Every's new skill "Is This Anything" turns your unfinished AI experiments into lessons
every · x · 2026-09-29
Katie Parrott built a skill called Is This Anything? that helps extract useful lessons from an AI experiment—even one you never finished.
It reconstructs what you tried, what you rejected and what changed your understanding, looking for up to three transferable lessons. Crucially, it separates three claim types: Observed (what the session shows), Inferred (what the AI thinks results might mean) and Untested (possible benefits not yet demonstrated), then recommends an action: apply a lesson, run a small test, save for later, or stop.
Usage: give your assistant the skill, the conversation to review and your current priorities, then ask "Is this anything?"
More from coding & agent
- Anthropic ships Claude Sonnet 5.5: 30% faster, up to 30% cheaper for most workloads — ClaudeDevs · 2026-09-29
- Stripe's Kaliski: we're asking our users' AI agents for integration feedback — hazelcough · 2026-09-29
- Last pass with Opus: model handles the final edit and even designs a custom-font ending animation — techhalla · 2026-09-29
- Creator finishes an ad in 2 hours using Opus 5.5 plus Magnific MCP, sharing the full workflow and prompts — techhalla · 2026-09-29
- LangChain Podcast: Prefect Team on the New MCP Spec, FastMCP, Jev and Evals — LangChain · 2026-09-29
- Dev builds quick game playtest entirely with Opus 5.5, claims near-AA quality — majidmanzarpour · 2026-09-29