AI Agent Skills

Writes the /goal condition that loops one feature. Sets the feature up first by running new-feature if it doesn't have a spec yet, then produces the goal command to past…

Use the capshelf CLI to manage shared skills, Pi extensions, subagents, settings, and MCP configs across multiple projects from a user-owned data repo.

Adversarial code review of server-side TypeScript for adherence to the kamae principles (discriminated unions, branded types, Result error handling, boundary validation,…

Detect new Claude Code features and upgrade your company's automation. Usage: /upgrade-automation

Business hypothesis validation skill. Validates ideas through 6 phases (origin check, market confirmation, interviews, evaluation, willingness to pay, minimum viable tes…

Generate a native, editable PPTX deck from an outline, notes, or source material with the pptwise CLI. Use when the user asks to create a PPT, deck, presentation, or sli…

WordPress REST API review and development guidance. Use when reviewing custom REST routes, permission_callback logic, schema design, WP_REST_Request handling, response s…

WordPress theme code review and block theme development patterns for WordPress 6.6+. Use when reviewing theme code, auditing theme.json schema, checking template hierarc…

Conduct accessibility audits against WCAG 2.2 guidelines. Evaluate pages, components, and flows for conformance at A, AA, and AAA levels. Identify issues, assess severit…

Plan, conduct, and analyze UX research using proven methodologies. Use when planning user research, writing interview scripts, creating test plans, recruiting participan…

Repurpose existing content into a native Instagram post. Take a LinkedIn, blog, YouTube script, or X tweet or thread and rebuild it for Instagram: a long piece becomes a…

This description is intentionally verbose to trip the skill budget check in tests. It rambles about everything the skill could conceivably do, in great detail, repeating…

Scaffolds a new mobile app for your project.

Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.

Convex backend specialist. Use this agent for any code inside a `convex/` directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints…

Safe background script execution patterns including automated execution via sys_trigger, fix script generation, error handling, and logging best practices