Developer Tools plugins

Flow-enforcement engine for coding agents: declarative yamlgraph recipes, durable runs, deterministic evidence gates

2 skills · 1 MCP server

Work with Langfuse tracing, prompts, datasets, evaluations, and documentation.

3 skills

Maps markdown acceptance items to explicit implementation evidence for advisory spec-drift checks.

1 skill · 2 commands

Maps markdown acceptance items to explicit implementation evidence for advisory spec-drift checks.

1 skill · 2 commands

React Three Fiber (R3F) + drei tooling for declarative Three.js in React.

3 skills

A two-sided loop for improving agent plugins from test sessions. The 'session' skill (tester side) turns the current session record into a copy-pasteable report grading the plugins exercised; the 'jot' skill files a quick note or idea about a single surface mid-session; the 'triage' skill (author side) aggregates many reports and jots into a prioritized action plan, routing each finding to a concrete fix. All three share one report-format contract.

3 skills

Drive Google Colab from Claude Code over a bundled MCP server — open Drive notebooks, run code in the kernel, manage multiple sessions, upload/download VM files, mount Drive, read Colab secrets, inspect variables, edit notebook cells, and run fine-tune round-trip + local MLX conversion helpers. Optional headless/Playwright backend. Includes guided /colab:setup and /colab:help commands.

2 commands · 1 MCP server

Scaffold and validate new Cursor plugins. Handles directory setup, manifest generation, and pre-submission quality checks for the marketplace. (from Cursor)

2 skills · 1 agent

A lightweight control layer that keeps coding agents scoped, consistent, and verifiable.

2 skills · hooks

jj (Jujutsu VCS) support: git misuse prevention, daily operation guide, and expert guidance

2 skills · hooks

Turn skills into complete Codex plugins, implement their behavior, and improve them through measured local feedback.

2 skills · 1 MCP server

Give Codex consequence awareness, proven recovery, and reviewed multi-effect sagas.

1 skill · 1 MCP server · hooks

Route Claude Dynamic Workflow agent calls to local coding CLIs through a structured MCP bridge.

2 skills · 1 MCP server

Maintain confirmed development rules, current documentation and durable design decisions during everyday Codex work.

2 skills · hooks

APEX Legends gameplay video analysis and evidence-based coaching for Codex.

1 skill · 2 MCP servers

Bring new pull request context into Codex at safe turn boundaries.

1 skill · 1 MCP server · hooks

Evidence-driven Android, Flutter AOT, and native reverse engineering with the local offline runtime.

2 skills · 1 MCP server

Use Claude Fable 5 as a deep-reasoning architect and evaluator inside OpenAI Codex.

1 skill · 1 MCP server · hooks

Skill-only Codex plugin for UnityAgent architecture, routing and evidence-backed execution.

3 skills

CERN ATLAS AnalysisBase, dataset discovery, and ServiceX-verified extraction maps.

3 skills

Scenario-driven Level-1 QA workflows for the FlytBase cockpit.

2 skills · 1 MCP server

Loop skills for goal-first planning, review-driven implementation, and UI polish workflows in Codex.

3 skills

Record and review local Codex flights with screen, input, action, and exact-frame evidence.

1 skill · 1 MCP server · hooks

Cross-stack delivery, security review, and release-readiness workflows for the CyberVPN monorepo.

3 skills

Guided creation, lifecycle status, and truthful verification for Codex Starter Kit repositories

3 skills

Plan and execute bounded Beads work ledgers with optional Jev feedback.

2 skills · 1 MCP server

Michal Biarda's personal Codex toolkit for project setup, shared configuration, GitHub issue selection, and pull-request review workflows.

3 skills

Claude adapter: the parent projects per-topic custom expert agents and dispatches a swarm-coordinator background session that runs a multi-expert discussion over the vendored runtime and returns only the synthesis. Keeps discussion mechanics out of the parent context window.

1 skill · 2 agents

Run, inspect, and compare reproducible Raw vs CompText benchmarks with quality-first evidence.

3 skills

Maintenance skills for the mikersays-plugins marketplace — /sync-docs /install-marketplace /uninstall-marketplace

3 skills