Agent skills for Claude Code

Unified timeline of all deadlines from emails, calendar, and vault.

Revenue & Sales engineer — B2B pipeline, deal strategy, pricing proposals, sales playbooks, and enterprise closing.

Uncover customer jobs, pains, and gains in a structured JTBD format.

Have the Claude and GPT partners critique each other's answers across a configurable number of rounds (default 1) before converging on a…

Multi-model adversarial debate where Claude defends positions against external CLI models (Gemini, Codex, Qwen).

Automated covenant compliance monitoring and calculation skill with early warning alerts

Build a structured, clause-referenced "Debt Document Review" of a leveraged debt document — a high-yield bond Offering Memorandum /…

You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools.

Browser automation and inspection for AI agents via WebSocket

When your last `vs_act` returned an unexpected result (NOT_FOUND, no visible state change, suspected silent failure), run this skill with…

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

WHEN users express issues with app behavior, visual appearance, or functionality in the iOS simulator collaborate on fixes with a…

Systematic Godot debugging decision trees for physics, signals, rendering, navigation, and input issues

Establish root cause by combining Datadog telemetry with the Langfuse repo.

Debug production-like issues in this repository with disciplined evidence gathering.

Add purposeful debug logging to improve observability without changing behavior.

Runtime debugging workflow with automated log collection.

Diagnose a persistent or unclear failure by stopping speculative edits, inventorying evidence and failed hypotheses, verifying assumptions…

Diagnose failure modes by systematically investigating traces.

Debug broken Zoom implementations quickly.

Diagnose MATLAB errors and unexpected behavior via MCP eval.