Dev & Coding

Audits a pipeline for bounded decisions that don't need a frontier model and proposes rule / classifier / small-model gates with fail-closed escalation.

Sets up a full QA process — AAA test cases, P0–P4 bug triage, quality-gate metrics, and OWASP security coverage — with one init script.

Turns any Claude Code skills repo into an official plugin marketplace — generating, validating, install-testing, and PR-ing marketplace.json.

Turns Claude into a fluent gh CLI operator for pull requests, issues, workflows and the GitHub API.

Invoke the local OpenAI Codex CLI as a non-interactive sub-agent to generate, refactor, or review code from Claude Code.

Safely diagnose and edit openclaw.json to switch OpenClaw models and repair 401, "no available channel", and thinking-level errors.

Rebuild only the actionable context from a prior Codex CLI session's local rollout files and finish the interrupted work — no `codex resume` needed.

An evidence-driven, falsification-first playbook for tracking down network, streaming and protocol bugs where the obvious cause is usually wrong.

A skill that guides you through configuring and running prompt tests and model comparisons with Promptfoo.

Drives i18next-cli end to end to turn an app full of hardcoded strings into a properly localized, continuously translated one.

Picks the correct semver bump for a change set and synchronizes every version surface in the repo plus the matching GitHub milestone.

An evidence-led skill that diagnoses and fixes slow web pages using real-user Core Web Vitals plus browser performance traces.

Audits and fixes web security, browser compatibility, and code quality using Lighthouse Best Practices as the baseline.

Diagnose and fix LCP, INP, and CLS using real-user CrUX field data plus browser performance traces.

Orchestrates a 2-layer parallel agent hierarchy for large refactors, multi-file migrations, and codebase-wide audits.

Drive a kitty-graphics terminal app headlessly in a pty and produce a recorded video, timeline and checks summary as the deliverable.

Turns approved game design and art direction into a runnable whitebox prototype or production build on the locked target runtime.

A practical CloudWatch reference that generates alarms, Logs Insights queries and dashboards via AWS CLI or boto3.

A reference skill for writing CloudFormation templates, deploying stacks, detecting drift, and troubleshooting failed deployments.

A hands-on DynamoDB reference skill for schema design, queries, indexes, capacity and performance troubleshooting with CLI and boto3 examples.