8,930 tagged agents, measured the same way as everything else here.
Browse within: LLM 429agentic-ai 277azure 179sdk 178tool-use 177ai-scientists 176reasoning-agent 176reasoning-language-models 176foundry 167agentskills 148agent 147cortex 147cortexai 147snowflake 147
Skill Codex
Use when Codex must directly operate or troubleshoot the installed grok-plugin-codex MCP capability surface, including CLI/model checks, literal prompt runs or continuations, session inspection or export, and known background-job control. Do not use for bounded repository delegation, implementation, review…
Skill Claude CodeCodex
Produce fact-checked academic research drafts using the Aurelius MCP tools. Use whenever the user asks to research a topic, write a paper/literature review/long-form report, generate a LaTeX document, draw an architecture or flowchart diagram, or verify claims and citations against real scholarly sources. Screens the…
Skill Claude CodeCodex
Run many subagents over one list of work without them colliding or each inventing its own idea of the task. Use whenever the user asks to process, extract, audit, translate, review, or convert a set of files, pages, records, tickets or rows and it would go faster with several agents at once. Also use when they say "in…
Skill Claude CodeCodex
A code-review workflow written in Chinese that checks software changes for correctness, security, performance, and maintainability. It also defines a report format for critical issues and suggestions.
Skill Claude Code
Use this skill when the user runs open source DataHub (self-hosted, not Acryl Cloud) and wants to write quality signals, not just read them: raise or resolve incidents on a dataset, or register external assertions with pass/fail results so they appear in the Validations tab. Triggers on: "raise incident on OSS"…
AvalancheAI-labs/agent-wiki-kit
Skill Claude CodeCodex
Compile a raw source (document, URL content, meeting notes, research output) into a wikikit agent wiki — merge-don't-overwrite, log contradictions, maintain cross-references, then lint. Use whenever the user says "add this to the wiki", "ingest this", or drops new source material for a wiki maintained with…
Skill Claude CodeCodex
Use when doing any delegated software work (a fix, feature, chore, or investigation) so it is tracked as a first-class task in dum-e. Create or claim a task, drive it through the lifecycle with a comment on every transition, and stop at manualtesting for the human to approve. Works over MCP tools or the dum-e CLI.
Skill Claude CodeCodex
Ask the human for something only they can give — a credential, a console click, an approval (a blocker), or a decision only they should make (a grill). Use whenever you hit a wall you cannot clear yourself, instead of stalling or asking in chat.
Skill Claude CodeCodex needs its repo
Build accessible UIs using HeroUI v3 components (React + Tailwind CSS v4 + React Aria). Use when creating React interfaces, selecting UI components, implementing forms, navigation, overlays, or data display. Use when installing HeroUI v3, customizing themes, accessing component documentation, building with compound…
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: