across 5 dimensions (wedge, friction, loop, timing, trust) using scientific frameworks (JTBD, TAM, ISO, Rogers, Mayer) with confidence-weighted scoring and PROCEED/ITERATE/KILL gates.
6 skills · 7 commands · 10 agents · 2 MCP servers · hooks
Desk cards, quotes, customers, and portfolio publish on agenthouse.
14 skills · 11 commands · 1 MCP server
Agent skills by lorenzh: research, publishing, agent dispatch and review, git, GitHub, terminal, shipping, audio and video workflows.
26 skills
Skills for engineering leadership: take over a team and audit what you inherited, record decisions, write status updates, run postmortems and incident comms, read delivery health, review on-call load, design the team cadence, a reorganisation and goals, make the case for headcount or for paying down tech debt, map team skills and single points of knowledge, plan onboarding, hire, benchmark pay, evaluate vendors, handle retention, growth reviews, improvement plans and difficult conversations, and assess how a team uses AI. Also ships two subagents, for reading contracts and synthesising feedback, and two commands.
22 skills · 2 commands · 2 agents
Product management skills for discovery, strategy, prioritization, and communication workflows
26 skills
26 skills de day trade e scalp em uma: gráfico, scalp, tape reading, tamanho de posição (inclusive WIN/WDO), disciplina, circuit breaker, diário, backtest, robôs MT5, alertas, risco e ordens só com aprovação.
26 skills
An agent-driven development pipeline: phases in order, gates enforced by hooks outside the model, auditors that did not write the code they review, and state that survives closing the session.
21 skills · 5 agents
Master developer skill framework combining planning, simplified TDD/diagnosis loops, adversarial reviews, and context compression rules.
26 skills
Free company lookups from official government registers - no API key. Poland (KRS, VAT white list), Czechia (ARES), Nordics, Baltics, France, LatAm, Asia, EU VAT, LEI, sanctions and procurement.
26 skills
Thinking tools from untools.co as skills. Each skill applies one tool to your idea, topic, or context and produces the tool's output. The choose-tool skill picks the right tool.
26 skills
Workato development toolkit for AI coding agents
22 skills · 1 agent · 1 MCP server · hooks
Production-focused Claude Code config with portable skills, commands, and hook guardrails.
18 skills · 6 commands · hooks
Connect your AI to the work and knowledge enabled for your Columnline account.
24 skills · 1 MCP server
AI-powered development workflows with TDD enforcement, planning, quality tracking, and 11 bundled review agents
10 skills · 13 agents · 1 MCP server · hooks
Per-task model routing and cost estimation for Claude Code: pick the right tier (frontier / Opus / Sonnet / Haiku) per task, estimate cost before running, track historical spend, and use the frontier tier optimally.
25 skills
Postavi ti na disku vlastni brain: stahuje cally z Fathomu, prepisuje hlasovky a videa lokalne, destiluje je do znalosti a dela z nich napady, story a plan publikaci. Bez serveru, bez povinneho GitHubu.
12 skills · 12 commands · hooks
An agentic consulting harness: a three-persona interface (the Partner you talk to, the Architect who plans, the Analyst who builds), an orchestrator, and 20 specialist skills across four phases plus a communicate-and-align thread and a framework reference library, red-teamed at every gate to produce board-ready strategy decisions.
25 skills
Ultra-compressed communication mode. Cuts a large share of output tokens against an unprompted baseline while keeping full technical accuracy by speaking like a caveman.
20 skills · 1 command · 3 agents · hooks
A lightweight bilingual growth operating system for agents: diagnose constraints, choose playbooks, act within autonomy policy, and verify outcomes.
25 skills