Dev & Coding

A playbook for using the GitHub CLI gh-stack extension to split multi-part work into reviewable stacked branches and PRs, safely and non-interactively.

A code-first skill for installing, running, and fine-tuning RWKV — the RNN+Transformer hybrid with O(n) inference and constant-memory infinite context.

A decision guide for delegating code lookup, small edits, and diff reviews to compressed-output subagents so your Claude Code context lasts far longer.

Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery that extracts goals, constraints, and project scale before handing off to spec generation.

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.

Internal skill for adding or extending Paperclip Runner protocol eval definitions, rosters, assertions, and report fixtures with strict provenance and narrow validation.

An internal, evidence-driven loop for improving Archify diagram accuracy, readability and authoring speed.

A deep-review protocol that attacks code, APIs, infra and tests for falsifiable defects, then traces and repairs their root cause.

The mandated recipe for reading TMDb movie, TV and people data from a Motoko canister via the `tmdb-client` mops package.

A Claude Code skill that decides when and how to delegate code-location, small edits, and diff reviews to three ultra-compact 'caveman-style' subagents.

Turns evaluated code-review findings into real edits, with hard soundness checks and an escalation path for anything ambiguous.

Drives the Compass CLI's local code knowledge graph so Claude answers architecture, dependency, and change-impact questions with cited evidence.

Guides Claude in creating and training self-improving agents using AgentDB's nine reinforcement learning algorithms.

Practical patterns for giving AI agents session memory, long-term storage, pattern learning and context management with AgentDB and ReasoningBank.

A skill that walks Claude through designing, implementing, and evaluating high-quality MCP servers in Python or TypeScript.

Turns a single GitHub pull request or commit on a Terraform module repo into a full review with a verdict and a ready-to-post comment.

A verified reference for how Claude Code plugin manifests, skills, commands, agents, and hooks actually work, for use while authoring or debugging plugins.

A four-layer project-memory playbook: search GitHub Discussions, the decision journal, and ADRs via verified GraphQL/ripgrep commands before re-investigating anything.

A disciplined workflow for verifying browser user journeys of a running Spring Boot 3 app with the agent-qa CLI, reporting only evidence from real runs.

Scaffolds new process definitions for the babysitter event-sourced orchestration framework following official SDK patterns.