sourcegraph

Archive old completed benchmark runs to save disk space and speed up scans. Triggers on archive runs, clean up runs, disk space, old runs.

Audit benchmark suites against ABC framework (Task/Outcome/Reporting validity). Checks instruction quality, verifier correctness, reproducibility. Triggers on benchmark audit, audit benchmark, abc audit, task validity.

Verify infrastructure readiness before launching benchmark runs — tokens, Docker, disk, credentials. Triggers on check infra, infrastructure check, ready to run, pre-run check.

Compare benchmark results across agent configurations (baseline, SG_full). Show where configs diverge. Triggers on compare configs, config comparison, which config wins, MCP impact.

Token and cost analysis per run, suite, and config. Shows most expensive tasks and config cost comparison. Triggers on cost report, how much did it cost, token usage, spending.

Generate the aggregate CSB evaluation report from completed Harbor runs. Triggers on generate report, eval report, ccb report, benchmark report.

Compute information retrieval quality metrics (precision, recall, MRR, nDCG, MAP) comparing file retrieval across baseline and MCP configs against ground truth. Triggers on ir analysis, retrieval metrics, file recall, ground truth, search quality.

Analyze MCP tool usage patterns, reward/time deltas conditioned on MCP adoption, and zero-MCP investigation. Triggers on mcp audit, mcp analysis, mcp impact, tool usage analysis, did mcp help.

Instructions for querying Google BigQuery using the bq command-line tool. Useful for running SQL queries, exploring datasets, and exporting results.

Instructions for using tmux to spawn multiple processes, inspect them, and capture their output. Useful for running servers or long-running tasks in the background.

Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.

Guides Sourcegraph CLI patch, minor, and major releases. Use when preparing release branches, selecting patch commits, running Trivy checks, creating release tags, or managing local/pushed release artifacts.

Writes and revises Sourcegraph pull request titles, descriptions, and single-PR commit messages. Use when creating or updating a pull request, or when preparing a commit that should stand on its own as the eventual PR.