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.
83
80%
Does it follow best practices?
Impact
82%
1.09xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./prompt-engineering/skills/humanitys-last-prompt-engineer/SKILL.mdQuality
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—what the 11 techniques actually are or what the skill produces remains unclear. The description is functional but could be stronger on specificity of actions.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Rewrites prompts using chain-of-thought, few-shot examples, role assignment, and other structured techniques' instead of just referencing '11 foundational techniques'.
Briefly enumerate or categorize the key techniques (e.g., 'chain-of-thought, few-shot prompting, role-based framing') so Claude understands the skill's actual capabilities rather than 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 provided). The 'Use when' equivalent is clearly stated at the beginning. | 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 phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The skill is clearly focused on prompt engineering and prompt improvement, which is a distinct niche. The mention of 'Forward Future's guide' and '11 foundational techniques' further distinguishes it. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
70%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 excellent workflow clarity and progressive disclosure. Its main weakness is that it spends significant tokens explaining prompting concepts (techniques, temperature settings, diagnostic patterns) that Claude already deeply understands, and the actionability could be improved with more concrete, diverse examples rather than descriptive tables. The skill would benefit from trimming explanatory content and adding more executable examples.
Suggestions
Remove or drastically condense the technique selection table and temperature guide — Claude already knows these concepts intimately. Replace with only project-specific conventions or non-obvious mappings.
Add 2-3 more concrete before/after prompt transformation examples covering different techniques (e.g., a chain-of-thought example, a few-shot example) to increase actionability beyond the single marketing example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably well-organized but includes some unnecessary verbosity. The diagnostic table, technique selection table, and common problems table all contain information Claude already knows well (e.g., what chain-of-thought is, what few-shot prompting is). The temperature guide section explains basic concepts Claude inherently understands. However, the structured tables do add some efficiency. | 2 / 3 |
Actionability | The skill provides a structured workflow and a concrete example transformation (weak→strong), plus a clear output format template. However, most guidance remains at the descriptive/instructional level rather than providing executable artifacts. The technique descriptions are surface-level summaries rather than actionable implementation details, and the single example transformation is relatively simple. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced (Receive → Diagnose → Select → Rewrite → Explain) with explicit diagnostic questions as validation checkpoints in Step 1, a structured output format in Step 5, and an operational rule to 'score the improved prompt against the diagnostic questions to verify quality' as a feedback loop. The process is well-defined and includes verification. | 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) with clear descriptions of what each contains. The main SKILL.md stays at the right level of detail while pointing to deeper resources. | 3 / 3 |
Total | 10 / 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
cc0ada7
- 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.