81,468 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Author zero-fix Design Docs that let a downstream implementation agent ship in one pass with no re-delegation. Target ≥500 lines for non-trivial tasks (correlates with zero post-delegation rework). Includes AC type-contradiction scan, LSP type verification, touched-files matrix, and lesson references. Use proactively…
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Situational awareness across your live Claude Code sessions. Open a fresh window and run /conductor to see what every OTHER running window is doing, what it finished, and what's left — read from each session's own transcript. Use when the user says "sort out my windows", "what are my sessions doing", "summarize my…
Agentic coarse-to-fine blueprint for generating large-scale, explorable, editable 3D open-world scenes from a single open-ended text prompt — derived from Tencent Hunyuan's WorldClaw (arXiv 2608.05248, Guo/Li/Li/Huang, 2026). Use whenever a project needs to generate a whole 3D world / open-world scene / large terrain…
Devil's advocate, red team, pre-mortem analysis. Assumes every plan has a fatal flaw and finds it. Invoke after forming a plan, before committing to a decision, or when something feels too good to be true.
Cross-project session management hub for Claude Code. Use this skill when the user wants to manage conversations across different projects and directories. Trigger on /recall command or these specific phrases: "/recall", "/recall save", "/recall list", "/recall load", "/recall resume", "/recall rename", "/recall…
Persist and recall per-workspace long-term memory in an Obsidian vault, organized by workspace (one folder per git repo). Use this skill at the START of working in any project to load what was previously learned there, and WHENEVER you make an architecture/design/tooling decision, settle a convention, hit and resolve…
Use the authenticated Cloister Host MCP bridge to discover and run macOS tools under the Profile's allowlist or on-demand policy. Prefer Guest tools; use Host execution for macOS capabilities or a required tool missing in the Guest. Do not use for reading, writing, listing, or patching files in the selected shared…
Produce an audit-aware, agent-executable master plan (PLAN.mdx) before application code is written. One command runs discovery, forces hard-to-reverse decisions, and plans product, business (pricing, entitlements, billing, metrics, feedback), architecture, roadmap, stack, repo, build, deploy, observability, launch…
Skill for managing model provider priorities with authentication (OAuth/Subscription/API), usage limits, and automatic fallback across all major AI providers.
Authorized software reverse engineering, binary analysis, and program comprehension for legitimate purposes including security review, interoperability, migration, modernization, debugging, and documentation. USE WHEN: user needs to analyze software they own or have explicit authorization to inspect, including legacy…
Iterative plan review with Codex, Grok, Gemini/Antigravity, or all (council). Trigger phrases: 'get codex to check', 'codex review', 'grok review', 'gemini review', 'agy review', 'what does grok/gemini think', 'ask both', 'ask all three', 'council review', 'second opinion on this plan'. Claude mediates — agrees…
Session control for the FULL opus-rail system (hook-enforced variant). "/opus-rail disable" (or off) pauses every rails injection for this session; "/opus-rail enable" (or on) resumes; "/opus-rail status" reports hook telemetry and mode. Use when the user runs /opus-rail with one of those arguments. This is NOT the…
Checks whether a website is legally covered against the complaints and demand letters sites actually receive: trackers and session recording running without consent, missing privacy or cookie policies, accessibility gaps. Detects the business profile and which countries it sells to, then shows exposure only for the…
Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.
★not rated 2 8mo agoA54 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: