Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. Bundles the behavioral skill and the inquisitor-mcp server (web search, project analysis, code tracing, phase tracking).
★not rated 5 28d agoA
tokens not measured
originalMIT
Drive a running Unity Mono development build from your coding agent (Claude Code, Codex CLI): ships the unity-devtools-mcp server (process discovery, live type reflection, C# expression evaluation, and ECS entity/component/buffer read-write over the Mono Soft Debugger protocol, no code injection), plus skills.
★not rated 5 4d agoA
tokens not measured
originalMIT
Diagnose and carry out the migration of an MCP server to the 2026-07-28 specification. Runs a deterministic rule engine over the code, then walks the remediation per finding: stateless transport, OAuth 2.1, the deprecated capabilities, and the SDK v2 rename.
★not rated 5 4d agoA
tokens not measured
originalMIT
A collection of development guides and automatic safeguards for CCL engineering work. It includes guides for planning products, testing, diagnosing defects, writing documentation, and building services, plus hooks that control parts of the workflow.
★not rated 5 todayA
tokens not measured
originalApache-2.0
Tight cause-fix-test triage from a pasted error or stack trace. No lectures, no bullet-point philosophy -- just cause, fix, regression test, sibling files to update.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Real-time metacognition for Claude Code. Six senses detect stuck loops, validation bias, repeated errors, and circular actions. Learns what works across sessions.
★not rated 5 4mo agoA
tokens not measured
originalApache-2.0
Live Flutter app introspection for coding agents: screenshots, widget-tree inspection, tap/type/scroll, and error capture. Dart package API summarization for agents.
★not rated 5 16d agoA
tokens not measured
originalBSD-3-Clause
Detect and optimize CPU and GPU workload bottlenecks with zymtrace continuous profiling — analyze flamegraphs through the MCP, plus install, upgrade, expose, and troubleshoot the platform.
Complete developer productivity toolkit: Git mastery, debugging skills, code intelligence, AI-assisted development, and best practices for modern software engineering.
★not rated 5 4mo agoA
tokens not measured
originalMIT
Scan a project and scaffold a complete Claude Code harness: hooks, skills, agents, rules, settings, strategic MCPs, worktree config and per-domain CLAUDE.md. Diagnose, approve, apply.
Plugin Claude Code full-stack de Direito Marcario brasileiro (uso nacional). Cobre o ciclo completo: pesquisa de anterioridade, diagnostico por CNPJ/contrato/site, classificacao NCL, proposta comercial e contrato por classe, deposito no e-Marcas e emissao de GRU; contencioso administrativo no INPI (oposicao, exigencia.
Systematic audit methodology for wireless driver control-frame and Information Element (IE) parsing across Linux kernel drivers and equivalents. Use when: (1) auditing a vendor's WLAN driver for memory-safety bugs in beacon/probe-resp/assoc-frame parsing, (2) hunting for cross-vendor bug-class propagation (idioms copy.
Continuously audit and improve an existing codebase. Ships /make-better (one-command flow) plus /systems-discover and /systems-review for fine-grained control. Audits across 9 topics: bugs, completeness, DRY, architecture, consistency, efficiency, tests, docs-sync, and security. Also ships /meta-review — a…
★not rated 5 22d agoA
tokens not measured
originalMIT
Comprehensive CI/CD failure analysis and fix toolkit with specialized agents for build failures, test failures, linting issues, and deployment problems.
Personal development workflow skills: brainstorming, planning, TDD, debugging, verification, review, and Codex integration.
★not rated 5 16d agoA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: