Browse Skills

Investigates questions using high-trust primary sources and saves cited findings as a Markdown file. Ideal for researching topics, gathering docs or API facts, and delegating reading legwork.

Plan large, multi-session work efforts as a shared map of investigation tickets, resolving them one at a time until the destination is clear.

Share real-time organizational context with your AI agent — query your context graph, manage records, and receive live insights

Local-first cross-harness memory for AI agents. Syke observes activity, maintains a memex, and gives agents syke ask, memex, and record commands for session continuity.

Builds reusable, specialized AI skills for designing and generating research paper figures from academic literature, with rigorous candidate comparison and optimization.

Compare AI skills side-by-side by running the same task through multiple candidate skills and a baseline, then generating an HTML report to help decide which skill works best.

CTO-level architectural advisor that audits AI-generated code for design soundness, resilience, and state management. Use when making design decisions, reviewing architectures, or ensuring system quality.

Turn a raw product idea into build-ready documentation through expert personas that interrogate and validate every aspect before code is written.

Dispatch multiple AI agents to research a topic in parallel, compile findings, and iteratively explore new discoveries until satisfied.

Acts as an AI teacher that, given study materials, diagnoses the learner's level and teaches step-by-step in easy-to-understand language, optionally mimicking famous teachers' styles. Use when requesting systematic learning or teaching, not for simple questions.

Inspect captured HTTP traffic, WebSocket messages, and Sitemap entries using Caido MCP tools with compact projections, HTTPQL filters, and regex excerpts for safe, evidence-focused security workflows.

Implements the shortest correct code that satisfies a locked PLAN.md, then verifies and updates the checklist. Used after planning and human approval to execute a coding task with minimal scope.