ExecCritic separates test writing from repair and freezes qualified tests before code changes. On SWE-bench Verified, weak generated tests hurt resolution, while separately trained roles reached 72.6%.FEED7 SUMMARY
Database tools safe for supervised development can be destructive at runtime. Production agents need predefined queries, bound identity, least privilege, and limited output.FEED7 SUMMARY
LinkedIn scales a large internal agent catalog through search, schema lookup, and execution rather than exposing every tool at once. Its playbooks add task-specific operating knowledge.FEED7 SUMMARY
AI SDK now runs GitHub Copilot behind the same HarnessAgent interface as nine other coding harnesses, using an official adapter and ACP connection.FEED7 SUMMARY
A cross-agent skill registry adds scanning, integrity checks, and auditable installs for teams that want reusable coding-agent workflows without blindly trusting marketplace packages.FEED7 SUMMARY
agent#skills
Trending today
What to Ignore This Week
How a researcher uses Codex and ChatGPT to search for new antimicrobial molecules. The use case lacks workflow, dataset, evaluation, and validation details, leaving no reproducible practice for the next agent session.
# feed7 Weekly #010 — Context
Use this for: preparing an agent-workflow planning session
- ExecCritic: Learn to Test, Test to Improve for Coding Agents (arXiv, needs review)
- Build-Time vs. Run-Time: Why Dev Tools Fail in Production — Averi Kitsch & Prerna Kakkar, Google (AI Engineer, source linked)
- 500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedIn (AI Engineer, source linked)