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

73%

Does it follow best practices?

Impact

94%

1.77x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/backend-development/skills/projection-patterns/SKILL.md

The canonical home for this skill is projection-patterns in wshobson/agents

Quality

Content

65%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 content is highly actionable with executable templates but front-loads too much inlined reference code into the overview and lacks an explicit build workflow with validation checkpoints for batch database operations. Splitting templates into reference files would improve both conciseness and progressive disclosure.

Suggestions

Move the five full projection templates into separate reference files (e.g., references/templates/) and keep only a concise quick-start example in SKILL.md, linking out to each template.

Add an explicit step-by-step workflow for building and deploying a projection (define handlers -> register -> run/rebuild -> verify lag and read-model state) with a validation checkpoint before considering a projection live.

Trim the repeated boilerplate across handler implementations (e.g., the per-event asyncpg connection blocks) to a shared helper to reduce token weight.

Dimension	Reasoning	Score
Conciseness	The body inlines five full Python templates (~250 lines of code) plus complete SQL handler implementations; while accurate, much of this reference bulk could be tightened or moved to separate files rather than held in the overview.	3 / 5
Actionability	The templates are fully executable, copy-paste-ready Python with real asyncpg SQL and Elasticsearch calls covering common projection cases (order summary, search, aggregation, multi-table).	5 / 5
Workflow Clarity	Projection building is a batch/database operation, yet the body provides no explicit step-by-step build workflow and no validation/verification checkpoints, so workflow clarity is capped at 3 per the destructive/batch guidance.	3 / 5
Progressive Disclosure	There is section structure (headers, a types table, an architecture diagram), but no bundle files exist and five full templates are inlined in SKILL.md that clearly belong in separate reference files, with only external URLs as navigation.	3 / 5
	Total	14 / 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 uses third-person voice, answers both what and when with concrete triggers, and carves out a clear niche. Its only weakness is modest action specificity, listing just two verbs.

Dimension	Reasoning	Score
Specificity	"Build read models and projections from event streams" names the domain with two concrete actions (build read models, build projections) but offers no broader action coverage, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	It clearly states what it does ("Build read models and projections from event streams") and explicitly answers when with concrete trigger phrases ("Use when implementing CQRS read sides, building materialized views, or optimizing query performance").	5 / 5
Trigger Term Quality	Natural domain terms like "CQRS read sides", "materialized views", "query performance", and "event-sourced systems" give good keyword coverage, though it lacks synonyms or file extensions for a comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The CQRS/event-sourcing projection niche is specific with distinct triggers, giving minimal overlap risk with other skills.	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: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/backend-development/skills/projection-patterns/SKILL.md
Commit: 6453c0b

Reviewed: about 9 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.