← ClaudeAtlas

unknownslisted

Surface what you do not know before prompting, log deviations during implementation, and verify understanding after. Use before starting in an unfamiliar area, when you cannot describe what you want, when a long-horizon task came back wrong, when a plan needs stress-testing, and before merging a change you have not fully read. Emits HTML artifacts that carry the prompt and the output together.
SamyakJhaveri/loam · ★ 0 · AI & Automation · score 68
Install: claude install-skill SamyakJhaveri/loam
# Finding your unknowns Source: Thariq Shihipar, *A Field Guide to Fable: Finding Your Unknowns* (2026-07-03), and the artifact set at thariqs.github.io/html-effectiveness/unknowns/. The premise: **the map is not the territory.** Your prompts, skills and CLAUDE.md are the map; the codebase and its real constraints are the territory. The gap between them is your *unknowns*, and clarifying them is now the bottleneck: > "Fable is the first model where I find the quality of the work is bottlenecked by my > ability to clarify its unknowns." > "Reducing and planning for your unknowns is *the skill* of agentic coding." ## The precondition — do this first or the rest underperforms > "The most important part of this process is to give Claude context about your starting > point. For example, tell it where you are in your thought process; disclose your > experience with the problem and codebase; and let it work with you like a thought partner." ## The two-sided failure — read before deciding how much to specify > "If you are too specific, Claude will follow your instructions even when a pivot may be > more appropriate. If you are too vague, Claude will often make choices and assumptions > based on industry best practices that may not be a fit for your task." Both directions fail. This is why "write more rules" and "delete all the rules" are equally wrong as blanket policies, here and in `.claude/rules/`. And when a long task comes back wrong, there are **two** remedies, not one