Search skill packs and skills together

Choosing between many skills and agents can delay technical work. This skill maps each task to focused tools using concise catalogs and selection rules.

Creating reliable AI agents requires clear schemas, safe tools, and repeatable review steps. This skill guides agent design, validation, migration, and maintenance for Claude Code workflows.

Designing reliable Claude Code agents is hard without structure. This skill provides templates, validation rules, and examples for agent prompts, triggers, tools, and metadata.

Molecular docking workflows require careful setup, validated inputs, and cautious result interpretation. This skill guides Claude, Codex, and Claude Code through DiffDock setup, docking runs, batch screening, and confidence-score analysis.

Research teams struggle to turn technical papers into traceable Chinese patent drafts. This skill structures evidence, claims, figures, formulas, and DOCX deliverables for expert review.

Product teams often mistake symptoms for root causes and spread resources across weak priorities. This skill identifies the main blocker and recommends measurable next actions.

Building reusable AI skills is hard when structure, resources, and validation rules are unclear. This skill provides a practical workflow for designing, writing, validating, and packaging skills.

Creating Claude Code plugins requires correct structure, validation, documentation, and safe packaging. This skill guides users through plugin architecture, templates, validation, and publishing workflows.

Long AI sessions can lose goals, decisions, and progress. This skill guides Claude, Codex, and Claude Code to store plans, findings, and logs in project files.

Weak prompts create inconsistent model outputs and slow AI feature development. This skill helps structure prompts, examples, constraints, and output formats for Claude, Codex, and Claude Code.

Claude Code components can be technically valid yet unclear, over-permissioned, or difficult to invoke. This skill scores five quality dimensions and recommends specific improvements.

Structured canister data is difficult for intelligence agents to query safely. This skill adds OQL entities, schema discovery, query execution, relationships, and per-entity authorization.