north-star

Constitutional source of truth for reusable Plate architecture and public API design. Use when introducing or changing reusable public APIs, runtime/service boundaries, builder or factory patterns, extension registration contracts, naming/layering rules, or performance-sensitive architecture.

Quality

63%

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/north-star/SKILL.md

Quality

Content

42%

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

The body is well-structured and lean, but its progressive disclosure is broken because every Constitutional Layer and Pattern Layer reference points to a missing file, and the workflow lacks explicit validation feedback loops. Routing content is also restated across three redundant sections.

Suggestions

Restore or provide the missing rules/*.md files (laws, decision-ladder, performance-selection-rules, update-policy, pattern-catalog, anti-patterns) so the signaled references resolve to real content.

Merge the redundant Hard Routing Rule, Routing Matrix, and Who Owns What sections into a single routing/ownership table to tighten token efficiency.

Convert the Binary Review Checklist into an explicit validation feedback loop (check → if fail, return to the relevant step → only proceed when all checks pass) to add a real checkpoint to the workflow.

Dimension	Reasoning	Score
Conciseness	The prose is lean and avoids explaining concepts Claude already knows, but the Hard Routing Rule, Routing Matrix, and Who Owns What sections restate the same routing/ownership decisions three times, adding redundant tokens.	2 / 3
Actionability	As an architecture-doctrine skill it legitimately lacks code, but the guidance is mostly abstract directives ("Run the decision ladder", "separate matcher logic from feature semantics") with only the Matcher Extraction Heuristic giving concrete, specific criteria.	2 / 3
Workflow Clarity	The eight-step Workflow is clearly sequenced, but validation is represented only by a static Binary Review Checklist rather than an explicit validate-then-fix-then-retry feedback loop, leaving checkpoints implicit.	2 / 3
Progressive Disclosure	The body is well organized with one-level-deep, clearly signaled references, but all six referenced files (laws.md, decision-ladder.md, performance-selection-rules.md, update-policy.md, pattern-catalog.md, anti-patterns.md) are missing from the bundle, so navigation points to non-existent content.	1 / 3
	Total	7 / 12 Passed

Description

85%

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 precise, well-triggered description with a clear distinct niche; its only weakness is reliance on architectural jargon that users may not phrase naturally. It answers both what and when.

Suggestions

Add more user-natural trigger phrasings alongside the technical terms (e.g., "Use when designing a plugin's public API" or "when deciding where a reusable helper belongs") to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete architectural actions — "introducing or changing reusable public APIs, runtime/service boundaries, builder or factory patterns, extension registration contracts, naming/layering rules" — matching the multi-action anchor rather than a single vague phrase.	3 / 3
Completeness	It states both what the skill is ("Constitutional source of truth for reusable Plate architecture and public API design") and when to use it ("Use when introducing or changing reusable public APIs...") via an explicit "Use when" trigger clause.	3 / 3
Trigger Term Quality	"Use when introducing or changing a reusable public API" is a natural trigger, but the surrounding phrasing leans on architectural jargon ("constitutional source of truth", "extension registration contracts") that a user is less likely to say verbatim, so common natural variations are partially missing.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to reusable Plate API/runtime doctrine and it explicitly routes implementation work away to sibling skills, making a wrong-skill trigger unlikely.	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
relative_links	Relative link issues: 12 missing, 6 suspicious	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/north-star/SKILL.md
Commit: 45116fd

Reviewed: about 14 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.