Loading...
Loading...
Found 29 Skills
Generate a test suite of natural-language → SQL pairs that becomes the quality benchmark for a nao agent, then run it via `nao test`. Use when the user wants to start measuring agent reliability, extend an existing test suite, or add tests for new metrics. Tests are the only honest answer to "is the context working?". Do not use for writing rules (write-context-rules) or diagnosing failures (audit-context).
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
Best practices for prompt engineering and context engineering for Coding Agent prompts
Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.
Write, slim, or audit a repository's agent instruction file — AGENTS.md, CLAUDE.md, or similar. Use when creating one for a repo that lacks it, when an existing one has grown bloated, stale, or contradictory, or when reviewing one for wrong commands and dead references. Covers what earns a place in always-on context and what belongs behind progressive disclosure.