Menu
SkillsMP a collecté 30 skills depuis sourcegraph/CodeScaleBench. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 30 skills collectés sur 30.
Archive old completed benchmark runs to save disk space and speed up scans. Triggers on archive runs, clean up runs, disk space, old runs.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Verify infrastructure readiness before launching benchmark runs — tokens, Docker, disk, credentials. Triggers on check infra, infrastructure check, ready to run, pre-run check.
Langue du texte source : anglais
Compare benchmark results across agent configurations (baseline, SG_full). Show where configs diverge. Triggers on compare configs, config comparison, which config wins, MCP impact.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Generate the aggregate CSB evaluation report from completed Harbor runs. Triggers on generate report, eval report, ccb report, benchmark report.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Point at any repo (GitHub, GitLab, Bitbucket, Azure DevOps, self-hosted, or local) and get eval tasks that compare baseline coding agents vs MCP-augmented agents. Mines merged PRs/MRs for real code-change tasks, auto-generates ground truth from patches,…
Langue du texte source : anglais
Run a single benchmark task locally to verify a fix. Uses haiku for speed. Triggers on quick rerun, rerun task, verify fix, test task.
Langue du texte source : anglais
Batch re-extract task_metrics.json for all runs after extraction bug fixes or schema changes. Triggers on reextract metrics, refresh metrics, update task metrics, fix extraction.
Langue du texte source : anglais
Run the repo health gate before commit or push to reduce doc drift and keep branches clean. Triggers on commit, push, before push, repo health, reduce drift, doc drift, clean branch.
Langue du texte source : anglais
Configure and launch CodeScaleBench runs with current paired-run and curation guardrails.
Langue du texte source : anglais
Quick status check on the currently active benchmark run. Lighter than watch-benchmarks, scoped to recent activity. Triggers on run status, how's it going, are tasks done, active run.
Langue du texte source : anglais
Scaffold a new Harbor-compatible benchmark task (SDLC or org-scale) and optionally a new benchmark suite. Generates task.toml, instruction.md, Dockerfile, test.sh, and registers the task. Triggers on scaffold task, new task, create task, add task, new…
Langue du texte source : anglais
Score individual task quality on instruction clarity, verifier quality, and reproducibility. Triggers on score task, task quality, rate tasks, task score.
Langue du texte source : anglais
Reconcile task metadata between selected_benchmark_tasks.json and task.toml files. Finds and fixes drift. Triggers on sync metadata, check metadata, metadata mismatch, reconcile tasks.
Langue du texte source : anglais
Investigate a specific failed benchmark task — read logs, identify root cause, check if known pattern, suggest fix. Triggers on triage, investigate failure, debug task, diagnose failure.
Langue du texte source : anglais
Pre-flight validation of benchmark tasks before launching runs. Catches truncated instructions, metadata mismatches, missing test scripts. Triggers on validate tasks, preflight, pre-flight check, check tasks.
Langue du texte source : anglais
Live benchmark monitoring — scan run directories, classify task status, fingerprint errors, present structured summaries. Triggers on watch benchmarks, benchmark status, run status, monitor runs.
Langue du texte source : anglais
Analyze current benchmark state and recommend what to work on next. Triggers on whats next, what should I do, next steps, prioritize work.
Langue du texte source : anglais
Run repo health checks, validate benchmark tasks, and audit run integrity.
Langue du texte source : anglais
Extract metrics, score traces, and evaluate benchmark task results.
Langue du texte source : anglais
Check infrastructure readiness, manage MCP tools, and audit system dependencies.
Langue du texte source : anglais
Plan upcoming work, analyze coverage gaps, and recommend next steps for benchmarking.
Langue du texte source : anglais
Generate evaluation reports, analyze run costs, and compare configurations.
Langue du texte source : anglais
Launch and manage CodeScaleBench benchmark runs with paired-run guardrails, quick reruns, and execution orchestration.
Langue du texte source : anglais
Create, mine, and validate new benchmark tasks and task suites.
Langue du texte source : anglais
Monitor active runs, check task completion status, and watch benchmark execution progress.
Langue du texte source : anglais
Investigate and triage failed benchmark tasks, analyze root causes, and plan reruns.
Langue du texte source : anglais