Validates an agent-authored clip plan, snaps cut boundaries to scene cuts and sentence ends, and concatenates the selected ranges into a single edited_source.mp4.
Turns an already-analyzed video into a director/edit plan and a timestamped narration script that passes automated review and validation.
Executes an agent-authored clip plan: validates clip_plan.json, snaps cut boundaries safely, and concatenates the selected ranges into edited_source.mp4.
Generates, annotates, reviews, repairs and validates synthesizable Verilog-2001 RTL behind a strict multi-gate quality pipeline.
Runs one holistic codex review against three focused passes (security, Ecto, LiveView) on the same branch diff, then classifies findings to prove whether the extra passes catch real misses.
Turns text, URLs, code repos and Obsidian vaults into InfraNodus knowledge graphs to surface content gaps, questions and GraphRAG answers.
Operating doctrine for using the `cass` CLI to search past agent session logs and return cited prior prompts, decisions, and failures.
A monthly CFO workflow that pulls bank, payment, payroll and expense data, computes end-of-month cash via transaction sums, forecasts runway, and writes the leadership report.
Pressure-tests an ISO/IEC 42001 AI Management System with six forcing questions before certification or internal audit.
The mandated recipe for reading TMDb movie, TV and people data from a Motoko canister via the `tmdb-client` mops package.
Delegate prototyping, debugging, code review and live web/X research to xAI's Grok CLI from Claude Code, with structured JSON results and multi-turn sessions.
Guides Claude through expert-grade design, configuration, and troubleshooting of Cloudflare One Zero Trust / SASE deployments.
A bridge skill that lets Claude Code delegate prototyping, debugging, code review, and cross-model second opinions to Codex CLI.
A bridge skill that delegates prototyping, debugging, and code review to the Claude Code CLI headlessly with session continuity.
A decision guide for delegating code lookup, small edits, and diff reviews to compressed-output subagents so your Claude Code context lasts far longer.
A battle-tested playbook for containerizing ROS2 workspaces and running robot software stacks with Docker Compose.
A production-grade best-practices skill for camera/LiDAR/depth calibration and building multi-sensor robot perception pipelines.
Configures a robot's onboard computer to launch its full ROS2 stack on boot using systemd services, layered launch files, udev rules and health checks.
Defines the implementation phase of a math-modeling project: Python/MATLAB code, result tables, publication-grade figures, flowcharts and a reproduction manifest, enforced by two independent QA gates.
Applies abstract interpretation with interval, sign, congruence, octagon, and polyhedra domains to infer variable ranges and loop invariants without running the code.