salsa

Mental-model reset for Salsa, the incremental computation framework for Rust. Use when building or reviewing Salsa databases, tracked functions, input/ tracked/interned structs, query pipelines, accumulators, cancellation, durability, LSP integration, memory management, cycles, or production Salsa architecture. Triggers on #[salsa::db], #[salsa::input], #[salsa::tracked], #[salsa::interned], #[salsa::accumulator], salsa::Storage, memoization, revisions, backdating, red-green algorithm, WillExecute, DidValidateMemoizedValue, Cancelled, returns(ref), no_eq, lru, cycle_fn, cycle_result, durability, or salsa::Event.

1.66x

Quality

82%

Does it follow best practices?

Impact

95%

1.66x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

65%Weight 40%Scale 1-3

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

The body is actionable and conceptually well organized with concrete Rust examples and clear progressive-disclosure intent, but it is padded by a lengthy project inventory/vocabulary and most deep-dive reference links are broken because the actual content lives under references/<topic>/ directories rather than the bare filenames cited.

Suggestions

Fix deep-dive links to point at the real files (e.g. references/database-architecture/salsa-framework.md) or add index files at the bare paths the body cites, so every '→ Deep dive' and navigation-table link resolves.

Trim or move the 'Real-World Scale' project inventory and 'Key Vocabulary' into a reference file so the SKILL.md body stays lean.

Add an explicit validate-then-fix feedback loop (e.g. for cancellation/cycle or database-mutation workflows) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	Code and core explanations are lean and assume competence, but the 'Real-World Scale' inventory of nine project blurbs and the 'Key Vocabulary' glossary add tokens that Claude largely does not need to act on the skill.	2 / 3
Actionability	Provides concrete, copy-paste-ready Rust for database setup, inputs, tracked functions, tracked/interned structs, and accumulators (e.g. 'Diagnostics::push(db, ...)') with specific attribute usage.	3 / 3
Workflow Clarity	The core loop is sequenced (create inputs → compute → mutate → re-compute) but there are no explicit validation checkpoints or error-recovery feedback loops for the fragile operations the skill references.	2 / 3
Progressive Disclosure	Overview is well structured with '→ Deep dive' signposts and a navigation table, but the referenced bare paths (e.g. database-architecture.md, query-pipeline.md, struct-selection.md, cycle-handling.md) do not exist; only references/overview/minimal-example.md resolves to a real file.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that concretely enumerates capabilities and triggers with excellent keyword coverage for Salsa-specific concepts. It clearly answers both what the skill does and when to use it, with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability areas: 'building or reviewing Salsa databases, tracked functions, input/tracked/interned structs, query pipelines, accumulators, cancellation, durability, LSP integration, memory management, cycles'.	3 / 3
Completeness	Explicitly answers both 'what' ('Mental-model reset for Salsa') and 'when' via an explicit 'Use when ...' clause plus a 'Triggers on ...' enumeration.	3 / 3
Trigger Term Quality	Strong natural-term coverage including 'Triggers on #[salsa::db], #[salsa::input], #[salsa::tracked], #[salsa::interned], #[salsa::accumulator], salsa::Storage, memoization, revisions, backdating, red-green algorithm, WillExecute, DidValidateMemoizedValue, Cancelled, returns(ref), no_eq, lru, cycle_fn'.	3 / 3
Distinctiveness Conflict Risk	Highly Salsa-specific niche with distinctive macro/attribute triggers (e.g. '#[salsa::db]', 'salsa::Storage', 'red-green algorithm') making it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 17 missing, 1 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 2 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: joshuadavidthomas/agent-skills
Path: salsa/SKILL.md
Commit: 516dee7

Reviewed: 11 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.