prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

1.16x

Quality

—

Does it follow best practices?

Impact

85%

1.16x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, actionability-focused catalog of executable prompt-engineering patterns, but it is held back by verbosity in concept restatements, lack of an overarching workflow with validation checkpoints, and a complete failure to use the provided bundle files for progressive disclosure.

Suggestions

Replace the concept-restating "Core Capabilities" bullets with one-line pointers to the matching reference files (e.g. "Chain-of-thought: see references/chain-of-thought.md") to remove content Claude already knows and activate progressive disclosure.

Link each Key Pattern to its supporting bundle file (scripts/optimize-prompt.py, assets/few-shot-examples.json, assets/prompt-template-library.md) so the references, scripts, and assets are no longer orphaned.

Add a short "Workflow" section sequencing how to apply the patterns (select examples -> draft prompt -> enforce structured output -> validate -> iterate) with an explicit validation/checkpoint step.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient code, but the "Core Capabilities" sections restate concepts Claude already knows (e.g. "Zero-shot CoT with 'Let's think step by step'", "JSON mode for reliable parsing") and the ~480-line catalog could be tightened, so it is mostly efficient with some unnecessary explanation.	2 / 3
Actionability	Provides multiple complete, executable code examples (Pydantic schemas, ChatPromptTemplate chains, SemanticSimilarityExampleSelector, prompt-caching calls) that are copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Individual patterns list internal steps (e.g. Pattern 5's fallback flow) but the skill is presented as a flat catalog with no overall sequencing or explicit validation checkpoints tying the patterns into a guided process.	2 / 3
Progressive Disclosure	The skill ships a bundle (5 reference files, scripts/optimize-prompt.py, and 2 assets) but the body never references or signals any of them; all content that belongs in those files is inline, making it a monolithic wall with orphaned references and poor cross-file navigation.	1 / 3
	Total	8 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-formed with an explicit "Use when" trigger clause and a clear domain, earning strong completeness. It is held back by abstract outcome language and incomplete natural trigger coverage that limits specificity and distinctiveness.

Suggestions

Replace the abstract outcome lead ("Master advanced prompt engineering techniques to maximize...") with a concrete action list, e.g. "Designs chain-of-thought and few-shot prompts, enforces structured JSON outputs, and builds reusable prompt templates."

Add natural trigger variations users actually say, such as "chain-of-thought", "few-shot examples", "structured output / JSON mode", and "system prompts".

Sharpen distinctiveness by tying triggers to specifics only this skill owns (e.g. dynamic example selection, prompt caching, A/B testing prompt variants).

Dimension	Reasoning	Score
Specificity	Names the domain and some actions ("optimizing prompts, improving LLM outputs, or designing production prompt templates") but opens with an abstract outcome statement ("Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability") rather than a list of concrete actions, so it is not comprehensive.	2 / 3
Completeness	Explicitly answers both "what" ("Master advanced prompt engineering techniques...") and "when" ("Use when optimizing prompts, improving LLM outputs, or designing production prompt templates"), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Includes relevant natural triggers ("optimizing prompts", "improving LLM outputs") but leans on jargon ("production prompt templates") and omits common variations a user would actually say (chain-of-thought, few-shot, structured output, JSON mode), so coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The prompt-engineering niche is somewhat distinct, but the phrasing is generic enough that it could overlap with general LLM/API coding skills and would not reliably outrival adjacent skills for a given query.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Dicklesworthstone/pi_agent_rust
Commit: e9f9b67

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.