Agent building

Example skill loaded from resources_discover

Save implementation cost by defaulting specification-locked coding to GPT-5.6 Luna max while the current main Codex agent retains specification, integration…

Generate an instrumental music bed via ElevenLabs Music, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent.

Make a repository's agent rulebook (AGENTS.md / CLAUDE.md) verifiable: vendor a deterministic checker, audit every rule and citation against the code…

Generate a private, local "Your Agents, Wrapped" card plus a Grader report from the user's own Claude Code and Codex session logs.

Collect and synthesize opinions from multiple AI agents.

为 AI 长期项目建立「项目记忆 + 文件索引 + 工作规则 + 版本记录」的治理系统，让 AI 在长期项目里「不忘事、不乱改、不重复犯错」，换会话后仍能接着做。Set up and maintain a project governance workspace for AI-assisted…

通过 QMT Bridge 生成当日交易复盘：客观证据（委托/成交/滑点/不操作基线/规则标签）+ Agent 层投顾/基金经理/交易员三角色专家评审与综合裁决。 在用户提到今日成交、交易复盘、今日操作评估、执行质量、三角色复盘、专家复盘、 不操作少赚多亏时使用。只读。

Clean up the local leftovers of finished work in one pass, removing worktrees and local branches whose pull request merged or closed, detached worktrees…

Use when a project has accumulated uncommitted changes and nobody has said so out loud — several edits in a row with no commit in between — or when a subagent…

Use when designing, reviewing, adding, enabling, disabling, installing, configuring, or debugging a plugin, bundle, feature, page, panel, tool, or MCP…

Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent.

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN…

Plan, create, edit, comment on, and triage Linear issues through the Linear MCP server.

Auto-use for context-heavy prompts (logs, CI failures, Kubernetes issues, runbooks, docs lookup, PR triage, codegen subtasks) and bounded Laya/Jev decisions…

Validate a local prompt pack, XLSX template, or EPUB/PDF ebook and produce an offline QA report.

Resolve evidence-backed `docs/follow-ups/*.md` through a bounded manual, Codex Scheduled task, or Claude Routine sweep.

Review this machine's recent Claude Code and Codex session logs for work agents redo by chance every session, and report candidates to hand to a deterministic…

Reviews a calendar month of local Codex sessions and their follow-up tasks to improve agent interactions.

Use when executing a written implementation plan (TSP) whose tasks are independent, in the current session.

Track decisions (AGD) with validation and indexing.

Use when user wants to optimize, improve, benchmark, or evaluate a skill's prompt.

Delegate bounded, independently verifiable coding or validation work to GPT-5.3-Codex-Spark while the main agent retains planning and final judgment.