skill-creator

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

Quality

76%

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-creator/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable and workflow-sequenced with explicit validation feedback loops, and its progressive-disclosure patterns are well taught. Its main weaknesses are verbosity from analogies and inline mockups, and dangling references to bundled files that are not actually shipped.

Suggestions

Add the missing references/workflows.md and references/output-patterns.md (or remove the two dangling pointers on lines 302-303) so all cited bundle paths resolve.

Trim the bridge/cliff analogy and consolidate the three illustrative directory mockups into one concise example to reclaim tokens.

Move the long anatomy/"What to Not Include" reference material into a references file, keeping only core procedural guidance in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~372-line body is mostly efficient but padded: the bridge/field analogy, three large illustrative directory mockups, and repetitive bullets explain or repeat what the reader already knows, so it could be tightened.	2 / 3
Actionability	It provides copy-paste-ready CLI invocations (init_skill.py and package_skill.py with flags and examples), concrete naming rules, and a fully worked description example, giving executable guidance throughout.	3 / 3
Workflow Clarity	The six-step creation process is explicitly ordered with a skip-condition rationale, and packaging includes a validate→fix→re-run feedback loop ("Fix any validation errors and run the packaging command again").	3 / 3
Progressive Disclosure	Structure and one-level signaling are present and scripts are correctly linked, but the body points to references/workflows.md and references/output-patterns.md (lines 302-303) that do not exist in the bundle, and large illustrative directory trees are kept inline rather than split out.	2 / 3
	Total	10 / 12 Passed

Description

75%

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" trigger and occupies a clear, low-conflict niche. It is held back from the top band only by limited action specificity and incomplete coverage of common trigger phrasings.

Suggestions

Expand the action list with concrete verbs (e.g., "author, scaffold, validate, and package skills") to raise specificity.

Add common natural trigger terms such as "build", "make", or "author a skill" alongside "designing, structuring, or packaging".

Optionally note validation/packaging explicitly in the trigger ("...or when packaging and validating a skill for distribution").

Dimension	Reasoning	Score
Specificity	"Create or update AgentSkills" names the domain and two broad verbs but does not enumerate multiple concrete actions (e.g., author SKILL.md, scaffold directories, validate, package), so it stops short of a comprehensive list.	2 / 3
Completeness	It states what the skill does ("Create or update AgentSkills") and provides an explicit trigger clause ("Use when designing, structuring, or packaging skills..."), clearly answering both what and when.	3 / 3
Trigger Term Quality	"designing, structuring, or packaging skills with scripts, references, and assets" surfaces relevant terms, but it omits common natural variations a user would say (e.g., "build", "make", "author a skill"), leaving coverage incomplete.	2 / 3
Distinctiveness Conflict Risk	The skill-authoring niche with its bundled-resource trigger ("skills with scripts, references, and assets") is clearly distinct from domain skills, making a wrong-skill trigger unlikely.	3 / 3
	Total	10 / 12 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: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 14 missing	Warning

	Total	14 / 16 Passed

Repository: RKiding/Awesome-finance-skills
Path: skills/skill-creator/SKILL.md
Commit: 853f09b

Reviewed: about 13 hours 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.