server-plugins

Framework server plugins and the `/_agent-native/` route namespace. Use when adding a custom server plugin, deciding whether to create an `/api/` route vs an action, or debugging auto-mounted framework routes.

Quality

74%

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/server-plugins/SKILL.md

Quality

Content

61%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, lean reference skill with clear routing rules and a useful actions-first decision guide. Its main weaknesses are the absence of concrete code/file examples for authoring plugins or routes and the lack of validation checkpoints in the decision workflow.

Suggestions

Add a minimal copy-paste example of a custom plugin file in server/plugins/ and a route file in server/routes/ so the guidance is executable, not just declarative.

Turn the actions-first guidance into an explicit numbered decision workflow with a validation checkpoint (e.g. 'inspect existing actions → confirm the operation cannot be an action → only then create the /api/ route').

Consider moving the full auto-mounted route table into a reference file and keeping only the most common routes inline to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is largely lean — directive rules, compact tables, and decision guidance with almost no padding of concepts Claude already knows; only light rationale sentences like 'to avoid collisions with template-specific `/api/*` routes' keep it from a 5.	4 / 5
Actionability	Concrete placement rules ('server/plugins/', 'server/routes/') and a clear route-vs-action decision flow are present, but there are no executable code or file-template examples showing how to actually author a plugin or route, leaving key execution details missing per anchor 3.	3 / 5
Workflow Clarity	A rough decision sequence exists ('Before adding a route, inspect the existing action files. Reuse the action… or add a new action…'), but there are no validation checkpoints or feedback loops and the multi-step path is only implicit, matching anchor 3.	3 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections with inline cross-references to related skills, and no bundle files are needed; the large auto-mounted route table inlined in SKILL.md is the minor organization gap that prevents a 5.	4 / 5
	Total	14 / 20 Passed

Description

87%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 what the skill covers and gives multiple concrete 'Use when' triggers tied to a distinctive framework namespace. Minor synonym/extension coverage is the only thing keeping trigger_term_quality and specificity from full marks.

Dimension	Reasoning	Score
Specificity	Names the domain ('Framework server plugins', '`/_agent-native/` route namespace') and lists several concrete actions — 'adding a custom server plugin', 'deciding whether to create an `/api/` route vs an action', 'debugging auto-mounted framework routes' — with only minor coverage gaps, fitting the anchor 4 example better than the 1-2 action cap of anchor 3.	4 / 5
Completeness	Explicitly answers both 'what' (framework server plugins and the `/_agent-native/` namespace) and 'when' via a concrete 'Use when...' clause with three trigger phrases, matching the anchor 5 example precisely.	5 / 5
Trigger Term Quality	Includes natural developer-facing phrases ('custom server plugin', '`/api/` route vs an action', 'auto-mounted framework routes') that a user would plausibly say, with good but not exhaustive synonym coverage, matching anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The `/_agent-native/` namespace and framework-plugin framing carve a clear, narrow niche unlikely to fire for unrelated skills, satisfying the anchor 5 'clear niche with distinct triggers; minimal conflict risk'.	5 / 5
	Total	18 / 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/server-plugins/SKILL.md
Commit: cc2a915

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.