Productivity & Workflow Agent Skills for DeepSeek Harness

Apply during planned rewrites and migrations with explicit phase boundaries.

Automate Outlook Calendar tasks via Rube MCP (Composio): create events, manage attendees, find meeting times, and handle invitations.

Build a practical meeting prep brief from an Outlook Calendar event and its nearby Microsoft context.

Prevent placeholders, truncated code, and half-finished agent outputs.

Structure Agent outputs to minimize human cognitive load.

This skill should be used when converting deprecated Claude Code output styles (.md files) into the new plugin format.

Configure and understand different output formatting styles for Claude Code responses.

Use when you need an independent second opinion before, during, or after implementation — run challenge, consult, or review mode in a…

Writing effective prompts for OutSystems Mentor (the AI that generates and modifies real OutSystems apps) and driving the mentor_start MCP…

Build, normalize, and audit engineering P2P cabling workbooks from an equipment list, BOM, port plan, and optional rack coordinates.

Simulates the stoic and gritty inner voice from Disco Elysium to help you endure hardships and push through obstacles.

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading.

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.

Apply when tempted to ask 'should I do X?' on reversible work.

Apply poteto's rigorous engineering workflow to non-trivial coding, investigation, review, migration, and verification tasks.

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

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

Apply when sequencing an addition, refactor, or rewrite.