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

77%

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

65%

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

The body is highly actionable with concrete templates, naming rules, and specific cross-skill references, and it avoids explaining concepts Claude already knows. It is weakest on workflow sequencing (no explicit create-then-verify flow) and on practicing the progressive disclosure it preaches.

Suggestions

Add a short numbered 'Steps to create a skill' flow (interview → pick type → fill template → name → set scope → verify) with a final verification checkpoint so the process is sequenced rather than implied.

Either move the three skill-type templates into a references/ file (e.g. templates.md) and link to it, or explicitly justify keeping them inline, to align the skill with its own progressive-disclosure guidance.

Tighten the scope section and de-duplicate the repeated template frontmatter placeholder to reduce token weight while preserving the actionable core.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of basic-concept padding, but the three near-parallel templates repeat shared headings and the identical placeholder line, and the ~30-line scope section is more than the core task requires; it could be tightened without losing clarity.	2 / 3
Actionability	It provides copy-paste-ready markdown templates for each skill type, concrete naming rules ('[a-z0-9-], max 64 characters'), a file-structure tree, and specific cross-references (useDbSync, view-screen action, navigation state key) — fully executable guidance.	3 / 3
Workflow Clarity	A reasonable order exists (When to Use → Interview → Templates → Naming → Scope), but the creation process is presented as a checklist rather than an explicit sequenced workflow, and there are no validation checkpoints to confirm a finished skill is well-formed.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is self-contained with well-organized sections, but it recommends pushing depth into references/ without employing that pattern itself, and the three inline templates are content that could plausibly live in separate reference files.	2 / 3
	Total	9 / 12 Passed

Description

90%

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 concise, third-person, and explicitly pairs a clear capability statement with a multi-situation 'Use when' trigger clause. Its main weakness is that the listed actions skew slightly abstract rather than naming concrete operations.

Suggestions

Replace the abstract phrase 'creating reusable guidance for the agent' with a more concrete action verb so capabilities read as distinct operations rather than overlapping intent.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('create new skills', 'documenting a pattern the agent should follow', 'creating reusable guidance'), but the latter two are relatively abstract compared to the concrete verb lists in the top anchor; not fully comprehensive on distinct capabilities.	2 / 3
Completeness	It explicitly answers both what ('How to create new skills for an agent-native app') and when ('Use when adding a new skill, documenting a pattern..., or creating reusable guidance'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	The clause 'Use when adding a new skill, documenting a pattern the agent should follow, or creating reusable guidance' covers natural phrases a user would say when needing this skill, with three distinct triggering situations.	3 / 3
Distinctiveness Conflict Risk	'Create new skills' carves a clear niche with distinct triggers; the guidance is specific to skill authoring and is unlikely to fire for unrelated skills, despite mild adjacency to writing-agent-instructions.	3 / 3
	Total	11 / 12 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: c1ee18b

Reviewed: 4 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.