create-skill

Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.

Quality

68%

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/skill-create/SKILL.md

Quality

Content

63%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 body is a thorough, actionable guide with a clear phased workflow and concrete templates and examples. Its weak spots are conciseness (duplication between the requirements-gathering and Discovery sections, near the 500-line ceiling) and progressive disclosure (it preaches splitting reference material into separate files but keeps everything inline in a single large file).

Suggestions

De-duplicate the 'Before You Begin: Gather Requirements' section with 'Phase 1: Discovery' — keep one canonical requirements list and reference it from the workflow to reclaim tokens.

Practice the progressive disclosure the skill teaches: move the five detailed 'Common Patterns' examples and/or the full 'Complete Example' into a separate reference.md linked one level deep from SKILL.md.

Trim any restatement of description best practices that already appears verbatim in the 'Summary Checklist' to avoid repeating the same guidance twice.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and example-driven without explaining concepts Claude already knows, but at ~490 lines it duplicates material — 'Before You Begin: Gather Requirements' and 'Phase 1: Discovery' cover the same purpose/location/trigger/requirements ground — so it could be tightened, matching the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	It gives concrete, copy-paste-ready guidance: exact storage paths, field constraints (name max 64 chars, lowercase/hyphens), description templates, commit-message examples, and a full 'Complete Example' SKILL.md, with only minor gaps where sections are principle-descriptive rather than executable.	4 / 5
Workflow Clarity	The 'Skill Creation Workflow' sequences Discovery → Design → Implementation → Verification with numbered steps and a verification checklist acting as a checkpoint, satisfying 'clear sequence with most checkpoints present'; no feedback loop is present, but the task is not destructive/batch so the 3-cap does not apply.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is a single ~490-line file; while it is well-sectioned with clear headers, content that the skill itself advocates splitting (the five detailed 'Common Patterns', the full 'Complete Example') is inlined, and the file sits at the very 500-line limit it warns against — matching 'some structure but content that should be separate is inline'.	3 / 5
	Total	14 / 20 Passed

Description

73%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 cleanly satisfies the what/when contract with explicit, third-person trigger guidance and a clear niche. Its main weakness is specificity: the capability statement is generic ('guides users through creating') rather than enumerating concrete authoring actions.

Suggestions

Replace the generic verb 'guides users through creating' with 1-2 concrete actions, e.g. 'Drafts SKILL.md frontmatter, structures reference files, and writes skill descriptions for Cursor Agent Skills.'

Consider adding the standalone trigger terms 'agent skills' and 'Cursor skills' so users who phrase the request that way still surface this skill.

Dimension	Reasoning	Score
Specificity	The 'what' clause is "Guides users through creating effective Agent Skills for Cursor" — it names the domain (Agent Skills for Cursor) but relies on a single generic verb ("guides users through creating") rather than listing concrete authoring actions such as drafting frontmatter, structuring references, or writing descriptions, matching the anchor for naming the domain with minimal/generic actions.	2 / 5
Completeness	It explicitly answers both what ("Guides users through creating effective Agent Skills for Cursor") and when ("Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The 'when' clause surfaces several natural user phrasings — "create, write, or author a new skill", "skill structure", "best practices", "SKILL.md format" — giving good keyword coverage, though standalone variants like "Cursor skills" or "agent skills" are not explicitly enumerated, so it falls just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The skill-authoring niche (Cursor Agent Skills, SKILL.md format) is clearly distinct with minimal conflict risk, but the standalone trigger term "best practices" is broad enough to potentially overlap with general coding-best-practices skills, leaving minor overlap risk.	4 / 5
	Total	15 / 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
relative_links	Relative link issues: 4 missing	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: xstongxue/best-skills
Path: skills/skill-create/SKILL.md
Commit: 88a38bb

Reviewed: ~1 hour 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.