EVOKORE-MCP — a multi-server Model Context Protocol aggregator with skill discovery, HITL approval, RBAC, session continuity, and an opinionated orchestration framework.
Base skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user intent to matching domain skills via symlinks, delegates execution to Refly backend. Use when user asks to: create skills, run workflows, automate multi-step tasks, or manage pipelines. Triggers: refly…
Run reverse engineering as a coordinated EVOKORE operating system with expert panels, additive workflows, and lightweight learning loops. Use when the target is complex enough that you want more than isolated tool calls.
Convert completed reverse-engineering work into better future workflows, skills, and panel narratives. Use after meaningful milestones, repeated friction, or major analysis wins.
Coordinate EVOKORE reverse-engineering work across Ghidra-style static analysis, semantic recovery, and debugger-guided triage. Use when opening an unfamiliar binary, planning a decompilation workflow, or choosing between static and dynamic analysis paths.
Recover subsystem meaning through disciplined decompilation, xref analysis, renaming, typing, and evidence tracking. Use when a binary is partly mapped and you want durable semantic cleanup instead of ad hoc notes.
Use when bootstrapping or extending the pre-commit hook chain (Husky + lint-staged + Prettier + typecheck + integration tests) for an EVOKORE-style TypeScript repo, including detecting an existing setup, surfacing the diff, and never silently overwriting a configured chain.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Establish the first analysis charter for an unfamiliar binary, library, firmware image, or package. Use when the target is new and you need to choose the right tool lane before diving in.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use when multiple agents need to write to the same repo concurrently without file-lock stalls — applies claim-before-write, parallel branch fan-out, and semantic 3-way merge to achieve 87% auto-conflict resolution.
Use when reviewing your own tool-call sequence (or another agent's) for wasteful patterns — re-reading a file you just edited, repeated reads of the same path, bash echo for plain communication. Surfaces concrete patterns to avoid, not vague style advice.
Use when automating browser interactions, web scraping, or E2E UI testing using AI-optimized abbreviated selectors and isolated multi-session contexts.
Use when cutting a GitHub release that needs progressive canary rollout (5%→25%→50%→100%) with automated health gates and auto-rollback on error-rate or latency regressions.
Use when you need to implement or debug Claude Code hooks using the 3-phase memory sync pattern (STATUS→PROGRESS→COMPLETE) with JSON flow-control responses.
Use when orchestrating a non-trivial coding task end-to-end and you want disciplined phase/panel/gate structure without giving up autonomous-loop continuity. Drives the 5/5/5 master workflow (5 phases, 5 panels, 5 gates).
Use when you need to structure complex development work using the 5-phase SPARC methodology (Specification, Pseudocode, Architecture, Refinement, Completion).
Use when ProxyManager throughput or cold-start latency is a bottleneck — catalogs six optimization patterns (O(1) lookup, 3-tier cache, batch compression, pool reuse, lazy deserialization, parallel boot) with TypeScript snippets and expected gains.
Analyzes a batch of completed phase specs against their actual session outcomes and produces an updated phase spec template with structural improvements, optionally applying the improved template to remaining unstarted phase specs.
Ingest external repositories, research papers, and benchmarks using 40-agent swarms to analyze, adapt features, and improve current workflows.
★not rated 3 3mo agoA31 tokens
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: