Productivity & Workflow Agent Skills for Windsurf (legacy)

Draft, audit, or revise Nature-style revision correspondence packages: point-by-point reviewer-separated response letters, rebuttal…

No-code automation democratizes workflow building.

Runs a disciplined Discuss -> Map -> Decompose -> Execute -> Verify loop that grounds code in verified structure — no invented APIs, no…

Automate Zoho tasks via Rube MCP (Composio).

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy…

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Read PDFs in a Zotero collection and create, update, or verify structured reading notes through the Zotero Web API.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.

Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or…

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes…

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.

Configure which models pstack uses per role.

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).

Fan out N parallel workers, drain them, and return one report.

Use when work may depend on prior user preferences, repo-specific constraints, earlier decisions, verified procedures, recurring caveats…

Searches, reads, and legally downloads academic paper PDFs by title or DOI using adaptive browser routing and open access channels.

Search literature across sources, verify or manage citations, and build MeSH strategies or citation-impact audits.

Claude cannot see your screen — this gives it eyes.

Expert legal advisor specializing in technology law, compliance, and risk mitigation.

Generate tailored AI agent instruction files via AgentRC instructions command.