Autonomous GitHub Issue Fixer agent called LoachBot. Picks the single most-recently-updated GitHub issue created by and assigned to you, implements a fix in a Pull Request, then unassigns the issue. Use when the user wants to work through issues assigned to them, or asks to "run LoachBot Issues", including repeated…
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.…
Use this skill for plan, architecture, product, technical design, or implementation-plan review when the review should improve the artifact through an adversarial, self-terminating convergence loop. Reviewers attack the plan, an independent verifier tries to refute every blocker before it can block, and a hard…
Run a rigorous conversion rate optimization audit on a real landing page, signup flow, or checkout — measuring the page in a browser and against analytics data rather than scoring it against a generic checklist — then produce prioritized fixes with lift ranges, and an experiment plan with the sample size and duration…
Scans a project's current practice, classifies each convention by how it is best enforced, and routes it to the fittest mechanism - config, project doc, rule, a project skill, or a paste-ready pointer. Use when setting up an existing project so the first agent execution follows its conventions, or when asked to…
Focuses all operations and file searches on the local clone of the OpenShift documentation repository at /openshift-docs. Use when working on openshift-docs content or when the user explicitly requests the OCP context via the /ocp command.
End-to-end test for a converted Unity project. Delegates the full conversion (including agent-driven Steps 4a and 4c) to /convert-unity, then launches Studio with the produced rbxlx, drives the gameplay-feature fixtures via Studio MCP, and writes a combined pass/fail report. Upload step (6) is skipped — cached asset…
Guides WeChat Mini Program project work through official WeChat DevTools and native Mini Program structure, WXML, WXSS, page/component code, and built-in components. Use when working with DevTools CLI, miniprogram-automator, uni-app mp-weixin output, app/page JSON, WXML/WXSS, official components, preview/upload…
Create self-contained HTML visualizations (single .html file) from conversation content, data, or ideas. Trigger on: "visualize this," "make a deck/slide/infographic/dashboard," "build a one-pager / poster / carousel / kanban / mind map / org chart / flowchart," "show me a chart," "render as HTML," or any ask to…
Cut a shoot into several finished, captioned 9:16 Instagram Reels with hooks and a caption, re-cut published pieces into new hook variants, register both for review on the Engage /video page, and push the approved ones to Buffer. Use when Jared says /vid-batch, "cut the footage", "draft the videos", or when intake…
Drive a task queue (loop-tasks.md) to completion in ANY repo. Detect the repo's own rules, then for each task plan -> /review-plan -> implement -> verify -> /review -> fix all findings -> /battle-test -> commit -> push -> client doc -> mark done. Each task runs in its OWN subagent (context isolation, token-cheap); the…
A release workflow for building and archiving iOS apps, then sending them to App Store Connect, Apple's service for managing App Store releases and review.
Access Wise (TransferWise) accounts to check balances, view recipients, and get quotes. For transaction history, use the archived CSV files. Use when the user asks about Wise balances, transactions, payments, or money transfers.
Create new skills, modify and 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, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Use when you need to send a message to another Claude Code agent, broadcast to all agents, or when you receive a message prefixed with [@agentName]. Covers terminal injection via TIOCSTI, pts discovery, message format, and kill switch.
Capture an idea as an atomic, self-contained note in your own words, link it to related notes, and store it in MemPalace so it resurfaces fast later. Use when the user wants to add a thought/idea/insight as a Zettelkasten note, reformulate notes atomically, or build a linked knowledge base.
★not rated 2 26d agoA79 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: