Development plugins

Persistent semantic memory for AI coding agents — semantic search, context injection, session learning, and memory graph visualizer.

7 skills · 8 commands · 2 agents · 1 MCP server · hooks

Universal evidence-gated Loop plugin with the canonical Simplicio Runtime, Mapper, Fast, Dev CLI, Prism, review, compression, and learning skills.

12 skills

Connect your agent to a live Kubernetes cluster with mirrord, so it tests code changes against real services. Covers setup, config, CI, database branching, queue splitting, and preview environments.

12 skills

Verified Runtime MCP bootstrap and governed Simplicio skills for Claude Code.

9 skills · 1 MCP server

Shared static-analysis skills for Polyspace as You Code, Bug Finder, and Code Prover — review, fix, and justify findings (in code or in the results database), configure checkers, and find checker/option documentation. Install alongside any Polyspace static-analysis product.

8 skills

Git and GitHub delivery: /commit (convention-checked subject, Co-authored-by trailer, surgical staging), /pull-request (prep, create, conflict resolution, CI monitoring, review triage, merge, CI logs), /babysit-prs (safe-by-default PR fleet loop, opt-in worker and autopilot tiers), /babysit-loop (merge lane; merge is human until the repo adopts it), /worktree, /check, and /setup (layered source-control convention config; Conventional Commits by default).

6 skills · hooks

Disciplined implementation stage: execute approved plans inline (`/implementation:implement`) or via orchestrated worker subagents (`/implementation:implement-dispatch`) with incremental validation, TDD-by-default cadence, green-checkpoint commits, scope-fence drift detection, and divergence detection that routes back to planning. Build/test/lint, testing, and outcome verification live in the companion `toolchain`, `testing`, and `verification` plugins, invoked when installed.

3 skills · 3 agents

Tuple-Space and Yool safe-speed prompt runtime with fan-out commands and an opt-in UserPromptSubmit adapter.

1 skill · 3 commands · hooks

Repo-agnostic polyglot verification toolchain: build + test + lint for changed files across .NET, Python, TypeScript, Bash, PowerShell, Markdown, Go, YAML, and cross-cutting surfaces (`/toolchain:check`, `/toolchain:lint` with format-only `--fix` and gated `--code-fix`), `/toolchain:setup` for the per-ecosystem command config, `/toolchain:ratchet` for a CI ceiling on a count, and a turn-end Stop hook that warns when the recorded check or lint result is not a pass.

4 skills · hooks

Cross-product foundations for the Polyspace Agentic Toolkit — resolve the Polyspace installation root, configure build options, and find Polyspace documentation entry points. Every toolkit user needs these.

3 skills

Run and review Polyspace Code Prover to prove the absence of run-time errors in C/C++ code, and triage orange (unproven) checks. Pairs with polyspace-static-core for justifying findings.

3 skills

Drive the BMAD build lane end-to-end — bmad-build-auto plan -> build -> follow-up review per story, or an ENTIRE epic in one run (`/auto-bmad epic`) — with risk-gated TEA, epic-boundary gates + retrospective, one branch, a commit per phase, a PR and a report. Every step is delegated to a model-tuned host-native subagent on Claude Code, Codex, or opencode (or run inline where the host has no subagents).

2 skills

Fast Kotlin and Java code intelligence in Claude Code, powered by ktlsp

LSP

Low-token live Unity Editor workflows through the Hera CLI.

1 skill

Build and deploy Prismatic custom components and Code Native Integrations

8 skills · 7 commands · 7 agents · 1 MCP server · hooks

Bridge to the local AgentLayer wallet runtime (Solana, Bitcoin, EVM). Installs and connects the backend runtime on first use.

1 skill · 13 commands · 1 MCP server · hooks

Flutter architecture and quality conventions, adapted to your stack through a project profile. Layering with a pure Dart domain, state rules for Bloc, Cubit and Riverpod, responsive layout, accessibility and RTL requirements that design files never specify, performance rules, and a read-only pre-commit review gate.

8 skills

The /seite skill (write, check, audit, preview, build, deploy, theme) and automatic `seite check` hooks for seite static sites. Needs the seite CLI 0.21 or newer (https://seite.sh).

1 skill · hooks

Use when working with Terragrunt (0.68 to 1.2; OpenTofu or Terraform) - stacks, units, catalogs, expansion, dependencies, remote state, CAS/OCI sources, version upgrades, CI/CD pipelines (GitLab CI, GitHub Actions), AWS/GCP OIDC, performance, multi-account deployments

1 skill

Creative development the way Luis Bizarro builds it: Lisergia, Preact, React, WebGL, WebGPU, motion and CSS.

1 skill

A skill that creates, reads, changes, formats and validates BPMN 2.0 models (.bpmn) with @miragon/bpmn-cli: semantic edits by id, the drawing kept, Camunda 7 and Camunda 8 details, no XML by hand.

1 skill

91 specialist skills + 16 dispatchable subagents + 48 slash commands for coding agents — orchestrator, backend, frontend, QA, security, deploy, design, copy, SEO, growth, retention, observability, detective-spec, reverse-engineering, anatomy, static-analysis and more. Spec-driven development (/constitution, /analyze, /checklist), path-scoped rules, anti-AI writing (/humanize), persistent memory with learned-skills (accepted/rejected states, freshness, post-compaction recovery, Codex/Grok memory profile), and a skills-vs-agents disambiguation hook. Release notes live in CHANGELOG.md, not here.

91 skills · 48 commands · 16 agents · 1 MCP server · hooks

Software design skills for DDD, clean architecture, error handling, package design, refactoring, and maintainable domain modeling.

29 skills

TAKT workflow engine skills for multi-agent orchestration. Includes analyzers, builders, and optimizers for TAKT workflow YAML.

8 skills

Diagnose a repository, install the quality tooling it is missing, and pin a baseline that can only get better

8 skills

GitHub workflow skills, including systematic issue triage, grouping, prioritization, and cleanup.

5 skills

Ballerina language support — LSP code intelligence for .bal files plus an AI coding assistant for writing integrations and services, discovering libraries from Ballerina Central, and running and testing projects.

1 skill · 1 agent · 1 MCP server · hooks · LSP

Explain and review existing AMD/Xilinx FPGA projects with drill-down Vivado-style diagrams and clock-domain, constraint and overlay checks.

4 skills

Debug Agent For Lynx

2 skills

ReactLynx Development Assistant Agent

1 skill