Real-time player recommendations during fantasy sports drafts for NBA and MLB, combining live game performance with season stats to surface value picks, sleeper candidates, and positional scarcity analysis. Triggers: fantasy draft, player recommendations, draft strategy, fantasy football, fantasy basketball, draft…
Sets up Alchemy (alchemy-run/alchemy, Infrastructure-as-TypeScript) in any codebase — new project scaffold OR add to existing app. Wires Cloudflare/AWS providers, state backend, secrets, and binding types end-to-end with strict secret hygiene. USE THIS SKILL whenever the user mentions "alchemy", "alchemy.run"…
Monitora saúde da conversa ao longo da sessão. ⚠️ TURNO 1: emitir status report ANTES de qualquer resposta, sem exceção. ATIVAR AUTOMATICAMENTE: 1. Turno 1 — OBRIGATÓRIO. 2. A cada 25% de contexto (25%, 50%, 75%). ATIVAR com: /context-status, status?, como está o contexto, quanto contexto resta, saúde da sessão, check…
Codex CLI second-opinion bridge for Claude Code. Wraps both codex exec (prompt-driven) and codex review (diff-driven) under one workflow with shared project-context preamble, filesystem boundary, JSON stream parsing, and a structured findings table. Five modes: review — custom-prompt audit of file/folder plan …
Discipline for reviewing someone else's pull request — the inverse of prod-ready (which is the author's pre-merge gate). Use when the user asks to "review this PR", "look over the diff", "check this change", "give feedback on", or invokes a code-review slash command. Reviews against the linked feature doc / ADRs /…
A process for creating country-specific labour-law compliance guides. It uses NotebookLM, a tool for researching and working with source documents, through a browser connection, then creates a Word document.
Use when a Hermes Kanban worker wants to run an autonomous implementation delegation lane with a 3-tier fallback chain across claudy -> codex (--yolo) -> agyd (agy --dangerously-skip-permissions) -> Hermes direct on quota exhaustion.
Hand work to — or pick up work from — an agent running in another window (Codex pane, other Claude Code session) via agent-bus. Use when the user says "hand this off", "what's the other agent doing", "check the bus", "tell codex about this", "pick up where the other window left off", or when coordinating edits so two…
Understand who the user is — background, resources, constraints, and deep motivations. Produces an ActorProfile that informs all downstream decisions. Use this tactic at the start of any crystallization process to build a model of the user's capabilities, limitations, and intent.
A command-line tool for checking Taiwanese parcel deliveries by tracking number. It supports several Taiwanese courier services and can show current status, pending parcels, and lookup history.
An AI assistant workflow for choosing university applications in China's Gaokao system, the national college entrance examination. It compares scores and rankings with school and major choices while accounting for regional admission rules.
Turn a YouTube URL or a local timestamped transcript into a designed, attributed EPUB reading edition. Auto-detects speakers/channel, cleans timestamps, always credits the original creators, and builds both a clean Markdown book and a book.epub.
Use when committing changes with git — staging files and writing commit messages. Makes the agent keep each commit focused on one logical change and write a clear, conventional message explaining why, instead of dumping unrelated edits into a single vague "update" commit.
Align a design to your real Storybook components instead of reconstructing it. Use when turning a Figma frame into React built from an existing component library (Build mode), or when pulling scrappy exploratory code into line with the library once a direction feels right (Align mode). Triggers include "build this…
Reversibly clean the agent debt that Kempt found — stale sessions, unused skills, stale/duplicate memories, orphan caches — with everything moved to a recycle bin that supports one-command undo. Use when the user asks to clean up their Claude Code / Codex state, free agent context budget, or act on a Kempt report ("清理…
End-to-end Luma event launch: research comparable events in the target city, draft copy that doesn't read like AI slop, create a Private draft via the admin API, fix the startat / duration / capacity traps, and polish theme, font, and cover. Use this whenever the user wants to publish, edit, or shape an event for…
Autonomous iterative improvement loop for any writing or thinking task — thesis frames, book titles, essay angles, product positioning, strategy arguments. Give a problem statement, the agent auto-designs the oracle (scoring dimensions + judge panel), shows it for approval, then iterates one change at a time until…
Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.
Generate and edit diagrams with the mcp-diagram-generator MCP server. Use this skill for new diagrams, existing .drawio/.mmd/.excalidraw edits, network topology, architecture, flowchart, swimlane, sequence, class, ER, and Excalidraw whiteboard work. Always use this skill when the user asks to draw, generate, revise…
Adversarial specification writer. Takes a brief (from grill-me or user) and produces a structured spec.md with YAML frontmatter, requirements, acceptance criteria, and target files. Git-aware pipeline: each run on its own branch, squash-merge on approval.
★not rated 2 1mo agoC58 tokens
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: