Synapse research orchestration plugin. Automates session lifecycle, provides 60+ MCP tools for experiment execution, literature search, progress reporting, and autonomous research loops.
Lean Project Management for solo developers managing multiple projects. 19 optimized commands, 50-60% token reduction via smart caching, natural workflow (plan, work, sync, commit, verify, done), tool-agnostic architecture supporting any PM system via MCP (Linear, Jira, Confluence, etc.), intelligent agent auto-invocation, interactive planning with deep research, monorepo support, safety-first design. Built for power users who value simplicity and extensibility.
A ticket tracker that is nothing but markdown files inside a repo. Ships the board skill, the worker, reviewer and queue planner agents, and the hooks that have the foreman dispatch the reviewer once a ticket is in review and write a handoff before its context is summarized.
Create, route, and inspect GitHub issues with gh CLI-backed defaults for DiversioTeam/monolith, repo-local execution repos, and project-board hydration.
Manage structured projects with long-term stable memory shared across humans and AI agents. Use this skill whenever the work needs a dedicated project manager (or project-manager agent) — including action items, kanban, sprint planning, decisions, history, and anything that benefits from persistent project context across sessions and agents. Read and write the project graph via MCP tools and the A2A protocol. Triggers: TensorPM, Context-Driven Project Management, CDPM, agentic project management, project memory, or any request to coordinate work with the local TensorPM desktop app. Local-first and MCP-native. Priced per account, never per seat: collaborators are free and unlimited on every plan, and AI model usage is included in the plan's monthly credit allowance rather than billed as tokens on top. Free Trial with no time limit and no credit card. Requires TensorPM desktop app running on macOS, Windows, or Linux.
Workspace management framework: structured markdown workspace for specs, context, memories, and issues with wikilinks, frontmatter relationships, and agent-executable issue decomposition.
Agentic Shape Up framework — TDD + BDD methodology with phase-specific agents (Shaping → Betting → Building → Validating → Done). Orchestrates pitches through a structured state machine with budget tracking and hill charts.
Agent-native dev task board with 3 core skills: devtask (investigate needs into well-specified tasks at any scale), devtask-doit (execute tasks end-to-end), devtask-review (review acceptance criteria + four-lens code-quality pass against real code).