create-skill

How to create new skills for an agent-native app. Use when adding a new skill, documenting a pattern the agent should follow, or creating reusable guidance for the agent.

Quality

75%

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 ./.agents/skills/create-skill/SKILL.md

Quality

Content

75%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, concise instruction skill with concrete templates and clear decision guidance for creating new skills. It avoids restating concepts Claude already knows and uses cross-references effectively, with only minor opportunities to externalize detail or add fully worked examples.

Suggestions

Move the three full template skeletons into a references/ file (e.g. references/templates.md) and summarize each type inline, to push the body closer to a pure overview.

Add one fully worked example skill (real name, real description, one filled section) so the templates become copy-paste-ready rather than placeholder skeletons, lifting actionability toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and structured, assuming Claude's competence and avoiding restating basic concepts; it keeps guidance tight with templates and short rules, with only minor instances that could be trimmed further.	4 / 5
Actionability	Provides concrete, copy-paste-ready markdown templates for the three skill types plus an interview checklist and naming rules, though the templates are skeletons with placeholders rather than fully worked examples.	4 / 5
Workflow Clarity	A clear 'When to Use / Interview / Skill Types / Naming / Frontmatter / Anti-Patterns / File Structure' sequence with explicit decision guidance and 'Don't create a skill when' guardrails; it is guidance rather than a destructive/batch operation, so the validation-cap concern does not apply, and minor checkpoints are implied rather than explicit.	4 / 5
Progressive Disclosure	Well-organized into clear sections with cross-references to related skills and an explicit instruction to push depth into references/; no bundle files exist so structure is judged on the body, which keeps content appropriately placed with minor room to externalize detail.	4 / 5
	Total	16 / 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 solid, third-person description that covers what the skill does and when to trigger it with concrete capabilities. It is concise and avoids fluff, though the trigger terms could be richer in synonyms and natural variations.

Suggestions

Add natural synonyms/variations a user might say (e.g. 'scaffold a skill', 'make a new skill', 'skill template') to broaden trigger coverage toward a 5.

Tighten the 'Use when' clause into a clearer scenario form (e.g. 'Use when you need to add, scaffold, or template a new skill or reusable agent pattern') to sharpen completeness.

Dimension	Reasoning	Score
Specificity	Names the domain (creating skills for an agent-native app) and lists concrete actions — 'adding a new skill', 'documenting a pattern the agent should follow', 'creating reusable guidance' — giving several specific capabilities with only minor coverage gaps.	4 / 5
Completeness	Clearly states what it does ('How to create new skills for an agent-native app') and when to use it ('Use when adding a new skill...'), satisfying both what and when with the 'when' slightly list-like rather than scenario-driven.	4 / 5
Trigger Term Quality	Includes natural user-facing phrases like 'adding a new skill', 'documenting a pattern', 'creating reusable guidance' that a user would plausibly say, though it lacks synonyms or file-extension-style variants.	4 / 5
Distinctiveness Conflict Risk	The niche — authoring agent skills — is fairly distinct and tied to specific triggers, with only minor overlap risk against the related writing/capture skills it cross-references.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/create-skill/SKILL.md
Commit: cc2a915

Reviewed: ~5 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.