Build and test agent skills
Turn a recurring workflow, prompt, or SOP into an agent skill with a clear job, activation boundaries, decision rules, and evaluation cases. OmniSkill routes each request to the next relevant specialist: architecture, authoring, evaluation, repair, host adaptation, or packaging. More
Skills 16 in the ChatGPT listing
Reuse Existing Tools Search for and leverage existing runtime primitives, standard libraries, repository utilities, and battle-tested ecosystem packages rather than building custom implementations. Workspace Operations Use when Skill Conductor needs to inspect, search, modify, or verify files in the active host workspace using the safest native capability available. Human-centered Decisions Understand human cognitive models, reading patterns, implicit assumptions, and intent formulation. Integrate Existing Code Protocol for adopting a new library, tool, or architectural pattern. Measure Claims Establish hypotheses and measurable verification criteria before implementing changes or diagnosing bugs, and decide strictly based on measured outcomes. OmniSkill Router Route a skill-engineering request to the next useful specialist. Engineering Principles Apply the 24 battle-tested engineering principles for architecture design, refactoring, implementation, bug diagnosis, migration, and verification. Distribute Skills Craft high-presence open-source repositories and configure universal multi-agent distribution manifests, GitHub discovery metadata, and automated installers. Deterministic Verification Use when a Skill Conductor workflow needs deterministic computation, file generation, parsing, package inspection, hashing, or validation that should be actually executed with host-native Python. Set Up OmniSkill Set up OmniSkill after installation or check which skill workflows this host can execute. Design a Skill Architect a new agent Skill or convert an existing prompt, SOP, playbook, runbook, workflow, or repeated agent behavior into a durable Skill. Author a Skill Create, refine, audit, and evaluate Agent Skills according to the AgentSkills.io v1 specification and Poteto principles. Improve and Package Skills Improve an existing agent skill from a reproduced failure, tune its activation wording, or package a validated skill. Evaluate a Skill Evaluate an agent Skill for activation accuracy, instruction compliance, outcome quality, efficiency, pressure resistance, and regression risk. Port a Skill Port an agent Skill across ChatGPT, Codex, Claude, API agents, or another compatible host without losing its decision logic, evidence gates, activation boundary, or completion conditions. Write Clear Instructions Standards and guidelines for drafting high-density, anti-slop technical documentation, PR summaries, commit messages, architectural records, and agent instructions. 