Agent skills for VS Code

Use to convert references to Cell Press author–date style — in-text "(Smith et al., 2021)", an alphabetical reference list by first author…

Use to convert references to NEJM's Vancouver / ICMJE numbered style — numbered in order of appearance, limited author lists then et al…

Analyze authorized videos into original prompt contracts.

Referral and partnership marketing strategist.

Use to monitor, investigate, and prevent abuse within referral programs.

Referral and affiliate program design covering referral loop architecture, incentive design, trigger moment optimization, viral…

Audit and improve a portable skill for contract compliance, triggering, progressive disclosure, script correctness, portability, safety…

Render and refine the system prompt of a nooa agent.

Use this plugin when the user has an existing OpenDesign artifact and wants targeted critique, patching, brand tightening, responsive…

Assesses and refines prompts using evidence-backed techniques.

Stage 2 skill of /arch. Reads the /specify quality profile, refines targets against architectural reality (inventory constraints…

Carefully curated, modern minimal style with elegant serif typography and understated, sophisticated palettes.

Operate Make-It-3D refinement, test rendering, multi-view

Reflect textlint or prh findings from the current conversation in the appropriate shared writing rules or skill-specific writing references.

Manage Reflex application processes: compile to test, run the server in production mode, reload a running app by finding and restarting…

Refresh README files and project documentation so they match the current repository state.

Adversarial claim verification. Before accepting any "it works / it's done / it's fixed" claim, construct the concrete input that would…

Check regulatory feeds now and report what's new since the last check, filtered by your materiality threshold.

Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only

Regenerate .windsurfrules for Windsurf with preserved team directives

Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence…