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

78%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 well-structured overview with executable commands, a genuine verify-fix-reverify feedback loop, and properly signaled one-level-deep references. It falls just short of top marks on conciseness (some redundant cautionary restatements), actionability (SMT request example deferred entirely to a reference file), and workflow clarity (sequence expressed in prose rather than explicit checkpoints).

Suggestions

Consolidate the three overlapping don't-over-claim sentences in 'Read the evidence' into a single freshness/verdict checklist to cut redundant tokens.

Inline a minimal query.json example next to 'sail runtime execute --file query.json' so the primary SMT workflow is fully executable without opening references/smt.md.

Render the verify-revise-reverify loop as a short numbered sequence with the scope/currentness check as an explicit validation step before reporting success.

DimensionReasoningScore

Conciseness

Overall lean with executable commands and no beginner-concept padding, but the 'Read the evidence' section restates the don't-over-claim caution three ways (e.g. 'Current describes freshness, not success', 'solver installation readiness alone is not a result about the formula') — minor trimming would fit anchor 5.

4 / 5

Actionability

Mostly executable with copy-paste commands ('sail verify --output json', 'sail new --lib demo', 'sail runtime execute --file query.json'), but the SMT request payload structure is not shown inline — it is deferred to references/smt.md — leaving a minor gap versus anchor 5's fully covered common cases.

4 / 5

Workflow Clarity

The verify-revise-reverify feedback loop and the scope/currentness validation checkpoint are both present ('Use the failure locations and diagnostics to revise the code or proof, then verify again'), but the sequence is prose rather than explicit numbered steps or a checklist, so it sits below anchor 5.

4 / 5

Progressive Disclosure

A concise ~60-line overview whose two references (references/verus.md, references/smt.md, both present in the bundle) are one level deep and well signaled with content descriptions ('for standalone files, MCP, background preparation, explicit jobs, proof-repair checks and cache management') — matching the anchor-5 pattern.

5 / 5

Total

17

/

20

Passed

Description

95%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 'Use when...' clause with natural trigger phrases, and a clearly distinguished tooling niche. The only weakness is minor coverage gaps around secondary capabilities such as project scaffolding and cache management.

DimensionReasoningScore

Specificity

Lists three concrete actions ('Verify Rust with Verus', 'check proof repairs', 'run cached Z3 queries with Sail') matching anchor 4's 'several specific actions; minor gaps in coverage' — secondary capabilities like new-library scaffolding and cache management are not mentioned, keeping it below anchor 5's comprehensive coverage.

4 / 5

Completeness

Explicitly answers both questions: the first sentence states what the skill does, and the 'Use when...' clause gives three concrete trigger phrases, matching the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Natural user phrasing is comprehensively covered: 'cargo verus verify is slow', 'developing Verus proofs', 'SMT-LIB solver access', 'Z3', 'CLI or MCP' — these are exactly the phrases a user would say when needing this skill, with domain synonyms present.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Verus proofs, Z3/SMT-LIB solving, Sail caching) with distinct triggers tied to named tools; virtually no overlap risk with generic Rust or testing skills.

5 / 5

Total

19

/

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