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.

1.42x

Quality

68%

Does it follow best practices?

Impact

98%

1.42x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/skill-creator/SKILL.md

Quality

Content

73%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 content delivers a clear, actionable, well-sequenced skill-creation workflow with validation checkpoints and strong progressive-disclosure guidance. Its main weakness is conciseness—several passages restate knowledge Claude already has—and the inlined reference examples slightly pad the body.

Suggestions

Tighten the 'About Skills' and 'Core Principles' sections by cutting restatements of general knowledge (e.g. what skills are, that the context window is shared) and keeping only the non-obvious guidance.

Move the long bullet lists of reference/asset example filenames into a short representative example plus a pointer, reducing inline padding.

Verify the referenced bundle files (references/workflows.md, references/output-patterns.md, scripts/init_skill.py, scripts/package_skill.py) actually exist, or note that they ship with the plugin so the in-SKILL.md pointers resolve.

Dimension	Reasoning	Score
Conciseness	The body is well under 500 lines and mostly efficient, but several sections restate what Claude already knows (e.g. 'Skills are modular, self-contained packages that extend Claude's capabilities...') and the principles are somewhat padded with explanatory prose that could be trimmed.	3 / 5
Actionability	It provides concrete, runnable commands ('scripts/init_skill.py <skill-name> --path <output-directory>', 'scripts/package_skill.py <path/to/skill-folder>') with a concrete frontmatter example and explicit examples for scripts/references/assets, with only minor gaps (e.g. init/package flags are not exhaustively documented).	4 / 5
Workflow Clarity	A clear six-step process is laid out in order with explicit sequencing and validation feedback loops: Step 5 packaging runs automated validation ('If validation fails... fix any validation errors and run the packaging command again') and Step 4 requires testing scripts by actually running them, satisfying the destructive/batch validation expectation.	5 / 5
Progressive Disclosure	The body is structured as an overview with well-signaled one-level-deep references (workflows.md, output-patterns.md) and clear patterns for splitting content; however the referenced bundle files (references/, scripts/) do not exist in this skill's bundle, so the structure is described rather than fully realized, and some reference example lists are inlined.	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 clearly states both what the skill does and when to use it, satisfying the Use-when requirement, and uses appropriate third-person voice. It is somewhat light on specific concrete actions and natural trigger-term synonyms, keeping it just above the midpoint.

Suggestions

Add concrete capabilities to the 'what' clause, e.g. 'scaffolds, writes, validates, and packages SKILL.md skills with bundled scripts, references, and assets'.

Broaden trigger terms with natural variations users would say: 'build a skill', 'write a SKILL.md', 'package a .skill file', 'skill metadata/frontmatter'.

Sharpen the 'when' clause with explicit trigger contexts such as 'Use when the user asks to create, structure, package, or iterate on a Claude skill'.

Dimension	Reasoning	Score
Specificity	It names the domain ('creating effective skills') and a couple of concrete actions ('create a new skill', 'update an existing skill'), but stops at the activity level rather than enumerating specific capabilities like scaffolding, packaging, or writing references.	3 / 5
Completeness	It answers both 'what' (Guide for creating effective skills) and 'when' ('should be used when users want to create a new skill or update an existing skill'), so the Use-when clause is present and explicit, though the 'when' could name more concrete triggering contexts.	4 / 5
Trigger Term Quality	It includes natural phrases a user might say ('create a new skill', 'update an existing skill') and the keyword 'skill', but lacks synonyms and common variations like 'SKILL.md', 'build a skill', or '.skill' that users would actually invoke.	3 / 5
Distinctiveness Conflict Risk	The trigger ('create a new skill or update an existing skill') carves a fairly distinct niche with low overlap risk against unrelated skills, though 'specialized knowledge, workflows, or tool integrations' is broad enough to invite minor overlap with general task skills.	4 / 5
	Total	14 / 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: 8 missing	Warning
referenced_paths_exist	Referenced path issues: 19 missing	Warning

	Total	14 / 16 Passed

Repository: NeverSight/skills_feed
Path: data/skills-md/0xdarkmatter/claude-mods/skill-creator/SKILL.md
Commit: 2f57aec

Reviewed: about 22 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.