"Did you tell it to do X?" Why writing agent skills pays off forever
jmschreiber91 · x · 2026-11-20
The author argues that many complaints like "the agent doesn't even know to do X" boil down to nobody having told it to. Brain-dumping your tacit knowledge into skills is slow and iterative, but the payoff compounds.
He sorts skills into three broad categories:
- Preferences: aesthetics, file system organization
- How-to: ways of working, e.g. how he develops open source software
- Workflows: full pipelines like downloading a paper and reproducing all analyses, or designing and validating DNA
Key takeaway: poor agent performance is often a missing-context problem, and time spent writing skills keeps paying off indefinitely.
Related event: Developers tout heavy investment in agent skills to capture tacit knowledge(4 posts)→
More from coding & agent
- DeepSeek V4.1 Flash pushed from broken to 284+ t/s on RTX PRO 6000, +78.7% over vLLM — SergioPaniego · 2026-11-20
- GTE-MLM sparse embedding models now natively supported in Transformers v5 — tomaarsen · 2026-11-20
- After evaluating Forge for MTG, researcher writes his own engine for RL agents — petrusenko_max · 2026-11-20
- Spring ecosystem ships 127 open-source releases in one day, led by Spring AI 2.1.0 — therealdanvega · 2026-11-20
- How to keep your Claude account from getting banned, according to one user's setup — huangyun_122 · 2026-11-20
- Study: AI agents barely learn social norms and rely mainly on being punished themselves — ghadfield · 2026-11-20