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.

1.77x

Quality

—

Does it follow best practices?

Impact

94%

1.77x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

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 content is highly actionable with executable, copy-paste-ready projection templates, but it is a monolithic 486-line document with repetitive code and no validation-gated workflow for the batch rebuild operation.

Suggestions

Consolidate the repeated connection-acquire and handler-dispatch boilerplate across Templates 2, 4, and 5 into a shared base/helper, or keep one full example and abbreviate the rest.

Add a sequenced rebuild workflow with an explicit validation checkpoint (e.g., verify checkpoint/row counts before declaring a rebuild complete) since rebuilding projections is a destructive batch operation.

Move the larger code templates into reference files under references/ (which do not yet exist) and leave concise overview snippets plus one-level-deep links in SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — it does not explain concepts Claude already knows — but the five near-identical projections repeat boilerplate (acquire-connection, handler-dispatch, SQL-update shape) that could be consolidated, padding the token budget.	2 / 3
Actionability	Templates are fully executable Python with real SQL and real library calls (asyncpg, AsyncElasticsearch) and concrete data shapes, making them copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Templates show structure and 'Best Practices' lists checkpoints/rebuild/monitoring as bullets, but there is no sequenced workflow with validation/feedback loops around the batch, destructive rebuild operation, capping it at 2.	2 / 3
Progressive Disclosure	No bundle files exist and all 486 lines are inline in one monolithic SKILL.md; sections are well-organized with headings, but the heavy code templates that could live in separate references are all inline, so it is not a 3.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, concise description that clearly states concrete capabilities and provides explicit, domain-appropriate 'Use when' triggers. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ('Build read models and projections', 'building materialized views', 'optimizing query performance'), matching the anchor for listing several concrete actions rather than just naming a domain.	3 / 3
Completeness	Explicitly answers both what ('Build read models and projections from event streams') and when via an explicit 'Use when...' clause with multiple triggers, matching the anchor that requires both with explicit triggers.	3 / 3
Trigger Term Quality	Triggers ('CQRS read sides', 'materialized views', 'query performance', 'event-sourced systems', 'event streams') are the natural terms a developer would say in this niche, giving good coverage rather than just 'some relevant keywords'.	3 / 3
Distinctiveness Conflict Risk	The CQRS/event-sourcing projection niche is clearly distinct with niche-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: Dicklesworthstone/pi_agent_rust
Commit: abece4a

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.