prompt-engineering
User request: $ARGUMENTS
Create, update, or review an LLM prompt. Prompts act as manifests: clear goal, clear constraints, freedom in execution.
If no request provided: Ask the user whether they want to create a new prompt, update an existing one, or review prompt structure.
If creating: Discover goal, constraints, and structure through targeted questions, then draft against the canonical template.
If updating: Read the existing prompt, identify issues against principles, make targeted high-signal fixes only.
If reviewing: Read the prompt, scan against the canonical template, cross-cutting principles, and anti-patterns. Report issues without modifying the file. For deeper structural audit, delegate to /review-prompt.
Modifier — when the prompt is an agent: Declare every required tool in frontmatter — agents run isolated and don't inherit tools (see Agents specialization below). Applies on top of the create or update branch.
If diagnosing a failing prompt: Load references/metaprompting.md and follow its pre-flight check ("when metaprompting is the wrong tool") before the diagnose-from-failures → surgical-revision workflow.
Before writing — discover context
Missing domain knowledge creates ambiguous prompts. You can't surface latent requirements you don't understand. Surface these before drafting:
More from doodledood/manifest-dev
define
Manifest builder. Plan work, scope tasks, spec out requirements, break down complex tasks before implementation. Converts needs into Deliverables + Invariants with verification criteria. Use when planning features, debugging complex issues, scoping refactors, or whenever a task needs structured thinking before coding.
15do
Manifest executor. Iterates through Deliverables satisfying Acceptance Criteria, then verifies all ACs and Global Invariants pass. Optional --mode efficient|balanced|thorough controls verification intensity (default: thorough). Only pass --mode when the user explicitly requests a different mode. Use when executing a manifest, running a plan, implementing a defined task.
15review-prompt
Review and analyze LLM prompts against prompt-engineering principles. Provides detailed assessment without modifying files.
1auto-optimize-prompt
Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill. Runs until converged.
1