Directional Prompting

Directional Prompting

A two-layer skill for writing prompts, agent directives, skill descriptions, slash commands, and anywhere else an LLM reads instructions. Works the same in **Claude Code** and **OpenAI Codex CLI**.

Same `SKILL.md`, same trigger surface, same outcome. Drop it into `~/.claude/skills/directional-prompting/` and `~/.codex/skills/directional-prompting/` and both agents pick it up natively.

The two layers

**Layer 1 — Outcome.** Every non-trivial prompt opens with a block that names the destination: the goal, what "done" looks like, when to stop, the true invariants. This is the frame.

**Layer 2 — Direction.** Inside that frame, every sentence names the path forward with positive verbs. "Trace", "build", "use", "read", "return", "ask", "check". The correct behavior is described so clearly and completely that the wrong behavior has no room to exist.

Outcome without direction reads as wishful — the model knows where to go but not how to step. Direction without outcome wanders — the model walks crisp paths to nowhere. Both layers together: a model that knows the destination and walks toward it on every token.

Why both labs converge here

Modern frontier models follow instructions literally. The Claude 4.7 guide: *"Positive examples showing how Claude can communicate with the appropriate level of concision tend to be more effective than negative examples or instructions that tell the model what not to do."* The GPT-5.5 guide: *"GPT-5.5 is strongest when the prompt defines the target outcome, success criteria, constraints, and available context, then lets the model choose the path."*

Both labs converge on the same shape. Name the destination. Name the path. Skip the pro