Agent skills for OpenAI Agents SDK

Sign in to the wallet. Use when you or the user want to log in, sign in, connect, or set up the wallet, or when any wallet operation fails…

Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access…

Author or repair an instruction layer to the Jidoka standard.

Use when creating, consolidating, editing, testing, or reviewing coding-agent skills, skill packs, orchestration skills, reusable…

Author error tracking alerts that fire when an issue is created, reopened, or starts spiking.

Author useful, low-noise log alerts on services in a PostHog project.

Use when adding a plugin to the marketplace, or when authoring, editing, or re-rendering a scene under scripts/animations/scenes/…

Author dashboard themes. Read this when asked to create, edit, recolor, or restyle the dashboard — change the accent, build a…

How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox.

Integrates the gritty, psychological 'Authority' persona from Disco Elysium to analyze power dynamics and hierarchy during interactions.

Help with ABAP authorization and IAM (Identity and Access Management) including authorization objects, authorization checks, IAM apps…

Autenticação e autorização na API da Tray.

Autonomous Linear-backlog iteration — ships exactly ONE issue per invocation (preflight → /next specified → /full auto wt → record…

Automates the full social media content production lifecycle from trend discovery to viral copywriting.

Orient before /auto starts. Loads the hypothesis JSON from lib/auto-detect.sh, surfaces one action line, dispatches when ambiguity is…

Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent.

Set up automatic, per-round git commits for a code project so the user's work is committed every round and never lost.

Dispatches OpenSpec for implementation and behavior changes: classifies L0/L1/L2, routes L2 to official skills, and schedules evidence…

Automate Autobound tasks via Rube MCP (Composio).

Search autocomplete and type-ahead suggestion optimization for knowledge bases

Parallel version of the Ralph Loop. Multiple agents process PRD items simultaneously in worktrees. Triggers: "parallel experiments"…