Skill Claude CodeCodex
Produce verification evidence so a human can decide whether to archive (accept) or follow up on a completed backlog item. You are NOT deciding correctness — you are gathering proof and showing it.
Skill Claude CodeCodex
Produce verification evidence so a human can decide whether to archive (accept) or follow up on a completed backlog item. You are NOT deciding correctness — you are gathering proof and showing it.
Skill Claude CodeCodex
You are a workshop clarification agent for the Swarm Manager backlog system. An operator is asking for help understanding a specific decision in a workshop round.
Skill Claude CodeCodex
Run the final synthesis pass for a non-research backlog item. Incorporate the latest answered workshop decisions into plan.md, reassess readiness against the updated plan, and write a finalize round that contains no new decisions.
Skill Claude CodeCodex
Run the final synthesis pass for a research backlog item. Incorporate the latest answered workshop decisions into conclusion.md, reassess readiness against the updated conclusion, and write a finalize round that contains no new decisions.
Skill Claude CodeCodex
Run one workshop round for a research backlog item. Analyze the research question, explore investigation directions, generate targeted decisions and informational findings, self-assess readiness across 5 research-oriented dimensions, and update the draft conclusion based on accumulated user responses and findings.
Skill Claude CodeCodex
Run one workshop round for a backlog item of any kind. Analyze gaps in the current implementation plan, generate targeted decisions and informational items to fill those gaps, self-assess readiness across 5 dimensions, and update the draft plan based on accumulated user responses.
Skill Claude CodeCodex
Apply a structured investigation methodology to any codebase or system: define what you need to learn, map the landscape, form understanding hypotheses, validate through targeted reading, and produce findings that inform downstream decisions. This methodology produces exploration reports that accelerate planning and…
Skill Claude CodeCodex
You are part of an independent specialist team. There is no coordinator in the default execution path. Own your lane, persist durable findings, and avoid inventing coordination work that the team policy did not enable.
Skill Claude CodeCodex
You are operating inside a leader-led team. The resolved team policy will tell you whether you are the lead or a reporting member, and whether execution is single-process or multi-process.
Skill Claude CodeCodex
You are part of a peer team. Teammates are independent specialists, but coordination between peers is expected when it improves outcomes.
Skill Claude CodeCodex
Govern how teams are equipped with scenario-based tool skills, using a lazy evaluation pattern that generates honest demand signals for development prioritization.
Skill Claude CodeCodex
Prioritize stabilizing and improving time-related behavior in this scenario.
Skill Claude CodeCodex
Apply a structured severity assessment to any incoming problem, finding, or escalation: gather evidence, assess severity and blast radius, then decide on response urgency and approach. This methodology produces triage reports that drive downstream investigation, resolution, or prioritization.
Skill Claude CodeCodex
Prioritize migrating scenarios/{{TARGET}}/ui/ to a token-driven, primitive-owned design system so major theme refreshes become low-risk and repeatable.
Skill Claude CodeCodex
Prioritize establishing robust unit test infrastructure in scenarios/{{TARGET}}/ across all service directories (ui/, api/, sidecars). This skill steers toward a testing foundation that makes it easy for agents and developers to add, maintain, and trust tests.
Skill Claude CodeCodex
Prioritize extracting, standardizing, and consolidating utilities so shared logic is consistent, discoverable, and testable. The goal is to prevent duplication and drift while keeping utilities sharply scoped and aligned to screaming architecture.
Skill Claude CodeCodex
Prioritize user experience quality across all interfaces in this scenario. Do not break functionality or regress tests; all changes must maintain or improve completeness.
Skill Claude CodeCodex
Produce marketing videos, product demos, and promotional content by combining AI-driven scripting with browser recording, desktop recording, and video compositing.
Skill Claude CodeCodex
Use visited-tracker to record file coverage, avoid duplicate work, and leave handoff notes that persist across conversations.
Skill Claude CodeCodex
Ensure scenario UIs work reliably across all three Vrooli deployment contexts — localhost development, Cloudflare tunnel, and app-monitor proxy/iframe — by adopting @vrooli/api-base and @vrooli/iframe-bridge with consistent file-level conventions.
Skill Claude CodeCodex
Generate engaging X/Twitter dev log threads by mining activity data from Vrooli scenarios for a given time period. Outputs draft content for review before posting.
MCP server Cursor
One of 3 in mcp.json
MCP server "vrooli-mcp-server", hosted remotely at 161.35.96.7, as configured in Vrooli/Vrooli.
MCP server Cursor
One of 3 in mcp.json
MCP server "weekly-review", hosted remotely at 161.35.96.7, as configured in Vrooli/Vrooli.
MCP server Cursor
One of 3 in mcp.json
MCP server "daily-standup", hosted remotely at 161.35.96.7, as configured in Vrooli/Vrooli.
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: