prompt-enhancer

Enhance user prompts by analyzing project context (code structure, dependencies, conventions, existing patterns). Use when users provide brief development requests that would benefit from project-specific context to generate more accurate, contextually-aware prompts.

Quality

66%

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-enhancer/SKILL.md

Quality

Content

70%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 skill is highly actionable with an excellent, checkpointed workflow, but it underperforms on token efficiency and structure: a large stack-patterns section and a very long worked example duplicate material that already lives in the provided reference files.

Suggestions

Move the 'Analysis Patterns by Stack' section (Flutter / Next.js-React / Python) into references/framework-guides.md and replace it in SKILL.md with a one-line pointer per stack, since that file already covers the same frameworks.

Trim the ~135-line 'Example Enhancement' to a short representative excerpt and move the full worked example into references/enhancement-patterns.md, keeping SKILL.md as an overview rather than a case-study document.

Consolidate the duplicated '성공 기준' / file-structure templates so the Step 3 scaffold and the worked example do not repeat the same structural layout twice.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful and avoids explaining basic concepts Claude already knows, but at ~400 lines it inlines an 'Analysis Patterns by Stack' section that duplicates references/framework-guides.md and a ~135-line worked example that re-walks the Step 3 template, so it could be tightened substantially.	3 / 5
Actionability	It provides an executable command ('view /mnt/user-data/uploads'), concrete file-path targets (package.json, pubspec.yaml, requirements.txt), complete output templates, and a fully worked example with specific endpoints and paths — minor gaps remain in the abstract placeholder scaffolding.	4 / 5
Workflow Clarity	The four-step Core Workflow is clearly sequenced with an explicit validation gate ('Do NOT implement until the user confirms'), a feedback loop (user requests modifications), and checklists (성공 기준); the skill is non-destructive, so the destructive-cap does not apply.	5 / 5
Progressive Disclosure	The two reference files are clearly signaled in a 'Reference Files' section and verified to exist, but the inlined 'Analysis Patterns by Stack' content clearly belongs in references/framework-guides.md — content that should be separate is inline alongside the separate file.	3 / 5
	Total	15 / 20 Passed

Description

62%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 answers both what and when with an explicit 'Use when' clause and a clear niche, placing it solidly above average. Its main weakness is that the trigger language stays abstract rather than listing concrete user phrasings.

Suggestions

Replace the abstract trigger 'brief development requests' with concrete examples users actually say, e.g. 'Use when the user gives a terse request like "add login", "make an API", or "로그인 기능 만들어줘" that needs project context to scope accurately.'

Strengthen specificity by naming the concrete output action, e.g. 'Generates a structured requirement document (file paths, layers, acceptance criteria) from the brief request' instead of the single verb 'Enhance'.

Dimension	Reasoning	Score
Specificity	It names the domain and the dimensions analyzed ('code structure, dependencies, conventions, existing patterns') but offers only one core action verb ('Enhance') plus 'analyzing', rather than multiple distinct concrete actions like the score-4 anchor requires.	3 / 5
Completeness	It clearly states what the skill does ('Enhance user prompts by analyzing project context') and provides an explicit 'Use when...' clause, but the 'when' condition ('requests that would benefit from project-specific context') is somewhat circular and could be more concrete.	4 / 5
Trigger Term Quality	It includes relevant keywords ('brief development requests', 'project context', 'prompts') but the triggers are abstract and miss the natural phrasings users actually say (e.g. 'add login', 'make an API'); concrete example triggers only appear in the body, not the description.	3 / 5
Distinctiveness Conflict Risk	'Enhance user prompts by analyzing project context' carves a fairly distinct meta-task niche, with only minor overlap risk against general prompt-improvement or code-generation skills.	4 / 5
	Total	14 / 20 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: bear2u/my-skills
Path: skills/prompt-enhancer/SKILL.md
Commit: 8ed5784

Reviewed: 10 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.