VoIP
claudeAsync VoIP library for the AI age. Ships an MCP server to make phone calls and (planned) skills.
4 skills · 1 MCP server
SuperJoe — CodingJoe's digital clone following his coding guidelines and best practices.
Plugin superjoe from marketplace codingjoe in codingjoe/claude-plugins. Commands read from the repo's manifest — yesterday.
joe-auditWhole-repo audit for over-engineering. Scans the entire codebase, not a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", or "joe-au
superjoe-codeWrite minimal code and review it. End after killJoe and stop for human review. Use superjoe-ship for tests and docs.
superjoe-shipAdd tests and docs to reviewed code. Run after superjoe-code and human review. Stop when coverage and docs pass.
builderJoeImplement features, fix bugs, and refactor code. Use for code changes, feature implementation, and bug fixes. Do NOT use for writing tests, documentation, code review, security analysis, or multi-file orchestration.
docuJoeWrite and update documentation, docstrings, README files, and comments in superjoe-ship after tests pass. Use for documenting code, auditing docstrings, writing user-facing docs, or explaining design decisions. Do NOT use for code changes, reviews, or security analysis.
inspectorJoeReview code for bugs, performance problems, naming violations, and test coverage gaps. Use for PR review, code audit, or checking for edge cases. Do NOT use for fixing issues found, docs, implementing features, or security audits.
killJoeCleanup tool for builderJoe's changes. Remove newly added tests, docstrings, and code comments. Run at the end of superjoe-code and after a cut in superjoe-ship.
lazyJoeGuard against unnecessary code. Find over-engineering, bloat, and work another joe already owns, then delegate back. Do NOT write, fix, or document code yourself.
researchJoeResearch online documentation and find and evaluate packages on package indexes. Use to verify, compare, and vet dependencies and to read current docs. Do NOT use for code changes or test changes.
secretJoeFind security vulnerabilities, evaluate exploitability, and provide proof-of-concept reproduction. Use for security audits, penetration testing, or vulnerability research. Do NOT use for fixing vulnerabilities found, writing documentation, making code changes, or general code review.
testJoeWrite tests for the reviewed code and run the test suite in superjoe-ship after human review. Do NOT use for writing production code, cutting branches, or docs.
Problems found in this repo's manifests
Async VoIP library for the AI age. Ships an MCP server to make phone calls and (planned) skills.
4 skills · 1 MCP server
Regular Expression Linter — write your own linting rules using regular expressions. Skills for running relint and authoring new rules.
2 skills
Write and check German text in Einfache Sprache, plain language to DIN 8581-1. Short sentences, active voice, no officialese, every technical term explained. Ships a checker and a test suite. Refuses when Leichte Sprache is what the reader actually needs.
1 skill
Auto-upgrade JavaScript and TypeScript syntax to new ECMAScript features based on browser support.
1 skill
Naming conventions guidelines — solving computer science's second-hardest problem.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.