prompt-engineering

Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design

Quality

73%

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 ./skills/prompt-engineering/SKILL.md

Quality

Content

87%

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

The body is concise, actionable, and well-organized with strong executable examples across prompt-engineering patterns. Its only gap is the absence of a sequenced workflow with validation checkpoints, which is only marginally applicable to a reference-style skill.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: each section is an executable example plus a single guidance line, with no padding or explanation of concepts Claude already knows; every token earns its place.	3 / 3
Actionability	Provides fully executable, copy-paste-ready code and JSON examples (system prompt, CoT, few-shot, tool schema, template function) with concrete, specific guidance throughout.	3 / 3
Workflow Clarity	The body is a pattern catalog with a checklist rather than a sequenced multi-step workflow; no explicit validation checkpoints or feedback loops are present, so it sits at the anchor-2 level.	2 / 3
Progressive Disclosure	A single-file skill with well-organized sections and clear navigation (headings, anti-patterns, checklist); no bundle files exist and no broken references, so the simple-skill path applies.	3 / 3
	Total	11 / 12 Passed

Description

60%

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 specific about capabilities but omits any 'when to use' guidance, so it only answers half of what a skill description should. Adding an explicit 'Use when...' trigger clause would lift completeness and distinctiveness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when designing or refining LLM prompts, structuring system prompts, or improving prompt reliability.'

Broaden natural-language trigger terms users would actually say (e.g. 'prompts', 'prompting', 'system prompts', 'prompt templates') to improve trigger coverage.

Tie the named patterns to concrete user goals (e.g. 'when you need deterministic output format or multi-step reasoning') to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities — 'structured prompts, chain-of-thought, few-shot learning, and system prompt design' — each a distinct, specific action rather than vague language.	3 / 3
Completeness	Clearly answers 'what' (lists the patterns) but provides no 'when' guidance — there is no 'Use when...' clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some relevant terms users might say ('prompt engineering', 'chain-of-thought', 'few-shot', 'system prompt') but lacks common phrasings and an explicit trigger clause; not the anchor-3 level of full natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	The prompt-engineering niche is somewhat specific, but with no explicit trigger terms the skill could still overlap with general coding or writing skills; not yet a clearly distinct, conflict-free niche.	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: rohitg00/awesome-claude-code-toolkit
Path: skills/prompt-engineering/SKILL.md
Commit: ebdf1d5

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.