CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rust-check

Run cargo check on the current Rust project to find compile errors

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./crates/tui/assets/plugins/rust-toolkit/skills/rust-check/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A short, appropriately sized body for a simple single-command skill: it gives an executable example command and a clear three-step sequence. Its main weaknesses are minor — slight redundancy with the description, vague "analyze/fix" steps without a verify-recheck loop.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows, but two lines could be trimmed: "Use this skill when you need to check for Rust compile errors" merely restates the frontmatter description, and "This skill is part of the rust-toolkit plugin." is organizational filler — fitting anchor 4 (minor instances that could be trimmed) rather than 5.

4 / 5

Actionability

The example command "cargo check --all-targets" is concrete and executable, and step 1 ("Run `cargo check` in the project root") is specific, but steps 2-3 ("Analyze the output for errors and warnings", "Fix any issues found") are high-level direction without specifics — mostly executable with minor gaps (anchor 4), not 5 since it does not cover common cases beyond the single command.

4 / 5

Workflow Clarity

The run → analyze → fix sequence is clearly ordered and the single action is unambiguous, but there is no re-check checkpoint after fixing (no "run cargo check again to verify"), a minor validation gap matching anchor 4; this is not a destructive or batch operation, so the score-3 cap does not apply, and the simple-skill 5 exception is undercut by the explicit multi-step workflow it claims without that checkpoint.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, has no need for external references (none exist in references/, scripts/, or assets/), and is organized into clearly labeled sections ("How to use:", "Example:"), which per the simple-skill guideline merits a 5 with just well-organized sections.

5 / 5

Total

17

/

20

Passed

Description

53%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 states a single concrete, distinctive action (running cargo check) but stops there: it lacks any "Use when..." trigger guidance and misses common trigger variations like "build errors" or "won't compile". It is a terse one-liner that works but leaves discovery and completeness on the table.

Suggestions

Add a "Use when..." clause, e.g., "Use when the user mentions Rust compile errors, a failing build, or wants to verify code compiles before committing."

Include natural trigger synonyms and terms users would actually say, such as "build errors", "won't compile", "does not compile", and "Cargo.toml".

Expand the capability description slightly to cover what the skill does with results (e.g., interpreting errors and warnings, not just running the command).

DimensionReasoningScore

Specificity

"Run cargo check" on "the current Rust project" to "find compile errors" names the domain and 1-2 concrete actions but is not comprehensive, matching anchor 3; it is not 4 because it does not list several specific actions, and not 2 because the action is concrete rather than generic.

3 / 5

Completeness

It has a clear "what" ("Run cargo check... to find compile errors") but no "when" clause at all; the guidelines explicitly cap completeness at 3 when a "Use when..." clause or equivalent trigger guidance is missing, so it cannot reach 4.

3 / 5

Trigger Term Quality

Relevant natural keywords are present ("cargo check", "compile errors", "Rust") but common variations and synonyms users would say are missing (e.g., "build errors", "won't compile", "rustc", "Cargo.toml"), matching anchor 3 rather than 4 whose keyword coverage is broad.

3 / 5

Distinctiveness Conflict Risk

Naming the specific cargo subcommand "cargo check" gives it a mostly distinct niche, but it carries minor overlap risk with closely related cargo skills (build, test, clippy) and provides no trigger phrases to disambiguate, fitting anchor 4 rather than the fully distinct anchor 5.

4 / 5

Total

13

/

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.

Repository

Hmbown/Codewhale

Path

crates/tui/assets/plugins/rust-toolkit/skills/rust-check/SKILL.md

Reviewed

Table of Contents

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.