CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

exploring-rust-crates

Generate Rust documentation to understand crate APIs, structure, and usage. Use when exploring Rust code, understanding crate organization, finding functions/types/traits, or needing context about a Rust package in the HASH workspace.

71

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

SKILL.md
Quality
Evals
Security

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 lean, fully executable skill: both cargo doc invocations, flag explanations, and the output path are all a reader needs to act. Its only weakness is two short sections that explain rustdoc conventions and obvious tips Claude already knows, which add tokens without adding information.

Suggestions

Delete or compress 'What Generated Docs Provide' — Claude already knows what rustdoc output contains (public API, trait impls, doctests); at most keep a one-line note like 'doctests and # Errors sections document usage and failure modes'.

Trim the Tips section to the non-obvious ones only; 'Generate docs before diving into unfamiliar Rust code' restates the skill's purpose.

If more depth is ever needed (e.g., parsing the generated HTML in a headless environment, or using --document-private-items selectively), move it to a references/ file rather than expanding the body.

DimensionReasoningScore

Conciseness

The command sections ('cargo doc --no-deps --all-features --package <package-name>', '--workspace', flags, output path) are tight, but 'What Generated Docs Provide' spends five bullets explaining what rustdoc output contains ("Public API surface - All public functions, types, traits, and constants", "Type relationships - Trait implementations, type aliases") — concepts Claude already knows — and tips like "Generate docs before diving into unfamiliar Rust code" and "Look for # Examples sections for idiomatic usage patterns" restate rustdoc conventions. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened'; it is not level 2 because the padding is confined to two short sections and the operative content carries no filler, and not level 4 because the unnecessary sections are recognizably over-explanation rather than minor trims.

3 / 5

Actionability

The skill gives copy-paste-ready commands for both common cases — per-package ('cargo doc --no-deps --all-features --package <package-name>') and whole-workspace ('cargo doc --no-deps --all-features --workspace') — documents each flag's effect ('--no-deps: Document local code only', '--document-private-items: Include internal implementation details'), and gives the exact output location 'target/doc/<crate_name>/index.html'. This matches the 'fully executable; copy-paste ready; specific examples cover the common cases' anchor; level 4 would require a noticeable gap, and none is present.

5 / 5

Workflow Clarity

This is a simple, non-destructive, single-purpose skill and the single action is unambiguous: generate docs (per-package or workspace variants both shown), then read them at the stated path. Per the simple-skill guidance the flow can score 5 when unambiguous, and no validation/feedback loop is needed since 'cargo doc' is read-only. Not level 4 because there are no 'minor validation gaps' — nothing here needs validation.

5 / 5

Progressive Disclosure

The body is 47 lines, no bundle files exist (no references/, scripts/, or assets/), and there is nothing here that warrants external files. Per the guideline that skills under 50 lines with no need for external references can score 5 with well-organized sections, the headed structure (Generating Documentation / What Docs Provide / Viewing Documentation / Tips) qualifies. Not level 4 because there are no organization gaps or misplaced inline content.

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: third-person voice, explicit 'Use when...' triggers covering multiple natural scenarios, and a clearly scoped Rust-crate niche. Its only gap is that the specificity and trigger coverage omit common phrasings like 'rustdoc' or 'Rust docs' that users would naturally say.

DimensionReasoningScore

Specificity

It lists several concrete actions and objects: 'Generate Rust documentation to understand crate APIs, structure, and usage' plus 'finding functions/types/traits'. This matches 'lists several specific actions; minor gaps in coverage' — the mechanism (cargo doc/rustdoc) and the distinction between generating vs. reading docs are left unstated. Not 3, since more than 1-2 concrete actions are named; not 5, since coverage of what the skill actually does is incomplete (the generated-docs lookup step is only implied).

4 / 5

Completeness

Both halves are explicit: what — 'Generate Rust documentation to understand crate APIs, structure, and usage'; when — 'Use when exploring Rust code, understanding crate organization, finding functions/types/traits, or needing context about a Rust package in the HASH workspace'. This matches the anchor 'clearly and explicitly answers both what AND when with concrete trigger phrases'. Not 4, because the 'when' clause is not merely adequate but enumerates four concrete triggering scenarios.

5 / 5

Trigger Term Quality

Natural trigger phrases are present: 'exploring Rust code', 'understanding crate organization', 'finding functions/types/traits', 'Rust package'. This is good keyword coverage matching anchor 4; a few natural terms are missing — users would plausibly say 'rustdoc', 'Rust docs', or mention 'Cargo.toml'/crate names. Not 5 because those common variations/synonyms are absent; not 3 because the core natural phrasing users would actually use is there.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche — Rust crate documentation in the HASH workspace — with distinct triggers ('crate APIs', 'crate organization', 'Rust package') that a general code-exploration or language skill would not claim. This matches 'clear niche with distinct triggers; minimal conflict risk'. Not 4 because the overlap risk with other skills is minimal, not just minor.

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.

Repository

hashintel/hash

Path

.agents/skills/exploring-rust-crates/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.