best-practices

Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.

Quality

72%

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/best-practices/SKILL.md

Quality

Content

75%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.

A highly actionable, well-structured body with concrete examples and a clear workflow, weakened mainly by repetition between the principles, examples, checklist, and eval tables that inflates token usage. Progressive disclosure is solid, though the body could shed more content to its reference files.

Suggestions

Consolidate the Quick Transformation Examples and Common Anti-Patterns table into the existing references (before-after-examples.md / anti-patterns.md) to remove restated content and reduce tokens.

Add an explicit validation/synthesis checkpoint in the 'Build context first' branch (e.g. 'verify all three agents returned, then synthesize; if any returned empty, re-launch that one') to close the workflow gap.

Trim the Success Criteria eval section or move it to a reference, since it restates the 5 principles in tabular form.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of irrelevant concept explanation, but the Success Criteria eval tables, the Quick Transformation Examples, and the Anti-Patterns table substantially restate the 5 principles already covered above and could be tightened or delegated to reference files.	3 / 5
Actionability	Fully executable throughout: concrete before/after examples with real file paths, the copy-paste-ready 4-phase pattern, specific transformation tables, and a copy-paste output format cover the common cases.	5 / 5
Workflow Clarity	The mode-selection, transformation, and 'After Agents Return' sequences are clearly numbered with a closing checklist, but the parallel-agent 'Build context first' path lacks an explicit validation/feedback loop after synthesis before output.	4 / 5
Progressive Disclosure	Structure is good with a clear overview and one-level-deep, well-signaled references (all five referenced files exist and are linked), but the body itself is long and some inline sections (Success Criteria eval, full example set) could move to the reference files.	4 / 5
	Total	16 / 20 Passed

Description

70%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.

A clear, specific description that names concrete capabilities and a distinct command trigger, but it lacks an explicit 'Use when...' usage clause, relying instead on an invocation instruction. Trigger-term coverage is good but could add natural synonyms.

Suggestions

Add an explicit 'Use when...' clause naming the natural situations that call for this skill (e.g. 'Use when the user wants to improve, rewrite, or harden a vague prompt for Claude Code').

Include common user phrasings as trigger terms, such as 'improve prompts', 'rewrite prompts', or 'make my prompt better', alongside the existing vocabulary.

Replace the generic 'Invoke with /best-practices' line with both an explicit trigger clause and the invocation note so the 'when' is unambiguous.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('Adds verification, specific context, constraints, and proper phasing'), with only minor abstraction in 'proper phasing' keeping it below the comprehensive anchor.	4 / 5
Completeness	The 'what' is clear (transforms prompts by adding verification, context, constraints, phasing), but 'when to use it' is only given as the invocation instruction 'Invoke with /best-practices', not an explicit 'Use when...' trigger, which caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms like 'prompts', 'Claude Code prompts', 'verification', 'constraints' plus the '/best-practices' command trigger, but misses common synonyms users would say such as 'improve' or 'rewrite prompts'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (prompt transformation for Claude Code) with a distinct command trigger '/best-practices' and minimal overlap with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (502 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: MoizIbnYousaf/ai-agent-skills
Path: skills/best-practices/SKILL.md
Commit: 1159592

Reviewed: 19 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.