CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-skill

Create Cursor Agent Skills. Use when authoring a new skill or asking about SKILL.md structure.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills-cursor/create-skill/SKILL.md
SKILL.md
Quality
Evals
Security

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.

This is a strong, highly actionable instruction skill: concrete templates, exact paths, worked examples, and a clearly phased creation workflow with a verification checklist. Its main weaknesses are duplicated requirement-gathering content that inflates length and the absence of any bundle files to practice the progressive disclosure it teaches.

Suggestions

Merge the duplicated requirements lists in 'Before You Begin' and 'Phase 1: Discovery' into a single section to remove verbatim redundancy and reduce token cost.

Move the 'Complete Example' and/or anti-pattern catalogs into an examples.md or reference.md file and link to them one level deep, demonstrating the progressive disclosure the skill prescribes.

Add an explicit error-recovery step to Phase 4 (fix failing checks and re-verify before delivering the skill) to close the feedback loop in the creation workflow.

DimensionReasoningScore

Conciseness

The body is mostly concrete guidance, but 'Before You Begin: Gather Requirements' and 'Phase 1: Discovery' repeat nearly the same information list verbatim, and the 'Summary Checklist' restates points already made in earlier sections. It is tighter than the padded anchor 2 example yet clearly could be consolidated, fitting 'mostly efficient but could be tightened'.

3 / 5

Actionability

The guidance is fully executable throughout: exact storage paths, a copy-paste SKILL.md frontmatter template, a required-metadata field table with constraints, four concrete description examples, named patterns with templates, and a complete worked example. Per the instruction-skill note, this concrete and specific guidance earns the top actionability score.

5 / 5

Workflow Clarity

The Skill Creation Workflow (Discovery, Design, Implementation, Verification) is a clear four-phase sequence ending in an explicit verification checklist. It stops short of anchor 5 because the workflow itself lacks an error-recovery loop (what to fix and re-verify when a Phase 4 check fails); feedback loops are only taught as a pattern for other skills.

4 / 5

Progressive Disclosure

The body is well organized with clear section headers, tables, and one-level example structure, and it explicitly teaches keeping references shallow. It does not reach 5 because the skill ships no reference files while sitting at its own recommended 500-line cap, with the complete example and anti-pattern sections inlined rather than offloaded.

4 / 5

Total

16

/

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 follows the WHAT/WHEN pattern with an explicit 'Use when' clause and a distinct Cursor-specific niche, avoiding vagueness. However, it under-sells the skill's capabilities and has thin trigger-term coverage, leaving discovery reliant on users phrasing requests close to its two listed triggers.

Suggestions

List the skill's concrete capabilities in the description (e.g., structure, frontmatter, descriptions, scripts, storage locations) to raise specificity from a single 'create' action.

Add natural trigger variations such as 'write a skill', 'agent skills', 'skill file', or 'skill template' so the description matches how users actually phrase skill-authoring requests.

Consider mentioning what the skill covers when asked about skill structure (description writing, progressive disclosure, utility scripts) to sharpen both completeness and distinctiveness.

DimensionReasoningScore

Specificity

"Create Cursor Agent Skills" names the domain and one concrete action (create) but does not enumerate the skill's specific capabilities (structure, descriptions, scripts), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is above a bare domain mention ('Processes PDF files') but below the several-specific-actions level.

3 / 5

Completeness

It has both a clear 'what' ("Create Cursor Agent Skills") and an explicit 'when' ("Use when authoring a new skill or asking about SKILL.md structure"), satisfying the Use-when requirement above the cap of 3. It falls short of 5 because the 'what' is thin and the trigger phrases are brief rather than concrete and comprehensive.

4 / 5

Trigger Term Quality

Phrases like "authoring a new skill", "SKILL.md structure", and "Cursor Agent Skills" are relevant triggers, but common variations users would naturally say ("write a skill", "agent skills", "skill file") are absent. Coverage is partial rather than good-with-a-few-missing, so it fits the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"Cursor Agent Skills" and "SKILL.md structure" carve a fairly distinct niche with low conflict risk against unrelated skills. There is minor overlap risk with generic skill-authoring guidance that is not Cursor-specific, placing it at 'mostly distinct' rather than the clear-niche, minimal-conflict level.

4 / 5

Total

14

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (505 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 4 missing

Warning

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

13

/

16

Passed

Repository

saski/arnesto

Path

.cursor/skills-cursor/create-skill/SKILL.md

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.