Cadre de Prompting Claude 5

1. Task Give the goal + the why, not the steps: "I'm working on [LARGER GOAL] for [WHO IT'S FOR]. They need [WHAT THE OUTPUT ENABLES]. With that in mind: [TASK]." 2. Context "Use everything in this Project first: my about-me doc, instructions, uploaded examples. If it's not there, pull it from my connectors - don't guess." 3. Skill "/[skill-name] - apply it fully." Anything you've explained to Claude twice should become a skill. 4. Effort "This is a [routine / hard / hardest-unsolved] problem. Scope it like it's at the top of your range." 5. Act "When you have enough information to act, act. Weighing a choice? Give a recommendation." 6. Scope "No extra features, refactors, or abstractions. If I'm describing a problem, the deliverable is your assessment." 7. Delegate "Split independent sub-tasks across subagents & keep working. Verify with a fresh-context subagent." 8. Evidence "Before reporting, audit every claim against a real result from this session. Unverified? Say so." 9. Memory "When you learn something about me that will matter next time, tell me at the end." 10. Checkpoint "Pause only for: destructive actions, real scope changes, or input only I can provide. Never end your turn on a promise." 11. Report "Open with the outcome. Complete sentences, no shorthand I never saw. Clear beats short."