task-prompts
73Skill Claude CodeCodex
Write grounded task and delegation prompts for coding agents.
Skill Claude CodeCodex
Write grounded task and delegation prompts for coding agents.
Skill Claude CodeCodex
Build browser UIs with HTML, CSS, JavaScript, and Tailwind.
Skill Claude CodeCodex
Check CLI and ADC logins across providers: expiry, scopes, re-login commands.
Skill Claude CodeCodex
Search, read, and update Brain Framework brains (bf): project notes, decisions, actions, and collected mail, calendar, Git, chat, and agent-session records.
Skill Claude CodeCodex
Copy the last requested output to the system clipboard.
Skill Claude CodeCodex
Review code security; scan secrets and vulnerabilities with Gitleaks and Trivy.
Skill Claude CodeCodex
Delegate task batches to agy or another harness on explicit request.
Skill Claude CodeCodex
Draft Gmail emails and replies in the recipient's language; never send.
Skill Claude CodeCodex
Fact-check articles and posts: claims, lychee link checks, primary sources.
Skill Claude CodeCodex
Save and copy a continuation prompt before /clear or switching harnesses.
Skill Claude CodeCodex
Smoke-test every repo task and CLI command; warnings count as failures.
Skill Claude CodeCodex
Shorten docs, prompts, skills, or configs without losing meaning or behavior.
Skill Claude CodeCodex
Red-team AI apps with PyRIT: prompt injection and tool misuse.
Skill Claude CodeCodex
Run product discovery, PRDs, launches, and learning; decide build or stop.
Skill Claude CodeCodex
Design AI app system prompts: instructions, context, tools, and output contracts.
Plugin Claude Code
Bundles 1 skill · 44 tokens together
Maintain shared subagent instructions and generate native coding-tool configurations.
Plugin Gemini CLI
Maintain shared subagent instructions and generate native coding-tool configurations.
Hook Claude Code
One of 5 in hooks.json
Runs when the agent sends a notification for permission_prompt tool calls, running dot agent hook notify grok needs-input. From fmind/dotfiles.
Hook Claude Code
One of 5 in hooks.json
Runs before the context is compacted, running dot agent hook session grok. From fmind/dotfiles.
Hook Claude Code
One of 5 in hooks.json
Runs when a session ends, running dot agent hook session grok. From fmind/dotfiles.
Hook Claude Code
One of 5 in hooks.json
Runs when the agent finishes a response, running dot agent hook session grok (2 commands). From fmind/dotfiles.
Hook Claude Code
One of 5 in hooks.json
Runs when a subagent finishes, running dot agent hook session grok. From fmind/dotfiles.
Skill Claude CodeCodex
Evaluate stochastic LLM/RAG/model/retrieval/tool agents in trials. Compare baseline/candidate on development/sealed holdouts with calibrated deterministic/model/trace graders; measure reliability, variance, leakage, safety, and cost.
Skill Claude CodeCodex
Configure MCP servers for Antigravity, Codex, OpenCode, Claude, and Copilot using stdio or remote transport at workspace or user scope, with source review and safe secret handling.
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: