Name: prompt-engineering-patterns
Rating: 38.4 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Quality

36%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/prompt-engineering-patterns/SKILL.md

The canonical home for this skill is prompt-engineering-patterns in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

36%Weight 40%Scale 1-5

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

The body covers broad ground with some executable code and a real bundle, but is padded with generic best-practice truisms, lacks a sequenced workflow with validation checkpoints, and mis-signals its references (including a broken file path).

Suggestions

Trim the generic Best Practices, Common Pitfalls, Success Metrics, and Next Steps sections down to non-obvious guidance or move them into a reference file.

Replace the fictional 'prompt_optimizer' library in Quick Start with real, runnable code (e.g., raw prompt construction or an actual library) so examples are copy-paste executable.

Fix the broken reference (line 23 says 'resources/implementation-playbook.md' but the folder is 'references/') and add inline links from each Core Capability section to its dedicated reference file.

Dimension	Reasoning	Score
Conciseness	Several sections are padded with truisms Claude already knows (Best Practices like 'Be Specific: Vague prompts produce inconsistent results', Common Pitfalls, Success Metrics, Next Steps), matching 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	Concrete code appears (Quick Start, RAG, validation snippets) but it imports a fictional-looking 'prompt_optimizer' API, and large capability sections are abstract bullet lists ('Example selection strategies (semantic similarity, diversity sampling)') — 'some concrete guidance but incomplete'.	3 / 5
Workflow Clarity	The Instructions section is generic ('Clarify goals... Apply relevant best practices and validate outcomes') with no sequenced steps or validation checkpoints; only a loose Level 1-4 progression exists, fitting 'rough sequence present but many gaps; validation absent'.	2 / 5
Progressive Disclosure	A Resources section lists real reference/asset/script files one level deep, but capability sections that have dedicated reference files are not linked inline, and the body references a non-existent 'resources/implementation-playbook.md' (actual dir is 'references/'), so 'some structure but could be better organized; references present but not clearly signaled'.	3 / 5
	Total	10 / 20 Passed

Description

37%Weight 40%Scale 1-5

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 names its domain clearly but relies on abstract benefit language and omits any explicit trigger guidance, leaving it vague on when to invoke and on what concrete actions it performs.

Suggestions

Replace benefit phrasing with concrete actions the skill performs (e.g., 'Design, optimize, and templatize prompts; build few-shot example sets; structure chain-of-thought reasoning').

Add an explicit 'Use when...' clause listing natural trigger phrases such as 'optimize prompts', 'few-shot examples', 'chain-of-thought', 'prompt templates'.

Include natural user-facing synonyms and file/term variants to improve trigger term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('advanced prompt engineering techniques') but the rest is outcome/benefit language ('maximize LLM performance, reliability, and controllability') rather than concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'.	2 / 5
Completeness	It gives a clear 'what' (master advanced prompt engineering techniques) but no 'when' / 'Use when...' trigger guidance, so per the judging guideline completeness is capped at 3 — 'clear what but when is missing'.	3 / 5
Trigger Term Quality	'prompt engineering techniques' and 'LLM performance' are jargon-laden and miss the natural phrases users actually say (e.g., 'write better prompts', 'optimize prompts', 'chain-of-thought', 'few-shot'), fitting 'one or two generic keywords; missing the natural phrases users say'.	2 / 5
Distinctiveness Conflict Risk	'Prompt engineering' is a recognizable niche, but the generic benefit framing ('maximize LLM performance, reliability, and controllability') leaves overlap risk with general LLM-assistance skills, matching 'somewhat specific but could still overlap with similar skills'.	3 / 5
	Total	10 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/prompt-engineering-patterns/SKILL.md
Commit: 57c135b

Reviewed: 2 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.