humanitys-last-prompt-engineer
This skill should be used when the user asks to "write a prompt", "improve my prompt", "fix this prompt", "optimize a prompt", "learn prompting techniques", "get prompt templates", or mentions prompt engineering, prompt quality, or prompt rewriting. Applies 11 foundational techniques from Forward Future's guide.
88
87%
Does it follow best practices?
Impact
82%
1.09xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 excels at trigger term coverage and completeness, providing extensive natural language phrases that would help Claude select this skill appropriately. Its main weakness is that it leans heavily on listing trigger phrases rather than describing the concrete capabilities and outputs of the skill—it tells you when to use it more than what it actually does. Specifying what the 11 techniques are or what outputs the skill produces would strengthen specificity.
Suggestions
Add concrete capability descriptions such as 'Rewrites vague prompts into structured, effective prompts using techniques like chain-of-thought, role assignment, and few-shot examples' instead of just referencing '11 foundational techniques'.
Briefly enumerate or categorize the key techniques so Claude understands the skill's actual outputs and methods, not just its trigger conditions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'write', 'improve', 'fix', 'optimize', 'learn prompting techniques', and 'get prompt templates' as actions, but these are mostly listed as trigger phrases rather than concrete capabilities the skill performs. It references '11 foundational techniques from Forward Future's guide' but doesn't specify what those techniques actually do. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (applies 11 foundational techniques from Forward Future's guide for prompt writing/improvement) and 'when' (detailed trigger phrases and use cases are clearly listed). The 'Use when' equivalent is thoroughly covered. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'write a prompt', 'improve my prompt', 'fix this prompt', 'optimize a prompt', 'learn prompting techniques', 'get prompt templates', 'prompt engineering', 'prompt quality', 'prompt rewriting'. These are highly natural phrases users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | The skill occupies a clear niche around prompt engineering and prompt improvement, with specific attribution to 'Forward Future's guide' and '11 foundational techniques'. This is unlikely to conflict with other skills unless there are multiple prompt engineering skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with strong actionability and workflow clarity. The 5-step process is clearly defined with concrete examples and a useful diagnostic framework. The main weakness is moderate verbosity — some content (temperature guide, basic prompting concepts like what a role or action verb is) is knowledge Claude already possesses, consuming tokens without adding unique value.
Suggestions
Remove or significantly trim the Temperature Guide section — Claude already understands temperature settings and their effects.
Condense the diagnostic questions table and prompt formula section, as Claude inherently understands prompt components like roles, action verbs, and format specifications.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity. The temperature guide and some of the diagnostic tables explain concepts Claude already knows well (e.g., what temperature does, basic prompt components). The tables are useful but could be tighter. | 2 / 3 |
Actionability | The skill provides concrete, actionable guidance throughout: a clear diagnostic checklist, a technique selection matrix, a specific prompt formula (Role/Task/Input/Format), a before/after example transformation, a common problems fix table, and a structured output template. Everything is specific and directly usable. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced (Diagnose → Select → Apply → Fix → Deliver) with explicit validation built in (Step 4 fixes common problems, operational rules include scoring the improved prompt against diagnostic questions). The output format in Step 5 provides a clear deliverable structure. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to three specific files (techniques-detailed.md, role-templates.md, scorecard.md). The main content is appropriately scoped as an overview, with detailed content delegated to reference files. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- back1ply/LLM-Skills
- Commit
b573078
- Reviewed
Table of Contents
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.