Development plugins

Author and evolve metaframework solution catalogs: SRN identity, kind-bucketed directories, frontmatter contracts, JSON Schema data models, additive-only evolution, and portal-enforced integrity

7 skills · 3 commands · 1 agent

Find security vulnerabilities in ELF binaries using ClearBit IR analysis. Skills: taint-bug-detection (buffer overflow, command injection, UAF), iot-bug-detection (cross-binary IoT firmware taint), cisb-bug-detection (compiler-introduced security bugs via DSE/UB/reordering), write-custom-query (custom IR queries). Orchestrates Plan, Analyze, and Validate agents.

4 skills · 5 agents · 1 MCP server · LSP

CLI-agnostic Ralph autonomous development loop — drives either claude or cursor-agent from a terminal with token tracking, context rotation, gutter detection, retry/backoff, and Spec Kit support

6 skills · 5 commands

The MCP servers and Claude Code plugins its owner has tested and likes, with their install, update, rename and fix procedures: /preferred-tools:install, /preferred-tools:configure, /preferred-tools:update and /preferred-tools:fix.

7 skills · 4 commands

PostgreSQL coding standards for AI assistants: queries, jsonb, schema, indexing, performance analysis, safe migrations. PostgreSQL 18 and later.

8 skills · 2 agents · hooks

Comprehensive multi-phase PR review — change analysis with risk_class routing, 2-pass deep code review, risk-gated quality-review passes (domain-architecture, data-contracts, ops-reliability, change-evolution), security scanning (OWASP deepen), and documentation-drift checks, posted as one unified GitHub review. Test execution and coverage analysis are left to CI. Plus fix: apply the findings in the working tree — refactor each code smell by the named Fowler/Kerievsky move in the language's own idiom, rewrite flagged docs and comments, regenerate stale artifacts, and defer anything needing a human design decision, one commit per finding and the test suite once per partition, then push the head branch once it is green and reply to and resolve the review comments it answered. Plus monitor-pr: continuously watch a PR for CI failures and review comments (drive with /loop), delegate the fixing to fix, push, and resolve or reply-acknowledge each comment once its fix ships. Rust and mac-ui Web Components changes get tailored checks.

11 skills

Design deep modules, sharpen a project's domain model, and draw the result. Shared vocabulary for module depth, interfaces, and seams; domain terminology, ADRs, and CONTEXT docs; a codebase deepening scan with an HTML report; and 45 self-contained HTML/SVG diagram types in the Fabric skin — including lifecycle phase maps — with .drawio, Mermaid, and Excalidraw import. Run setup-matt-pocock-skills once first.

5 skills · 6 commands

Spec-driven development skills with blocking quality gates and an audit trail.

11 skills

Use Apple's on-device Foundation Model from Claude Code for private, offline reviews, summaries, and commit messages.

2 skills · 8 commands · hooks

Agent Skills for maintaining high-quality open-source Node.js, TypeScript, Next.js, and React apps and packages - linting, type safety, testing, packaging and releases, and CI quality gates.

10 skills

Coding agent skills tailored to NethServer development guidelines

10 skills

Reviews iOS apps for App Store readiness using 8 specialized agents. Supports React Native and Swift/Xcode.

1 skill · 1 command · 8 agents

Autonomous agentic software factory: orchestrator + model router + scheduler over mattpocock/skills tickets, with parallel worktree-isolated implement/review/fix/merge loops and a live HTML kanban board.

3 skills · 6 agents · hooks

Analyze codebase architecture and tech stack to automatically generate specialized Claude Code agent teams

2 skills · 4 commands · 4 agents

Multi-agent PR review: 6 specialist reviewers in parallel, including a behavior-parity reviewer that compares old and new code, a validator that re-reads the code behind every finding (dedupes, scores confidence, checks the suggested fix), and an impact analyst that maps which existing flows the change could break.

2 commands · 8 agents

An installable toolkit for measuring, operating, and improving AI systems.

10 skills

pydantic-ai-powered semantic hook enforcement — classifies AI output against YAML rules using a configurable hosted LLM provider

7 skills · 1 command · 1 agent · hooks

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

5 skills · 1 command · 4 agents

Default end-to-end development skillset — pairs with the session-manager scheduler to form a develop → queue → validate → release loop.

10 skills

Senior Software Engineer and Senior IT Architect: core loaded by SessionStart hooks, language selector (es/en), 7 Skills, 2 subagents without write tools and deterministic hooks (NN-08, project knowledge, validation at stop). / Ingeniero de Software Senior y Arquitecto de TI Senior: núcleo por hooks SessionStart, selector de idioma (es/en), 7 Skills, 2 subagentes sin herramientas de escritura y hooks deterministas (NN-08, conocimiento del proyecto, validación al terminar).

7 skills · 2 agents · hooks

Specialized subagents for multi-agent architecture, deterministic testing, reliability review, security audit, incident triage, and evaluation design.

4 commands · 6 agents

REQ/flow templates, requirements lint, skills and subagents for the requirements lifecycle.

6 skills · 3 agents · hooks

Autonomous GitHub Project board runner: super-board, super-build, super-qa, super-review, super-collect, visual, git-sync, ui-refine-loop. After install, run /super-board onboard to add the guard hooks, .claude/bin scripts and workflows a plugin cannot ship.

9 skills · hooks

AST-aware code queries, code-health and dependency analysis for AI agents across 43 languages: skeletons, symbols, repository outlines, definitions, references and callers; structural patterns, hotspots and duplicated code; and file dependency graphs, cycles, coupling and impact, over MCP.

9 skills · 1 MCP server

Senior Software Engineer and Senior IT Architect: core loaded by SessionStart hooks, language selector (es/en), 7 Skills, 2 subagents without write tools and deterministic hooks (NN-08, project knowledge, validation at stop). / Ingeniero de Software Senior y Arquitecto de TI Senior: núcleo por hooks SessionStart, selector de idioma (es/en), 7 Skills, 2 subagentes sin herramientas de escritura y hooks deterministas (NN-08, conocimiento del proyecto, validación al terminar).

7 skills · 2 agents · hooks

/q-plan, /q-brainstorm, /q-skystorm, /q-validate, /q-review, /q-research via the quorum MCP server

7 skills · 1 MCP server · hooks

Build features as vertical slices — colocated specs, context, and tests — measured by oracle strength.

9 skills

Harness Engineering toolkit — Context Budget, Knowledge Pyramid, Feedback Ladder, Maturity Assessor, Gardener Agent, Gate Runner, Features Validator

6 skills · 2 agents · hooks

Agent session spawning, messaging, and dispatch — the Legion and its Legate.

7 skills · 1 agent · hooks

Engineering working contracts, bug-audit, and verification skills for coding agents.

9 skills