Productivity & Workflow Agent Skills for OpenAI Agents SDK

Use when the user wants to list, create, switch, delete, compare, or inspect config sync profiles.

Use when the user wants to set up config sync for the first time, connect to GitHub, or re-initialize the backup repo.

Connect Codex to any app via the Composio CLI.

Connect Claude to external apps via the Composio CLI.

Enforces minimal, safe code modifications to prevent unnecessary refactoring and protect core project architecture.

Queries comprehensive zodiac profiles and multi-cycle horoscope readings with pay-per-query Alipay A2M protocol integration.

Audits construction contracts and compliance documentation to extract performance milestones, payment conditions, responsibility…

Extracts performance milestones, payment conditions, responsibility boundaries, and evidence gaps from construction contracts and…

Extracts verifiable facts, issue ledgers, responsible parties, and evidence chains from construction daily logs and site records.

Generates structured construction site daily reports and Markdown drafts from site notes, chat logs, photo captions, and team updates.

Audits building construction technical schemes to extract safety hazards, key process control points, compliance verification items, and…

Routes construction scheme tasks intelligently between drafting and audit workflows based on user intent.

How the agent knows what the user is looking at.

Audit token consumption across all loaded components — skills, agents, MCP tools, rules, hooks

Refresh or inspect a structured task checkpoint for a long Codex task before handoff, phase change, resume, or repeated compaction.

Recover missing conversation context after explicit compaction or truncation, or when the user explicitly asks to recover prior work.

Save current work-in-progress context as a git WIP commit — captures all staged and unstaged changes with a timestamped stash message so…

Use when the user returns to a client after days or weeks away, resumes a paused engagement, or moves between concurrent clients…

Keep long-running AI-assisted projects on course across sessions, context compaction, and agent switching.

Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.

Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions