Repowire mesh usage skills for AI coding agents: cross-agent review and planning, delegate, usage patterns, and install/update. Backend-agnostic and parameterised on the agent you choose.
OWASP API Security Top 10 skills for AI coding agents: BOLA detection, auth and RBAC scaffolding, injection checks, security test generation, full API security review, and OpenAPI schema hardening.
★not rated 21 21d agoA
tokens not measured
originalMIT
WAYD (What Are You Doing?). A deliberately minimal social feed for devs using AI coding agents: the scroll break you take while your agent works, without leaving your console. Share a vibe, react, reply, then get straight back to the task. Built on GitHub Issues as a transparent backend.
★not rated 8 4mo agoA
tokens not measured
originalMIT
Intent-Driven Development framework plugin — automates the IDD workflow with role-specific tools for stakeholder interviews, artifact generation, and structured documentation.
Generates a grounded, verified, two-tier agent context layer (lean CLAUDE.md + deep .ai/docs) for any codebase, plus report-only issue detection. 100% local, read-only.
★not rated 6 23d agoA
tokens not measured
originalMIT
Shakespeare, pirate, gen-alpha, toronto-mans, and ontario-bud persona skills for Claude Code. Changes register (how Claude talks) without changing behavior — code, paths, commits, safety warnings, and errors stay plain English by default.
★not rated 3 2mo agoA
tokens not measured
originalMIT
Unofficial skillset inspired by The Rails and Hotwire Codex (by Ayush Newatia), published with the author's permission. Skills and runnable checkers for Rails + Hotwire apps that ship to web/PWA, iOS, and Android. Unique vs other Rails plugins (which are LLM coders/reviewers): every skill ships a deterministic…
★not rated 3 3mo agoA
tokens not measured
originalMIT
Autonomous software delivery for Claude Code — 8 lifecycle phase skills (auto-spec → auto-ship) plus the loop/verify/checkpoint/budget primitives, with deterministic enforcement hooks and runnable Workflow templates.
Codexa for Claude Code. MCP server exposes evidence-backed repo context tools; SessionStart injects repo context, PreToolUse saves an implicit pre-edit baseline, Stop runs the post-edit drift review and surfaces blocking drift to the model. Slash commands wrap the codexa CLI.