CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

jeffreykent/sail-verification

Verify Rust with Verus, check proof repairs, and run cached Z3 queries with Sail. Use when cargo verus verify is slow, when developing Verus proofs, or when giving coding agents SMT-LIB solver access through the CLI or MCP.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

85%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.

A well-constructed skill body: lean overview, executable commands, explicit verify-again feedback loops and evidence-validation checkpoints, and clean two-file progressive disclosure with real, accurately described references. The small deductions are for slight intro redundancy and for deferring the SMT request example and repair-check command entirely to references.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — it never explains what Verus, Z3, or SMT-LIB are — and every sentence in "Read the evidence" carries a distinct rule. Minor trimmable instances remain, e.g. "It also runs SMT-LIB queries through bundled Z3 with a persistent result cache" partially repeats the frontmatter description, keeping it just below the lean anchor-5 bar.

4 / 5

Actionability

Gives copy-paste commands for the primary workflow ("sail verify --output json", "sail new --lib demo", "sail runtime capabilities", "sail runtime execute --file query.json") with error-recovery paths for missing Sail or runtime. The SMT request body and repair-check command live only in the reference files, leaving a minor gap that fits anchor 4 rather than the fully self-contained common-case coverage of anchor 5.

4 / 5

Workflow Clarity

Each workflow has a clear sequence with an explicit feedback loop ("Use the failure locations and diagnostics to revise the code or proof, then verify again") and explicit validation checkpoints ("check scope and currentness before reporting success", "Verify again after further edits", "solver installation readiness alone is not a result about the formula"), plus recovery guidance for missing installs. This matches anchor 5; anchor 4 would require missing or merely implicit checkpoints, which is not the case.

5 / 5

Progressive Disclosure

The body is a concise overview with two well-signaled, one-level-deep references ([Verus workflows](references/verus.md) and [SMT requests](references/smt.md)), both of which exist in the bundle, accurately match their in-body descriptions, and do not nest further bundle references (only external docs). Content is appropriately split and navigation is easy, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Description

87%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.

A strong description: concrete third-person actions, an explicit multi-trigger "Use when" clause, and a well-delineated niche with low conflict risk. The only weaknesses are minor coverage gaps in the action list and a few missing natural synonyms such as "formal verification".

DimensionReasoningScore

Specificity

Lists three concrete actions — "Verify Rust with Verus", "check proof repairs", and "run cached Z3 queries with Sail" — matching the anchor for several specific actions with minor gaps. Not 5 because capabilities like project scaffolding and watch/background verification are unlisted; not 3 because the actions named are specific rather than generic.

4 / 5

Completeness

Explicitly answers both parts: the what ("Verify Rust with Verus, check proof repairs, and run cached Z3 queries with Sail") and the when ("Use when cargo verus verify is slow, when developing Verus proofs, or when giving coding agents SMT-LIB solver access through the CLI or MCP") with three concrete trigger phrases in third person. This matches the anchor-5 example structure exactly; anchor 4 would require a vaguer or less explicit when-clause.

5 / 5

Trigger Term Quality

Natural domain phrasing is present ("cargo verus verify is slow", "developing Verus proofs", "SMT-LIB solver access") alongside tool names Verus, Z3, and MCP. A few natural synonyms like "formal verification" or "theorem proving" are missing, which fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche — Verus proof verification with answer caching and bundled-Z3 SMT execution via Sail — with triggers (cargo verus verify, Verus proofs, SMT-LIB) that would not fire for unrelated skills. Minimal conflict risk, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

100%

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.

Reviewed

On this page