stbenjam

Search and analyze a Calibre library or Goodreads export, including reading lists, series, statistics, and recommendations.

Eliminate everyday friction through direct action, delegation, specialist services, or automation within explicit authorization boundaries.

A Stop hook for Claude Code and Codex that requests one final completion pass, with an opt-in infinite mode.

Autonomous loops that shepherd work to completion, such as driving a PR to a mergeable state

A grab-bag of miscellaneous OpenClaw skills stbenjam uses day to day, with no unifying theme.

Code review with specialist reviewers and runtime reproducers, plus guided eval and benchmark task walkthroughs

Context-specific rules for safe Git operations and rigorous test-failure investigation.

A configurable linter for agent skills, plugins, and AI coding assistant context

Compact conversation-steering skills for changing direction, explaining decisions, asking for clarity, answering questions without implied action, finishing punted work, delegating research to a subagent, tightening prose, executing decisively, rethinking code architecture, and raising frontend quality.