skill-creator

Guide for creating effective skills. Use this skill when users need to create a new skill or reshape a draft skill package before hardening, benchmarking, or distribution.

Quality

71%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./Plugins/skill-factory/fixtures/budget-archive/2026-04-21/deferred-store/skills/scaffolding_templates/skill-creator/SKILL.md

Quality

Content

85%

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

This is a well-structured, highly actionable skill with strong workflow clarity and excellent progressive disclosure patterns. Its main weakness is moderate verbosity — some sections (Philosophy, Remember, parts of Execution Boundaries) could be tightened without losing information. The skill practices what it preaches about navigation-first design and delegating detail to references.

Suggestions

Trim or remove the 'Philosophy' and 'Remember' sections — their content is either self-evident to Claude or already expressed through the procedural steps and constraints.

Remove the Table of Contents; it adds tokens without value since Claude navigates by content, not by clicking links.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some unnecessary philosophical framing ('Treat skill authoring as durable systems design'), a verbose Table of Contents, and sections like 'Remember' and 'Philosophy' that restate what Claude already knows about good documentation. The output contract section is detailed but could be tightened. However, most sections do carry meaningful, non-obvious information.	2 / 3
Actionability	The skill provides concrete, executable commands throughout (init_skill.py, quick_validate.py, validate_role.sh, generate_openai_yaml.py), specific file paths, clear deliverable lists, and a structured output contract with named fields. The procedure is step-by-step with real CLI invocations that are copy-paste ready.	3 / 3
Workflow Clarity	The procedure section provides a clear numbered sequence with explicit validation checkpoints. The validation section enforces a fail-fast policy with re-validation after fixes. The workflow includes feedback loops (stop at first failure, fix, re-run) and clear handoff criteria. Agent injection steps are also well-sequenced with validation gates.	3 / 3
Progressive Disclosure	Excellent progressive disclosure with well-signaled 'Read when:' signposts throughout, pointing to specific reference files for specific contexts. The References section provides a clear one-level-deep navigation table. Content is appropriately split between the concise SKILL.md entrypoint and detailed references/ documents. However, bundle files were not provided so actual reference content cannot be verified.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 provides a clear 'Use when' clause which helps with completeness, but it lacks specificity about what concrete actions the skill performs. The 'what' portion is too abstract—'creating effective skills' doesn't tell Claude what specific guidance or steps are involved. The trigger terms are adequate but could be more comprehensive with file-type references and common user phrasings.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Guides structuring YAML frontmatter, writing description fields, defining trigger terms, and organizing skill markdown sections.'

Include more natural trigger terms users might say, such as 'SKILL.md', 'skill file', 'skill template', 'write a skill', 'skill authoring'.

Dimension	Reasoning	Score
Specificity	The description says 'creating effective skills' and 'reshape a draft skill package' but doesn't list any concrete actions like 'write YAML frontmatter', 'define trigger terms', 'structure markdown sections', etc. The language remains abstract.	1 / 3
Completeness	The description answers both 'what' (guide for creating effective skills) and 'when' ('Use this skill when users need to create a new skill or reshape a draft skill package before hardening, benchmarking, or distribution') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'create a new skill', 'draft skill package', 'hardening', 'benchmarking', and 'distribution', but 'skill' is quite generic and could conflict. Terms like 'SKILL.md', 'skill file', 'skill template' are missing.	2 / 3
Distinctiveness Conflict Risk	The term 'skills' is somewhat domain-specific to this context, but 'creating' and 'reshaping' are generic enough that it could overlap with other meta-skills or documentation skills. The mention of 'hardening, benchmarking, or distribution' adds some distinctiveness but the core concept remains broad.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: jscraik/Agent-Skills
Commit: 8e7e19d

Reviewed: 5 days 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.