Developer Tools plugins

Board-aware firmware, electronics, testing, recovery, and deployment workflows.

46 skills

Inspect and analyze WebAssembly modules through MCP tools backed by the Hexana runtime.

1 skill · 1 MCP server

Design TRMNL ePaper screens with the full TRMNL design system, and run your displays through the TRMNL MCP server.

1 skill · 1 MCP server

Skills, agents, and workflows for Honeycomb observability

11 skills · 1 command · 2 agents · 1 MCP server · hooks

Portable cfKanban guidance and skills for daily collaboration, Owner administration, and safe Cloudflare deployment.

5 skills

Offline text to speech on your own computer: add local speech to an app, pick a voice, make WAV files from text, clone a voice you have the right to use.

4 skills

A documentation-only Codex plugin that adds one explicit $fable-mode skill for intent locking, visible routing, grounding, capability, depth, and delegation control.

1 skill

Open source maintenance skills, commands, agents and workflows

6 skills · 37 commands · 8 agents

Governance-first specialist skill framework for routed, auditable AI coding workflows.

14 skills · 21 commands

Governance-first specialist skill framework for routed, auditable AI coding workflows.

14 skills · 21 commands

Official Boxel card-building skills, from cardstack/boxel-skills. Installed automatically with boxel-cli.

27 skills

AI-powered network analysis, visualization, and export using Gephi Desktop. Provides 121 MCP tools plus specialized agents for claim verification, layout iteration, structural analysis, and text-network construction.

1 skill · 11 commands · 4 agents · 1 MCP server · hooks

Skills for working with Boxel realms via @cardstack/boxel-cli.

10 skills

Local repo-intelligence index + MCP server: semantic search, symbol/graph navigation, impact-surface preflight, git + GitHub papertrail, and a source-anchored memory graph.

4 skills · 1 MCP server · hooks

No description.

5 skills

Three-skill flow for building Quarkus + LangChain4j agentic AI applications: setup (prerequisites), scaffold-project (create + component scaffolding), and audit-project (conformance review). Pairs with the repository's CLAUDE.md conventions. Requires the Quarkus Agents MCP and context7 (see README).

3 skills

DEPRECATED — moved into aws-startup-advisor in the Agent Toolkit for AWS (aws/agent-toolkit-for-aws). All seven skills ship there; install that plugin instead. Migrate from Azure, GCP, or Heroku to AWS — including your entire AI stack. Moves infrastructure (Azure App Service → Elastic Beanstalk, AKS → EKS, Cloud Run → Fargate, Heroku Dynos → Elastic Beanstalk by default with Fargate/EKS overrides, databases → RDS/Aurora), Azure OpenAI/OpenAI/Gemini/Anthropic workloads to Amazon Bedrock, and agentic systems (LangChain, CrewAI, AutoGen, OpenAI Agents SDK) to AWS-native frameworks. Generates runnable Terraform, migration scripts, provider adapters, and deployment artifacts. Gives honest model-by-model pricing comparisons so you know exactly when Bedrock saves money and when it doesn't. The bundled llm-to-bedrock skill executes AI/LLM migrations automatically (rewrite, evaluate, deliver a branch).

6 skills · 7 agents · 1 MCP server

Set up and maintain portable coding-agent skills with explicit local consent

2 skills · 1 MCP server

Zero-cost live Figma canvas bridge (`figma-agent` CLI + DESIGN:OS Bridge plugin) for AI coding agents — works on Figma Free.

2 skills · 1 command

The best of Matt Pocock's Skills, Superpowers, and Compound Engineering. One complete, simple, supercharged SDLC system for your coding agent.

41 skills

Turn AI sessions into a maintained, human-reviewed knowledge base: capture sessions to append-only logbooks, compile into consistency-checked dossiers gated by trust tiers (proposed → verified → canonical), query the canon tier-aware, and render it as a navigable offline gazette (built by the bundled press). A deterministic recursion engine tracks claim-level dependencies (rests_on + author-anchored spans) via an append-only decision log, per-span revisions, an early-cutoff gate, and an fsck byte-fixpoint. Author architecture decisions as MADR ADR pages (bureau:adr) with supersedes edges — a superseded decision leaves current fact only once the superseding ADR is content-bound approved (ADR-0006). Delegate the review queue to Codex as your representative (bureau:codex-review) — it advises, or, where a workspace opts the codex authority in, commits under --by codex (ADR-0007). Bulk-approve the whole backlog in one confirmation (bureau:approve-all) — the AI prepares and confirms, you fire the single --by human line. Karpathy LLM-wiki pattern + session provenance + a human review gate. Self-contained — no separate install.

4 skills · 18 commands · hooks

Mod almost any game you own with an AI agent: engine recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos, and a shared knowledge base of how games were modded.

12 skills · 3 agents · 1 MCP server · hooks

A quiet, risk-scaled engineering method layer for Codex.

13 skills

Stop AI agents from patching symptoms. Forces structural root-cause fixes over symptom patching in any language or stack.

1 skill

Inspect local Parquet metadata, compression, encodings, indexes, statistics, and Bloom filters with iParq.

1 skill

Design a new database, audit an existing one on two independent axes, and plan safe migrations — across SQL, document, key-value, vector, time-series, and graph engines.

36 skills · 6 agents · hooks

Best-of-breed agentic-coding skills for planning, execution, quality, and verification with any agentic coding harness.

22 skills

Use BuildBetter's MCP server and bb CLI from Claude Code.

9 skills · 1 MCP server

Sub-task notifications and delegation to Claude Code, Codex and Grok Build.

1 skill

Collective browser automation intelligence. Share and discover reliable methods for web interactions across the Claude agent network.

6 skills · 1 MCP server