Deterministic harness-maturity audit for your repository: measures AGENTS.md, rules, skills, hooks, sensors, CI, and hygiene against a 5-level maturity model — without any LLM calls — and teaches the agent how to fix every gap.
★not rated 551▲
+2 2d agoA
tokens not measured
originalMIT
Figma design system to design.md — Extract Figma design system into a structured design.md document. Automatically detects token files, style configs, and Figma MCP data to generate comprehensive design system documentation covering Colors, Typography, Spacing, Border Radius, Elevation, Responsive, and more.
★not rated 39▲
+1 6mo agoA
tokens not measured
originalMIT
Comprehensive toolkit for creating production-ready Claude Code resources: agents, skills, plugins, commands, hooks, MCP tools, MCP servers, and patterns. Expert guidance with templates, examples, and best practices following Anthropic specifications.
★not rated 21 1mo agoA
tokens not measured
originalMIT
Day-zero operating system for AI-assisted SaaS development. A 5-phase Project Genesis Wizard that prototypes before it specifies, 28 skills, 12 agents, 11 commands, 12 rules, a generated CODEMAP so agents find code without reading it, a curated registry of external packs, a 1.346-project self-hosted catalogue, and…
Spec-driven development workflow + a production-tested full-stack reference. A 5-step /spec- workflow (draft, refine, phases, plan, implement) plus /spec-setup, /spec-doctor, and /spec-troubleshoot for environment setup, /spec-secrets for redacted secret-leak auditing, and a vibe-spec skill with 21 on-demand stack ref.
★not rated 9 3mo agoA
tokens not measured
originalMIT
Adds intent-and-decision alignment before implementation with an optional durable HTML record, explicit behavior-preserving codebase cleanup, evidence-based review and fixes repeated until material issues are resolved, PR explanations and a complete diff reader with reasons, UI design and mockups, clear explanatory…
★not rated 8
changed 6d agoA
tokens not measured
originalMIT
A plan/execute/verify loop for a single developer in Claude Code, with adversarial review at every gate: plans and diffs get refuted by a fresh Claude subagent or a panel of outside models (OpenAI, Gemini, DeepSeek), not just approved. State lives in files, not the conversation, so you clear aggressively and keep both.
★not rated 8▲
+2
changed 3d agoA
tokens not measured
originalMIT
Intent-Driven Development framework plugin — automates the IDD workflow with role-specific tools for stakeholder interviews, artifact generation, and structured documentation.
Vibe coding is how you start; engineering is what keeps it alive. Auto-activating Claude Code plugin that silently installs production engineering guardrails — architecture awareness, TDD, quality gates, security-first development, and 25+ skills so vibe coders build real systems without thinking about process.
★not rated 6 6mo agoA
tokens not measured
originalMIT
Three agent skills that catch structural decisions as you make them, ask you to defend each one, and hand back a mastery map of your project: /ledger, /ledger-audit, /ledger-report.
★not rated 6
changed 1mo agoA
tokens not measured
originalMIT
Project-wide living documentation for AI-assisted codebases. Maintains one source of truth per user-visible feature in a hierarchical feature tree, with drift detection and bidirectional code-doc linkage.
★not rated 5 4mo agoA
tokens not measured
originalMIT
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: