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

81%

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

Quality

Content

82%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 lean, well-structured reference/decision skill: tables carry the bulk of the information, hard rules are unambiguous, and the actions-first workflow includes an explicit pre-check before creating a route. The only notable gap is the absence of a minimal concrete example (e.g., a plugin file's export shape) for the customize-a-plugin path.

Suggestions

Add a minimal example of a custom plugin file (export shape and where it lives in server/plugins/) so the 'customize a default plugin' path is copy-paste actionable like the rest of the guidance.

Consider trimming the slight redundancy between the Hard rule bullets ('Never put framework routes under /api/' vs 'ALL framework routes go under /_agent-native/') to tighten the top section.

Dimension	Reasoning	Score
Conciseness	Lean throughout: tables instead of prose, hard rules as terse bullets, and zero explanation of concepts Claude already knows (no 'what is a server plugin' padding, no library background). Every token earns its place.	5 / 5
Actionability	Concrete, executable decision rules with real paths and route names ('Only create plugin files for plugins you need to customize', 'use defineAction in actions/', files in server/plugins/, and the four legitimate custom-route cases). As an instruction-only skill the absence of code is acceptable, but a minimal plugin export example is missing — a minor gap that fits anchor 4.	4 / 5
Workflow Clarity	Clear decision sequence with an explicit pre-checkpoint ('Before adding a route, inspect the existing action files. Reuse the action if it already encodes the business rule...') and a default-then-exception flow (actions first, custom routes only for the enumerated cases). No destructive or batch operations, so the validation cap does not apply; it lacks only anchor 5's explicit validate/feedback loop.	4 / 5
Progressive Disclosure	Well-organized sections, an appropriately sized body, and a 'Related Skills' section for navigation; the inline route table is core content rather than misplaced reference material. No bundle files exist and none are needed; it sits just below anchor 5's clean overview-plus-one-level-references pattern only because there is nothing reference-shaped to split out or signal.	4 / 5
	Total	17 / 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 tight, well-scoped description with an explicit and multi-trigger 'Use when' clause and specific, natural terminology. Its main weakness is that the 'what' reads as a topic label rather than a statement of the skill's capabilities, and its route-vs-action trigger slightly overlaps a sibling skill.

Suggestions

Convert the topic fragment into a capability statement, e.g. 'Documents the default server plugins and the /_agent-native/ framework route namespace; explains when to customize each plugin and when /api/ routes are allowed.'

Add one or two natural synonyms for discoverability (e.g. 'endpoint', 'middleware', 'backend route') without lengthening the description.

Dimension	Reasoning	Score
Specificity	Names the domain plus three concrete, distinct scenarios ('adding a custom server plugin', 'deciding whether to create an `/api/` route vs an action', 'debugging auto-mounted framework routes'). Falls short of 5 because it states trigger scenarios rather than comprehensively listing what the skill itself does.	4 / 5
Completeness	Has an explicit 'Use when...' clause with three concrete triggers, but the 'what' ('Framework server plugins and the /_agent-native/ route namespace') is a topic fragment rather than an explicit capability statement — not the fully explicit what+when of anchor 5, but clearly above anchor 3.	4 / 5
Trigger Term Quality	Contains natural phrases a developer would actually say ('custom server plugin', '/api/ route vs an action', 'auto-mounted framework routes') plus the specific route namespace. A few natural synonyms (endpoint, middleware, backend route) are missing, so it fits anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche with highly specific triggers, but 'deciding whether to create an /api/ route vs an action' overlaps the sibling 'actions' skill's trigger space, so minor overlap risk keeps it at anchor 4 rather than 5.	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/server-plugins/SKILL.md
Commit: a941a2e

Reviewed: 9 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.