skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Quality

77%

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 ./.claude/skills/skill-creator/SKILL.md

Quality

Content

70%

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

The body delivers a clear, sequenced skill-creation workflow with executable script commands and well-signaled one-level-deep reference files that actually exist. It loses points on conciseness (definitional framing and metaphors Claude already knows) and on actionability (several steps are guidance prose rather than executable instructions).

Suggestions

Trim conceptual framing Claude already knows (the modular-self-contained definition, the narrow-bridge/open-field metaphor) to tighten the body toward the conciseness it itself prescribes.

Convert guidance-level steps ("Include information that would be beneficial", "Consider what procedural knowledge...") into concrete, checkable instructions or short worked examples to raise actionability.

Consider moving the detailed "Progressive Disclosure Patterns" code-fence examples into a reference file, keeping only the core principle and navigation in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is ~355 lines and includes conceptual framing Claude largely already knows ("Skills are modular, self-contained packages that extend Claude's capabilities") and metaphors (the narrow-bridge/open-field analogy), so it is mostly efficient but padded in places — score 2 rather than 1 (it is not bloat-level) or 3 (not lean enough to assume Claude's competence throughout).	2 / 3
Actionability	Concrete executable commands appear ("scripts/init_skill.py <skill-name> --path <output-directory>", "scripts/package_skill.py <path/to/skill-folder> ./dist") with a clear 6-step process, but many steps are guidance-level prose ("Include information that would be beneficial and non-obvious", "Consider what procedural knowledge...") rather than copy-paste instructions, landing at score 2 rather than 3.	2 / 3
Workflow Clarity	A clear ordered 6-step sequence is given with an explicit validation feedback loop ("The packaging process automatically validates the skill first" and "Fix any validation errors and run the packaging command again") plus a test checkpoint ("Added scripts must be tested by actually running them"), matching the score-3 anchor with explicit validation and error recovery.	3 / 3
Progressive Disclosure	Detailed design patterns are offloaded to real one-level-deep files clearly signaled from the body ("See references/workflows.md for sequential workflows", "See references/output-patterns.md"), and both referenced files exist, matching the score-3 clear-overview-with-well-signaled-references anchor.	3 / 3
	Total	10 / 12 Passed

Description

85%

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 the skill does and when to use it with explicit triggers and uses correct third-person voice. It is somewhat narrow in trigger-term variation and slightly stilted phrasing, which keeps trigger_term_quality below the top anchor.

Suggestions

Broaden trigger-term coverage to common user phrasings (e.g. "build a skill", "make a skill", "design a skill") alongside "create" and "update".

Tighten the when-clause toward natural keyword form (e.g. "Use when users want to create, build, or update a skill...") rather than "This skill should be used when users want to...".

Dimension	Reasoning	Score
Specificity	Quotes "creating effective skills" and enumerates concrete capability types ("specialized knowledge, workflows, or tool integrations") plus both "create a new skill" and "update an existing skill" — multiple specific concrete actions, matching the score-3 anchor rather than the score-2 single-domain framing.	3 / 3
Completeness	Clearly answers both what ("Guide for creating effective skills... extends Claude's capabilities with specialized knowledge, workflows, or tool integrations") and an explicit when ("This skill should be used when users want to create a new skill (or update an existing skill)"), matching the score-3 anchor with explicit triggers.	3 / 3
Trigger Term Quality	Natural trigger phrases "create a new skill" and "update an existing skill" are present, but coverage of common variations (e.g. "build a skill", "make a skill") is thin and the phrasing "This skill should be used when users want to..." is stilted rather than the natural keyword form, landing at score 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	The niche of "creating effective skills" is distinct from domain skills and the explicit create/update-skill triggers make misfiring unlikely, matching the score-3 clear-niche anchor rather than the score-2 overlap case.	3 / 3
	Total	11 / 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: 12 missing	Warning

	Total	14 / 16 Passed

Repository: sentient-agi/EvoSkill
Path: .claude/skills/skill-creator/SKILL.md
Commit: 36f6f04

Reviewed: 1 day 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.