projection-patterns

Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

Quality

53%

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 ./skills/projection-patterns/SKILL.md

Quality

Content

25%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.

The body is a generic, abstract stub with no executable guidance and a reference to a file that is not present. While token-light, it fails to deliver the concrete patterns and examples its own description promises.

Suggestions

Replace abstract directives with at least one concrete, executable projection example (e.g., a code snippet subscribing to an event stream and updating a read model table) so the skill is actionable.

Create the referenced resources/implementation-playbook.md or remove the reference; a broken pointer leaves the skill with no detailed material.

Replace the vacuous "Do not use this skill when the task is unrelated" line with substantive scope boundaries, and add explicit validation/verification checkpoints for projection rebuild and idempotency scenarios.

Dimension	Reasoning	Score
Conciseness	The body is short and does not over-explain concepts Claude already knows, but it includes vacuous filler such as "Apply relevant best practices and validate outcomes" and a "Do not use this skill when the task is unrelated" line that add no value. It is mostly token-efficient yet could be tightened into substance.	3 / 5
Actionability	The instructions are entirely abstract ("Clarify goals...", "Apply relevant best practices...", "Provide actionable steps and verification") with no concrete code, commands, or executable guidance. It only describes rather than instructs, matching the lowest anchor.	1 / 5
Workflow Clarity	A rough sequence exists (clarify goals, apply practices, verify) but the steps are generic and poorly defined with no concrete validation checkpoints. It sits above the no-sequence anchor (1) but well below a clearly sequenced workflow (3).	2 / 5
Progressive Disclosure	No bundle files exist and the body's only detailed reference, resources/implementation-playbook.md, does not exist on disk, leaving a stub pointing to a missing file. Structure is minimal and the reference is effectively broken rather than well-signaled.	2 / 5
	Total	8 / 20 Passed

Description

82%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.

The description is well-constructed: it clearly states the skill's purpose and provides explicit, domain-natural trigger conditions. Its only weakness is that the capability list is slightly narrow rather than comprehensive.

Dimension	Reasoning	Score
Specificity	"Build read models and projections from event streams" names the domain plus a couple concrete actions, but the action set is not comprehensive. It is above the domain-only anchor (2) but does not list several specific actions (4).	3 / 5
Completeness	It explicitly states what the skill does ("Build read models and projections from event streams") and gives an explicit "Use when..." clause with concrete trigger phrases. This matches the anchor that clearly and explicitly answers both what and when.	5 / 5
Trigger Term Quality	Phrases like "CQRS read sides", "materialized views", "query performance", and "event-sourced systems" are natural terms a user in this domain would actually say, giving good keyword coverage. It falls short of 5 because no synonyms or file-extension-style variants are included.	4 / 5
Distinctiveness Conflict Risk	The CQRS/event-sourcing read-side niche has distinct triggers and minimal overlap with other skills, making it unlikely to fire for the wrong skill. The triggers are specific enough to satisfy the clear-niche anchor.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/projection-patterns/SKILL.md
Commit: 3eff4af

Reviewed: 22 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.