skills.rest
sourcegraph
sourcegraphOFFICIAL
Explore all skills by this author →
Website𝕏@sourcegraphGitHub

whats-next

Analyze benchmark run status and recommend prioritized next actions for AI coding agents.

32|4|Updated Feb 1, 2026
Search Tags:#workflow#debugging#task management#ai agent#prioritization#benchmark
One-click install
npx skills add https://github.com/sourcegraph/CodeScaleBench --skill whats-next-sourcegraph
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whats-next
Source: https://github.com/sourcegraph/CodeScaleBench/tree/main/skills/whats-next
Command: npx skills add https://github.com/sourcegraph/CodeScaleBench --skill whats-next-sourcegraph

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps users understand the current status of benchmark runs and recommends the most impactful next action to take, preventing wasted effort and ensuring progress.

Core Features & Use Cases

  • Status Analysis: Aggregates benchmark run status, identifying missing tasks, ongoing runs, and failures.
  • Prioritization: Ranks issues like missing runs, infrastructure errors, and task failures by impact.
  • Actionable Recommendations: Provides specific commands and steps to resolve identified issues or proceed with analysis.
  • Use Case: After a batch of benchmark tasks completes, use this Skill to see if any failed, if new runs are needed, or if it's time to analyze the results.

Quick Start

Analyze the current benchmark state and recommend what to work on next.

Frequently Asked Questions about whats-next

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prioritize my next coding task after a benchmark run?▼

Missing benchmark runs are prioritized first, followed by infrastructure errors and task failures, ensuring operational workflow progress is optimized by addressing the highest impact issues before proceeding to post-run analysis.

What is the best way to analyze benchmark run status for an AI coding agent?▼

The mechanism works by scoping benchmark execution data to identify missing task runs, infrastructure errors, and task failures, then ranking these issues by impact to provide specific commands for resolution.

How do I manage AI agent workflow tasks when benchmark runs fail?▼

It provides specific commands and steps to resolve identified issues like missing runs or infrastructure errors, allowing you to fix failures methodically and trigger post-run analysis when ready.

When do I need to trigger post-run analysis for benchmark execution?▼

Once the skill identifies that missing runs, infrastructure errors, and task failures are resolved, it triggers post-run analysis to evaluate benchmark results and optimize subsequent coding agent progress.

Does this task prioritization skill work without external dependencies?▼

It requires no external dependencies, relying solely on internal scripts to evaluate benchmark execution status and output actionable recommendations for missing runs, failures, and post-run analysis.

Related Skills

Explore More Software Engineering Skills→
korchasakorchasa

diagnose-benchmark-failure

Diagnose flowai benchmark failures by comparing run artifacts against a failure taxonomy.

Community
Advanced
sourcegraphsourcegraph
32

run-benchmark

Configure and launch CodeScaleBench benchmark runs with paired-run and curation guardrails.

Official
Advanced
1mancompany1mancompany
380

Project Management

Coordinate multi-agent task execution and consolidate results into unified reports.

Official
Intermediate
NVIDIANVIDIA
3.4k

eagle3-review-logs

Analyze EAGLE3 pipeline logs to classify failures and summarize task outcomes.

Official
Advanced