skill-builder-generic

Universal guide for creating production-ready Claude Code skills for any project. Includes 6-step workflow (understand, plan, initialize, edit, package, iterate), progressive disclosure design, YAML frontmatter templates, validation scripts, reference organization patterns, and 10 community-proven innovations. Use when creating new Claude Code skills, converting documentation to skills, improving existing skills, or learning skill development best practices for any domain.

Quality

70%

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 ./skill-builder-package/skill-builders/skill-builder-generic/SKILL.md

Quality

Content

57%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 body is concise and well-structured as an overview, but it underdelivers on the description's promises: the 6-step workflow is only a pointer, and the validate/package steps reference scripts that are absent from the bundle. Fixing the broken script references and surfacing the remaining reference files would meaningfully raise the score.

Suggestions

Add the missing scripts/validate-skill.py and scripts/package-skill.sh to the bundle, or replace the quick-start invocations with commands that actually exist, so the validate/package steps are executable.

Inline at least a brief outline of the 6-step workflow (understand, plan, initialize, edit, package, iterate) in the body instead of deferring it entirely to a reference, so the core process promised in the description is visible.

Signal the other bundled reference files (anti-patterns-and-fixes.md, progressive-disclosure-architecture.md, validation-checklist-complete.md, writing-style-imperative-guide.md) from the body so navigation covers the full bundle.

Dimension	Reasoning	Score
Conciseness	The ~60-line body is lean and mostly efficient with compact code blocks, though the Overview and When-to-Use sections partially restate the frontmatter description.	4 / 5
Actionability	Quick-start steps 1–3 are concrete and executable, but steps 4–5 invoke scripts/validate-skill.py and scripts/package-skill.sh that do not exist in the bundle, and the core 6-step process is deferred to a reference rather than given.	3 / 5
Workflow Clarity	The quick start provides a clear 5-step sequence, but the promised 6-step workflow is only a pointer and the validation checkpoint references a missing script, capping clarity for a packaging/destructive operation.	3 / 5
Progressive Disclosure	The body is an overview with a one-level reference to references/yaml-frontmatter-complete-guide.md (which exists), but it signals only one of five reference files and links to non-existent scripts/, leaving navigation incomplete.	3 / 5
	Total	13 / 20 Passed

Description

83%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 is strong: it clearly answers both what the skill does and when to use it, in third person, with concrete capabilities and natural trigger phrases. The only soft spots are mild abstractness in the actions and broad 'any project/domain' framing that slightly raises overlap risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities (creating skills, converting documentation, improving skills) plus bundled contents (6-step workflow, templates, validation scripts), but the actions stay somewhat more abstract than the 5-anchor's concrete file operations.	4 / 5
Completeness	Explicitly states what it does ('Universal guide for creating production-ready Claude Code skills') and when to use it ('Use when creating new Claude Code skills, converting documentation to skills, improving existing skills...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like 'creating new Claude Code skills, converting documentation to skills, improving existing skills, learning skill development best practices' map well to what a user would say; a few synonyms and shorthand forms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear skill-building niche with distinct triggers and minimal conflict risk, though 'for any project' / 'for any domain' breadth introduces minor overlap with general development skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skill-builder-package/skill-builders/skill-builder-generic/SKILL.md
Commit: 93ed392

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.