Principal-level prompt engineering — task decomposition, role + context + instructions + examples + output-format structure, few-shot patterns, chain-of-thought, tool-use prompts, evaluation, prompt versioning, and the discipline that separates "works once on the demo" from "production-grade prompt that survives model upgrades". Select explicitly when this guidance applies.
Pro scans all 2 files and shows the line behind each finding
Scanned 10/6/2026
npx -y skills add Nmor/the-council --skill prompt-engineering --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Prompt Engineering?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nmor-prompt-engineering-the-council)More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.
---
name: prompt-engineering
description: Principal-level prompt engineering — task decomposition, role + context + instructions + examples + output-format structure, few-shot patterns, chain-of-thought, tool-use prompts, evaluation, prompt versioning, and the discipline that separates "works once on the demo" from "production-grade prompt that survives model upgrades". Select explicitly when this guidance applies.
disable-model-invocation: true
---
# Prompt Engineering
> **Size budget: 8 KB** — `token-budget.mjs --check`.
Principal-level prompt engineering — task decomposition, role + context + instructions + examples + output-format structure, few-shot patterns, chain-of-thought, tool-use prompts, evaluation, prompt versioning, and the discipline that separates "works once on the demo" from "production-grade prompt that survives model upgrades". Select explicitly when this guidance applies.
## Working procedure
1. Establish the relevant mode and existing evidence; do not repeat completed intake.
2. Define the requested scope, baseline, success criteria and evidence before choosing a procedure. Verify current external requirements from primary sources. Distinguish observed facts from hypotheses and implemented controls from tested outcomes. Preserve user authorization, sensitive data, rollback options and the existing plan.
3. Read only the corresponding sections below before applying their examples.
4. Verify the result with meaningful positive, negative and failure controls. Record actual outcomes, limitations and next action.
## Selected references
- [Purpose](references/procedure.md#purpose) — read when this part of the task applies.
- [Standards Cited](references/procedure.md#standards-cited) — read when this part of the task applies.
- [When to Fire](references/procedure.md#when-to-fire) — read when this part of the task applies.
- [Core Patterns](references/procedure.md#core-patterns) — read when this part of the task applies.
- [Anti-Patterns](references/procedure.md#anti-patterns) — read when this part of the task applies.
- [Verification Checklist](references/procedure.md#verification-checklist) — read when this part of the task applies.
- [Cross-References](references/procedure.md#cross-references) — read when this part of the task applies.
- [Why This Skill Exists](references/procedure.md#why-this-skill-exists) — read when this part of the task applies.
- [Learning hooks](references/procedure.md#learning-hooks) — read when this part of the task applies.
The [full procedure](references/procedure.md) preserves detailed examples and standards.
Load relevant excerpts rather than the entire reference. Runtime capabilities and higher-priority instructions govern imported templates.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!