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.

1.17x

Quality

71%

Does it follow best practices?

Impact

99%

1.17x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/skill-creator/SKILL.md

The canonical home for this skill is skill-creator in chrisboden/cursor-skills

Quality

Content

67%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.

A well-structured, actionable guide with a clear sequenced workflow and an explicit validation feedback loop in the packaging step. Its main weakness is conciseness: conceptual framing and redundant illustrative examples add tokens, and it keeps all material inline rather than splitting detailed guidance into reference files.

Suggestions

Trim the 'About Skills' conceptual framing and collapse the three parallel Step 2 examples (pdf-editor, frontend-webapp-builder, big-query) into a single illustrative example, since they restate the same point.

Reduce the scripts/references/assets descriptions to just the 'When to include' guidance; Claude already knows what fonts, images, and reference documents are.

Move the detailed anatomy and best-practices material into a references/ file and keep SKILL.md as a lean overview, practicing the progressive disclosure the skill itself advocates.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but carries conceptual padding (the 'About Skills' framing and three parallel Step 2 examples that each restate the same point) that could be tightened. It also explains concepts Claude already knows, such as what fonts, images, and reference docs are.	3 / 5
Actionability	Concrete commands are given for the bundled scripts (`scripts/init_skill.py <skill-name> --path <output-directory>` and `scripts/package_skill.py <path/to/skill-folder>`) plus specific questions to answer, yielding mostly executable guidance. The Step 4 writing guidance is advisory rather than executable, a minor gap.	4 / 5
Workflow Clarity	A clear six-step 'Skill Creation Process' is sequenced with an explicit validate→fix→retry loop in Step 5 ('If validation fails... fix... run the packaging command again') and a numbered iteration checklist in Step 6. Validation is centralized at packaging rather than checkpointed after each step, a minor gap versus the most granular anchor.	4 / 5
Progressive Disclosure	Structure is good with a directory tree, clear section headers, and well-signaled one-level-deep script references (`scripts/init_skill.py`, `scripts/package_skill.py`) that match the actual bundle. However all guidance is inlined in SKILL.md with no references/ files, so the skill does not itself practice the offloading it preaches.	4 / 5
	Total	15 / 20 Passed

Description

75%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.

A strong, third-person description that clearly states both what the skill does and when to use it, occupying a distinct niche with low conflict risk. Its weaker spots are capability specificity and trigger-term synonym coverage, which stop at one clear pair of actions.

Suggestions

Add concrete actions beyond 'create' and 'update' (e.g., 'scaffold, design, and package skills') to improve capability specificity.

Include common synonyms users say, such as 'build a skill' or 'make a skill', alongside 'create' to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ('create a new skill (or update an existing skill)'), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 2 because it goes beyond a bare domain label, and not a 4 because it lists no further specific actions.	3 / 5
Completeness	It explicitly answers both 'what' ('Guide for creating effective skills') and 'when' with a concrete third-person trigger clause ('This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities...'). This matches the anchor that clearly and explicitly answers both with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes natural phrases users actually say ('create a new skill', 'update an existing skill'), but misses common synonyms such as 'build a skill', 'make a skill', or 'design a skill'. This matches 'some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor above.	3 / 5
Distinctiveness Conflict Risk	Skill creation is a clear, distinct niche with specific triggers ('create a new skill', 'update an existing skill') and minimal overlap with other skills. This matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/skill-creator/SKILL.md
Commit: a9fa86d

Reviewed: about 19 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.