Productivity & Workflow Agent Skills for Windsurf (legacy)

Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste /orchestrate…

Create an execution-ready PRD and README for an HQ project.

Creates a product requirement doc (PRD) and an implementation plan (IMPL), suitable for a prototype

Start from a detailed product description, and systematically turn that into an implementation specifications.

Create development track with spec and hierarchical plan through interactive Q&A

Adversarial verification of AA-MA plans using 6 independent angles.

Deep expertise in Microsoft Planner (Classic and Premium) and Microsoft To Do via Graph API and Dataverse — create…

Given a UK planning application, work out which material planning considerations are actually engaged and which representation skill(s) to…

Use when writing an implementation plan from an existing PRD markdown, listing files and tests without coding, discussing edge cases…

Orchestrate research and save an implementation-ready plan file through a goal-backed planning loop for large product, UI/UX…

Orchestrates complex coding tasks using persistent, crash-proof markdown files that maintain state across AI sessions.

Manages complex, multi-step agentic tasks using persistent Markdown files to maintain state across AI sessions.

Persistent file-based planning for multi-step AI-agent work.

Play a short, friendly chime over the speakers once the session's work is finished, so the user knows to look back without watching the…

Use when drafting a PLDI author response inside the short February window — triaging reviewer objections about soundness, baselines, and…

Orchestrates an end-to-end product management workflow from feature teardown and prior-art discovery to requirement evaluation, PRD…

Defines lean MVP boundaries, core validation hypotheses, and measurable success criteria within a structured 60-minute framework.

Full PM playbook — triage backlog, prioritize, assign, track, report, escalate.

Archive a done POC out of the active set but keep it as a parity/regression oracle, moving it under .pocs/archive/.

Create a new POC-driven feature file under .pocs/ from any source (a sentence, an issue, a document, a URL).

List every POC in .pocs/ with its phase and gap counts (split by [agent]/[user]).