writing
claudeStyle enforcement and AI trope detection for human-consumable prose
6 skills · 3 agents · hooks
Hill-climb a skill, agent, rule, or prompt against its eval suite, and review a climb's claimed gain
Plugin evals from marketplace bendrucker in bendrucker/claude. Commands read from the repo's manifest — today.
evals:hill-climbHill-climb a skill, agent, rule, or CLAUDE.md against its eval suite. Use when changing one to raise an eval score, when building or readying the suite a climb runs on, when judging whether a score change beat noise, or when testing whether an instruction still earns its tokens. - Read - Write - Edi
reviewUse before opening or merging a PR/MR that claims an eval gain, or before accepting a climb, whenever asked whether its gain is real. Reviews the claim, diff, and stored results cold, for noise, drift, leakage, grader edits, and holdout. Dispatch with a PR/MR URL, or a climb log and result paths.
Style enforcement and AI trope detection for human-consumable prose
6 skills · 3 agents · hooks
GitHub Actions monitoring and pull request tooling
5 skills · 1 agent · hooks
Honeycomb CLI and MCP server for observability
6 skills · 1 MCP server
Code review workflows for pull requests and the working diff
5 skills · 1 agent · hooks
Pull request workflows: create, update, babysit CI, and reviewer follow-up
4 skills · hooks
GitLab workflow best practices and glab CLI usage
2 skills · 1 agent · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.