agent-prompt-authorlisted

Write, revise, and diagnose system prompts, orchestrator instructions, subagent delegation contracts, tool descriptions, and harness text for LLM agents you build and ship. Use whenever someone wants an agent to behave differently by changing its text — "write a system prompt for X", "improve this orchestrator prompt", "my agent keeps ignoring this rule", "the prompt got worse after I edited it", "add a constraint so it stops doing Y", "write a tool description", "should I run GEPA or DSPy on this", "review this agent prompt", "is this prompt any good", "how much of this is still needed". Also use when a prompt has grown past ~200 lines, when a refinement loop has stopped helping, or before investing in automated prompt optimization. Do NOT use for one-off chat prompts, for CLAUDE.md and repo context files (opposite policy — see Route C), or for brand voice and creative style guides.
amylyra/agent-prompt-author · ★ 0 · AI & Automation · score 70

Install: claude install-skill amylyra/agent-prompt-author

# Agent Prompt Author Prompt work fails for four reasons, in descending order of frequency: 1. **The prompt was never the bottleneck.** Most requests to improve a prompt should end here. 2. **The rule lives in a layer that cannot enforce it.** Prose is a request; hooks are a gate. 3. **Rules written for an older model are still firing.** 4. **The revision loop has no external verifier**, so it optimizes readability instead of behavior. Skipping to "write a better rule" is the default failure mode of this task. ## Precondition **Always name the route.** Routing is done from what the user said and never needs the artifact. **Do not diagnose from description alone.** What needs the artifact is the FINDING. Route D is the one exception — a prompt that does not exist yet has no text to ask for. On every other route, before you produce a finding, get: - The actual artifact text, or the assembled context if the artifact is templated. - One concrete failure — the input, what happened, what should have happened. - For Route E, the previous version too. Regression is invisible without a diff. - **Which model families the artifact must run on.** If more than one, read `references/portability.md` alongside your route — several rules invert. If the user describes a symptom without producing the artifact, name the route, then ask for it once, plainly. A diagnosis built on a description of a prompt is a guess about a class of prompts, not a finding about theirs. ## Route Match t