Workflow plugins

OpenShift Node team assistant: kubelet, MCO, CRI-O, crun, conmonrs, Kueue operator, Jira (OCPNODE/OCPBUGS), Red Hat Knowledge Base, support cases, Prometheus, K8s/OCP docs, debug-binary + CVO deployment, and upstream SIG Node CI workflows

2 skills

Friction mining lifecycle for Total Recall — mining session transcripts, writing v2 stories, extracting moments from Kyle's comments, logging to the knowledge graph, and enriching over time. Encodes quality conventions so future sessions don't need re-teaching.

1 skill · 1 agent

Front door for Total Recall — query/operate Kyle's externalized self-model via skill modes (status/search/ingest/brief) and the /tr-brief cold-start command

1 skill · 1 command

Jev karar katmani: risk kapisi, triage/yonlendirme, hafiza filtresi, review triage + OTel/Grafana akisi

1 skill · hooks

Engagement doctrine for Octavian-Alpha-7: identity, precedence, operational rites - enforced by the heresy-guard.

1 skill · hooks

Stops every Claude Code agent from spending usage credits until you say so. When your claude.ai plan crosses a usage threshold (5-hour 95%, weekly 98% by default), all sessions, subagents and workflow agents pause on one macOS dialog: Allow credits until the window resets, or Stop. One-time /credit-gate:setup connects it to your status line. macOS only; needs jq.

1 command · hooks

Write a handover when a Claude Code session gets long, type /clear, and the next session picks up where you left off with nothing to paste. Shares its store with the clear-resume VS Code extension.

1 skill · hooks

Worktree isolation, a plan gate, a gate-before-stop and a push guard for Claude Code sessions.

1 agent · hooks

GitHub Actions for a container web app or console worker: a PR deploys to UAT, merging to main deploys to prod.

2 skills

Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.

1 skill

Get notified when Claude Code is waiting for you.

hooks

Scout-then-plan workflow for Agent Teams. Gathers context with subagents, enters plan mode to design team strategy, then executes with an agent team.

1 skill

Drives a coding task down the V (define each level + its paired verification), implements, then climbs verifying bottom-up and validating against intent. Traceability matrix as the spine.

1 skill

Conventions for running an agent loop unattended: state in files, a different approach each round, stall detection by counting, orchestrator/worker separation, and a heartbeat watchdog.

1 skill

Scaffold root and nested CLAUDE.md, AGENTS.md, GEMINI.md files using context architecture principles.

1 skill

Creates and maintains Architecture Decision Records (ADRs) in docs/decisions/ using the MADR 4.0 format. Supports creating, listing, updating, superseding, and searching ADRs.

1 skill

Designs and reviews REST, GraphQL, and gRPC APIs. Design mode produces OpenAPI specs, GraphQL schemas, or proto files. Review mode audits existing APIs for consistency, best practices, and breaking change risks.

1 skill

Claude Code integration for Hookify. Discovers and executes .hookify/<event>/*.{ts,sh,md,...} handlers from user and project scopes on every Claude hook event.

hooks

Translate EPUB files from a source language to a target language while preserving structure, HTML attributes, and metadata.

1 skill

Drive the coxd autonomous-coding orchestrator as the lead/firstmate — start the daemon, dispatch a GitHub issue to the crew, watch the loop, review the PR, merge on your word, deploy. Install once, use from any repo on any machine.

1 skill

Heavy structural codebase scan - surfaces weak patterns to upgrade and strong patterns to codify, and proves whether the repo's own gates (lint rules, hooks, CI checks, type rules, test guards, ratchets) still fire, producing ADR-style decisions with a durable cross-session backlog. The highest-risk / highest-payoff scan in the suite; walks the context map area by area. Modes: scan (one theme…

1 skill

Blind design contest between CLI agent seats (Claude Code, Codex CLI, Grok CLI, Antigravity agy, Muse). Each participant you name - engine:model@effort - builds three genuinely different prototype variants of one idea in its own workspace; a cross-family panel scores every variant blind on seven dimensions (wow, clarity at scale, wayfinding, interaction, craft, concept, utility); the host adds a…

1 skill

Strict, evidence-first triage of ONE already-built feature or ONE architecture redesign, ending at a human gate the method itself may never pass. Bounded members each answer a single question - worth to the user, workmanship, prior art, resilience, running cost, undo cost - reading only an evidence pack built from the tree, never the implementer's own account and never another member's answer.…

1 skill

Drops social padding, challenges assumptions, and optimizes responses for correctness over user comfort. Answer first, no preamble, second-guess conclusions.

1 skill

Answer inline review comments left in VS Code (Treehouse Review extension), with a background watcher for live back-and-forth

1 command

Companion (optional, not bundled): technical and product diagrams as standalone HTML with inline SVG. Pinned by commit sha — see MAINTAINING.md for how the pin is raised. MIT, (c) Cathryn Lavery.

1 skill

Write, review, and debug QTSurfer Java trading strategies — AbstractTickerStrategy, indicator builder, window listeners, state management, and advanced patterns

1 skill

Write, review, and debug QTSurfer strategies in QTScript (.qtscript) — beta: a compact strategy language whose braced bodies are plain Java

1 skill

Use Comment.io shared documents with the using-commentio skill

1 skill

Make a folder of skills installable and updatable with /plugin: a marketplace.json, versions that move when files change, names checked against Claude Code's built-in commands, strict validation, and install lines in the README.

1 skill