cross-harness-skill-authoring
Use when creating, reviewing, or modernizing one agent skill that must work in both Claude Code and Codex, especially when reconciling current GPT-5.6-series…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,709 results
gpt6-prompting-guide
Write, review, debug, or migrate prompts, tool descriptions, skills, and AGENTS.md for GPT-6 Astra or GPT-6.1 Sol, including migration from legacy GPT-6 Sol or…
handoff-prompt-writer
Use when the user wants a successor-ready handoff prompt, continuation prompt, next-agent prompt, session transfer file, or asks to package current work so…
reviewing-english-prompts
Use when a user wants an English task prompt reviewed or quietly coached while the requested work continues, especially for software engineering, AI research,…
workspace-handoff-compiler
Use when a work session is ending and a successor agent must continue it, or when the user asks for a handoff, context pack, session handoff, "continue across…
review-and-ship
Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
skill-publish-verify
Pre-publish black-box verification. Isolated venv + paths, the agent reads SKILL.md as a new user and uses the skill under test on its own, collects run_record and artifact facts, then the agent writes a usability report. Any skill with a SKILL.md can be run through this once before publishing. Use this skill when the user mentions "pre-publish verification" or "skill black-box verification".
agent-media
Use Agent Media as one composable media toolbox: upload and inspect reference images, generate or edit images, build storyboards and frames, generate video and…
Agent-Media UGC Playbook
Playbook for Agent-Media UGC Video — the one tool for UGC video on agent-media. Always call the single make_ugc skill: give it a `script` (any length) and…
antigravity-sdk-java
Guidelines, API reference, patterns, and best practices for building, configuring, hosting, and executing AI agents in Java using the Antigravity SDK for Java…
lab-homework
Use when the user wants a practice assignment between Claude Code Lab meetings — a concrete task tied to a specific lab meeting, that combines their personal…
lab-review
Use when the user wants a coaching-style review of a Claude Code session — either the current live session, the most recent one, or a specific session by ID.…
flow-next-capture
Synthesize the current conversation context into a flow-next spec at `.flow/specs/<spec-id>.md` via `flowctl spec create + spec set-plan` — agent-native,…
flow-next-export-context
Export RepoPrompt context for external LLM review (ChatGPT, Claude web, etc.). Use when you want to review code or plans with an external model. Triggers on…
flow-next-prime
Comprehensive codebase assessment for agent and production readiness. Scans 8 pillars (48 criteria), verifies commands work, checks GitHub settings. Reports…
flow-next-rp-explorer
Token-efficient codebase exploration using RepoPrompt CLI. Use when user says "use rp to..." or "use repoprompt to..." followed by explore, find, understand,…
flow-next-setup
Optional local install of flowctl CLI and CLAUDE.md/AGENTS.md instructions. Use when user runs /flow-next:setup.
flow-next-resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch per-thread resolver agents, validate, commit, reply + resolve via GraphQL. Triggers on…
decision-tree-helper
Decision tree architect, assisting users in designing and producing ready-to-use decision tree prompts (guard clause format) for skills. When to use: (1) when "decision tree", "conditional logic", "branch judgment", or "guard clause" is mentioned, (2) when describing the desire for a skill to do different things depending on different situations. Not applicable: general prompt writing, tasks not involving branching logic, general-purpose skills...
sam-a2a-bridge
Use when the task should be delegated to a remote A2A agent on the SAM agent mesh: send it work with send_agent_task (with text, structured data, or file…
operator
Google Cloud (GCP) assistant and operator via the autocloud ask_cloud_operator MCP tool. Use for any GCP request: how-to/why, gcloud or Terraform syntax,…
ge-demo-generator
Synthesizes and deploys complete, domain-specific Gemini Enterprise demo environments directly to Google Cloud. Use when the user asks to create an AI agent…
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant…
create-chatgpt-video-ad
Produce a 9:16 social-native ad that recreates a ChatGPT mobile chat — user types in the composer with the iOS keyboard visible, taps send, keyboard slides…