Agent skills for OpenAI Agents SDK

Compare two versions of a skill's instructions to detect degradations and complexity increases.

Catch up on a git change before you review it — background on the system it lands in, the idea behind it, a literate diff of the real…

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for…

Use the diffs tool to produce real, shareable diffs (viewer URL, file artifact, or both) instead of manual edit summaries.

Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a new model), run on HF…

Automate Digicert tasks via Rube MCP (Composio).

Digital archiving workflows with AI enrichment, entity extraction, and knowledge graph construction.

This skill should be used for personal operating-system workflows: content creation, voice consistency, relationship lookup, meeting…

Audit multilingual content consistency. Use when: checking language parity, regional compliance, or translation quality.

Configure a brand's regional settings — timezone, languages, currency, compliance regulations (GDPR, CCPA, APPI, LGPD, EU AI Act Article…

AI creative director with recursive self-assessment: 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synectics), 3-axis evaluation…

Automate DigitalOcean tasks via Rube MCP (Composio).

Production-quality Python coding standards for writing clean, maintainable, modern Python code (versions 3.10-3.13).

Prepare for due diligence meetings — management presentations, expert network calls, customer references, and advisor sessions.

Models dilution impact across funding rounds, option pool expansions

Surfaces the parallel domain dimensions implicit in a dense or minimal prompt.

Star schema, snowflake schema, SCD types, and Kimball methodology for analytical data modeling.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that…

Writes high-converting direct-response copy — headlines, hooks, VSLs, landing pages, ads (Meta/Google/TikTok/Native), emails, Instagram…

Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus…

Optional 3-5 direction picker for users who explicitly ask to compare visual directions.