Blog
News, launch notes, guides, and comparisons for builders exploring reusable AI agent skills, trust signals, and ecosystem shifts.
Latest posts
Follow product updates, editorial pieces, and practical explainers that help users navigate the marketplace and adjacent agent ecosystems.
-
Test agent-written web changes in a real browser and hand failures back for repair with Expect
Run an agent-native browser QA loop that reads recent code changes, generates a test plan, and returns concrete failures for the coding agent to fix.
-
Track coding-agent quota burn and remaining headroom across providers with onWatch
Monitor quota, spend, resets, and alerts across multiple coding-agent providers from one local dashboard before a long run hits throttling or budget limits.
-
Evolve reusable coding-agent skills from failed trajectories with EvoSkill
Mine failed agent runs for reusable skills, benchmark the candidates, and keep only the variants that improve a supported coding agent over your baseline.
-
Run agents in disposable microVM sandboxes with network allowlists and secret injection using Matchlock
Launch risky agent work inside disposable microVMs when you need stronger isolation, sealed egress, and host-side secret injection instead of direct host access.
-
Lint and autofix agent config files before broken prompts, hooks, or MCP settings derail runs with agnix
Validate and optionally autofix SKILL.md, CLAUDE.md, AGENTS.md, hooks, and MCP config files before bad agent metadata or wiring silently breaks a workflow.
-
Generate and evaluate agent skills from traces before shipping them into repeatable production workflows with UPskill
Turn successful traces into reusable skills, then benchmark those skills across models before you trust them in production.
-
Browse search and cost-audit local coding-agent histories before resuming or standardizing workflows with agentsview
Index local coding-agent sessions into a searchable SQLite-backed view so you can inspect usage, compare failures, and recover prior context quickly.
-
Search and resume past coding-agent sessions locally with exact handoff commands using Agent Sessions
Browse archived sessions from multiple coding agents, search across them locally, and copy exact resume commands when you need to re-enter prior work.
-
Automate Lark and Feishu docs, sheets, mail, calendar, meetings, and chat tasks from agents with Lark CLI
Operate Lark and Feishu work objects from one agent-ready CLI instead of stitching together separate APIs and browser flows.
-
Scan agent skill folders for risky patterns and missing safeguards before sharing or deployment with Cisco Skill Scanner
Run a pre-trust security pass over skill packs and prompt bundles before they get shared, merged, or deployed.