← ClaudeAtlas

prompt-engineeringlisted

Write and debug instruction text on any surface: requests, standing context such as CLAUDE.md, tool and schema descriptions, and prompts written for other model instances.
xobotyi/cc-foundry · ★ 23 · AI & Automation · score 84
Install: claude install-skill xobotyi/cc-foundry
**A model that reasons natively does not need to be taught how to think. It needs to be told what done looks like, and left alone.** Instruction text that explains, encourages, or supervises costs more than it buys — the model already does those things, and your text competes with its own judgment. Prompt text lives on four surfaces, and the same words behave differently on each. A rule that helps in a request can tax every turn for months as persistent context. Identify the surface before writing. ## On encountering a defective prompt Do not read past it. Prompt text that violates these rules is found far more often than it is written — in a skill, a tool description, a standing instruction file, a subagent brief. - **Already editing that file** — fix it, in the same change. - **Not editing that file** — name the defect and the fix, once, in a sentence. Then continue the task you were asked to do. - **Flag what changes behavior**, not what offends taste. A stale fact, a contradiction between two rules, a filter that suppresses recall, a rule the model already follows — these cost output. Wording preferences do not. - **One flag, then proceed.** A task does not become a prompt audit because a prompt was involved. Raising the same class of defect repeatedly in one session costs more attention than the defect does. ## Not a prompt problem Write nothing for these. Each has a fix that prompt text cannot reach, and reaching for words instead is the most common wasted m