Reasoning-first, feature-aware development workflow for Claude Code. Git is the source of truth; status is derived, never stored. Turns 'I want X' into a planned, executed, verified, and landed change through eleven yolo- skills Claude routes to from plain intent.
★not rated 9 2mo agoA
tokens not measured
originalMIT
The framework client-facing teams use to build internal and client apps with AI. Two agents (Product Owner + AI Developer) run a disciplined spec-to-deploy lifecycle, packaged with FuseBase Apps domain skills. Closes the gaps that break real AI app development: drift, context rot, scope creep, unreliable hand-offs.
★not rated 9 11d agoA
tokens not measured
originalMIT
Multi-agent workflow patterns for Claude Code. Skills for brainstorming, research, debate, prototyping, risk analysis, stress testing, and build planning. Includes hooks for auto-formatting, diff-aware scoping, guard rails, worktree setup, notifications, and verification.
★not rated 9 1mo agoA
tokens not measured
originalMIT
AI-First Product Builder skills: falsifiable hypotheses, exposure plans, and the hypothesis-to-evidence experiment loop for prototypes built with coding agents.
★not rated 9
changed yesterdayA
tokens not measured
CC-BY-SA-4.0
Turn a short project brief into a ready-to-build Claude Code workspace: persistent 12-page wiki, domain-specific skills, phase Execution Docs with per-activity model routing, a gated /task pipeline with QA and simulated user testing, proactive context handoff, wiki lifecycle with archive, and hooks that guard against…
★not rated 9 1mo agoA
tokens not measured
originalMIT
Self-contained AI readiness assessment for any repo — scan for evidence, ask clarifying questions, place the team across all fourteen dimensions of the Agentic Experience 5-Level Habitat Maturity Model (the spine) and the six-level Sovereign Engineer cognitive ladder, compute the Habitat/Workflow Gap, and produce a…
★not rated 9 19d agoA
tokens not measured
originalApache-2.0
Engineering decision framework based on Elon Musk's 5-step algorithm: question requirements, delete parts, simplify and optimize, accelerate cycle time, automate. Decomposed into 6 skills with strict order enforcement and Obsidian-compatible wiki links.
★not rated 9▲
+1 3mo agoA
tokens not measured
originalMIT
Skills for running AAIF (Agentic AI Foundation) in-person and online events — event content writing (announcements, Luma pages, LinkedIn carousels, recaps, speaker bios/invites, day-of slides, attendee reminders) and chapter ops (spin up a new city chapter or online event series, triage community intake, clean intake…
★not rated 9▲
+1 2d agoA
tokens not measured
originalMIT
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▲
+1 2mo agoA
tokens not measured
originalMIT
A plugin that shows a live, layered map of a software project's dependencies and architecture. It displays planned parts as inactive nodes and marks them as work is built and verified.
★not rated 10▲
+2 9d agoA
tokens not measured
originalMIT
AI Development Methodology: 6 phase gates from discovery to ship, 28 skills, 38 review sub-agents, and WHY-first enforcement hooks. Stops code being written before the problem is understood.
★not rated 9 3d 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: