Expert MBSE engineer for system models, specifications, architectures, ontology authoring, semantic contracts and semantic query contracts. Use when exploring, updating and refactoring requirements, specifications and system model, adding features, managing verifications and creating tasks from introduced changes in…
★not rated 19▲
+1 2mo agoA
tokens not measured
originalApache-2.0
(beta/experimental) Host-agnostic, N-model variant of multi-llm-convergence. Drives any artifact (plan, PRD, design doc, spec, or implementation diff) to cross-model consensus from Claude, Codex, Gemini, or another capable host by rotating multiple built-in reviewer families through one uniform read-only reviewer…
★not rated 18▲
+1 1mo agoA
tokens not measured
originalMIT
The five-skill discipline loop for long-running agent work: freeze a task's scope into a workorder, gate sensory output behind human review, log decisions so they survive a context reset, hand off state when work changes hands, and close out with evidence instead of claims.
★not rated 17 5d agoA
tokens not measured
originalMIT
Plan-Build-Run — Structured development workflow for Claude Code. Solves context rot through disciplined subagent delegation, structured planning, atomic execution, and goal-backward verification.
★not rated 17 5mo agoA
tokens not measured
originalMIT
Structured development skills for any project. Provides brainstorming, planning, parallel agent development, browser testing, systematic debugging, and self-improvement workflows.
★not rated 17 2mo agoA
tokens not measured
GPL-3.0
Tactical AI-native SDLC layered on Claude Buddy — Cole Medin's R-PIV loop (Research, Plan, Implement, Validate) for brownfield projects, with epic/story/task decomposition in Jira & Confluence and GitHub as source control via MCP. A complement to buddy: reuses its Foundation, adds a checked-in AI layer (lean CLAUDE.md.
★not rated 17 14d agoA
tokens not measured
originalMIT
A self-contained, reliability-first agent development flow — grill a decision until it holds, turn it into a spec, and build it under deterministic gates. Plug-and-play skills, not vibe coding.
★not rated 17 26d agoA
tokens not measured
originalMIT
Neutral thinking partner for the user. USE WHEN the user asks for coaching, help with reflection, is struggling to get started or understand a fuzzy topic, wants to talk something through, wants to talk out loud, asks for a Socratic mode, is struggling to phrase a concrete problem or idea, seems emotionally loaded…
★not rated 17▲
+1 4d agoA
tokens not measured
originalMIT
Pre-1.0 preview. AI-Driven Specification-Driven Development (SDD) workflow — skills, agents, and commands for the 8-layer doc flow (BRD → IPLAN). Consumes the aidoc-flow framework spec. The doc--autopilot skills opt in to running their dispatched subprocesses without permission prompts; see README "What the autopilot.
★not rated 17 yesterdayA
tokens not measured
originalMIT
Marketing OS for developerneurs and solopreneurs. Built for engineers shipping products with zero marketing experience required. Spec-driven campaigns with positioning-as-invariant enforcement and quality gate walls.
★not rated 16 3mo agoA
tokens not measured
originalMIT
Scaffold multi-step agent workflows: per-stage subagents (each with a SubagentStop gate), manual launcher skills, and a dynamic-workflow orchestration script. Run once per stage you add.
★not rated 16 2mo agoA
tokens not measured
originalMIT
Strategic thinking partner for product decisions. Works through problems conversationally, challenges assumptions, helps you ship faster. Grounded in frameworks from Marty Cagan, Teresa Torres, Elena Verna, Brian Balfour, Chip Huyen, Ryan Singer, Hamel Husain, and more. Complete eval chain from first 20 test cases…
Structured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams.
★not rated 16 3mo agoA
tokens not measured
originalMIT
Orchestrate full delivery of a beads epic through polecats, refinery, and integration branches. The final stage of the design-to-delivery pipeline: gt-toolkit formulas produce the spec and plan, design-to-beads converts the plan into beads issues, and this skill delivers those issues through Gas Town infrastructure.
★not rated 16 yesterdayA
tokens not measured
originalApache-2.0
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: