Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires…
Skill Claude Code
A research skill for turning web searches into short reports or deeper, structured investigations. It can deliver the result in chat, Markdown, or HTML when a page-like layout is needed.
Skill Claude CodeCodex
Keep Companion billing money values tied to source of truth: usage markup/credits in billing economics, and subscription plan prices across plan constants, Autumn/Stripe, RevenueCat, and App Store Connect when Apple IAP is in scope. Load when changing CREDITMARKUP, usage credit math, plan prices, top-ups, billing…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.
Skill Claude CodeCodex
Use when starting Phase 1 of the Beam workflow, or when a new repository needs a plan.md before any scaffolding, AGENTS.md, or technical spec work begins.
Skill Claude CodeCodex
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Skill Claude CodeCodex
Use Feishu Base (Bitable) as an AI agent's external brain — task management, execution logs, long-term memory, and code-driven dispatch. Activate when managing tasks, logging findings, storing memories, or running automated task scheduling.
Skill Codex
Audit a SDD Epic end to end against current implementation reality with subagent delegation, mandatory full reverse traceability, systematic Requirement/Scenario testing, Epic coherence review, missing Story/Requirement/Scenario detection, Story label/reference traceability checks, Change-status and evidence drift…
Shanmus4/figma-variables-tokens-generator
Skill Claude CodeCodex
Generate a fully connected design token system instantly from a chat prompt. Supports everything from a simple 1-tier flat architecture, to 2/3-tier systems (Primitives, Semantic with light/dark modes, Component Colors), all the way up to an enterprise 4-tier setup (Primitives, Theme, Semantic, Component Colors +…
Skill Claude Code
Checklist for adding a new public module or sub-package to console-toolkit.
phanbaohuy96/flutter_base_structure
Skill Claude CodeCodex
Builds the data layer with Freezed DTOs, Retrofit clients, the storage-seam local data manager, and repositories wired through injectable.
Skill Codex
Organise uncertain product work into evidence-bearing phases from problem definition through post-release evaluation. Use for a new product, experiment, risky refactor, or feature whose value or feasibility is not yet established. Track hypotheses, prototypes, decisions, implementation readiness, applicable hardening…
Skill Claude CodeCodex
Canonical per-record archive format (YAML front matter + Markdown body).
Skill Claude Code
Manage Zotero library - list collections, list papers, add papers to collections. Requires ZOTEROAPIKEY env var.
Skill Claude Code ✓ vendor
Inspect and drive the PLG "SuggestionGrant" token-gated fix system for a site's opportunities (broken-backlinks, alt-text, cwv) — check which suggestions currently hold a grant, revoke stale ones, and trigger a regrant of the best available suggestion. Use when asked to check/revoke/ regrant suggestion "grants" or…
Skill Claude CodeCodex
Task tracker for LLM sessions. Use "$ba ready" to see available work, "$ba claim " to take ownership, "$ba finish " when done.
Skill Claude CodeCodex
Comprehensive system check for Mastra AI agent projects. Validates configuration, agents, workflows, memory, tools, prompts, and security across 66 rules organized by priority. Use when setting up new projects, debugging issues, reviewing code, or preparing for production deployment.
fermonterom/claude-testing-kit
Skill Claude Code
Unit + E2E testing + quality gate para Next.js con Claude Code. Combina TDD workflow, Vitest patterns, Playwright E2E, validacion de build, env vars, y security check en una sola skill. Se activa al crear/modificar route.ts, page.tsx, o archivos de test. Para cualquier proyecto Next.js con App Router.
Skill Claude CodeCodex
Execute Codex CLI for code analysis, refactoring, and automated code changes. Use when you need to delegate complex code tasks to Codex AI with file references (@syntax) and structured output.
Rito-w/claude-code-best-practice-zh
Skill Claude Code
Instructions for fetching current Dubai time via bash command.
Skill Claude CodeCodex
Expert in agsync, the Git-native CLI that syncs skills, commands, and MCP tools across AI coding agents. You MUST use this skill when working on agent skills, commands, MCP configurations or agsync (agsync.yaml) directly.
Skill Claude CodeCodex
Personal Knowledge Management documentation system based on Zettelkasten principles. Use when documenting conversations, decisions, development work, learnings, or any knowledge that should persist. Triggers on new projects, technical decisions, completed tasks, lessons learned, meeting notes, or when the user says…
Skill Claude CodeCodex
PROHIBITS placeholder code, default values that mask missing data, and silent failures. Enforces fail-fast with loud errors. Use when implementing ANY function or data structure.
jacinthpaul/Claude-Certified-Architect
Skill Claude Code
Map an unfamiliar module's structure and dependencies, returning a summary.
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: