zig-docs

Fetches Zig language and standard library documentation via CLI. Activates when needing Zig API details, std lib function signatures, or language reference content that isn't covered in zig-best-practices.

1.50x

Quality

—

Does it follow best practices?

Impact

72%

1.50x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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 highly actionable, command-first reference with clear routing and fallback guidance. Its weaknesses are token efficiency (repeated full URLs and a redundant module-paths table) and a lack of progressive disclosure, since all reference material is packed into SKILL.md with no split-out detail files.

Suggestions

Define the Codeberg raw base URL once and list only the differing module suffixes, removing the ~10 repeated full-URL lines and shrinking the 'Common Module Paths' table to the part that isn't already implied by the URL pattern.

Move the extensive 'Common Module Paths' table and/or the per-task command catalog into a references file (e.g. references/module-paths.md) and keep SKILL.md as a concise overview pointing to it, giving one-level-deep progressive disclosure.

Collapse the duplicated base-URL examples in 'Fetch Standard Library Source' into a single parameterized example plus a short module list, since the URL pattern is already shown in the 'Documentation Sources' table.

Dimension	Reasoning	Score
Conciseness	Quotes the repeated full Codeberg raw URLs (e.g. the same 'codeberg.org/ziglang/zig/raw/branch/master/lib/std/<module>.zig' base restated ~10 times) and the 'Common Module Paths' table that largely duplicates the URL pattern — efficient and command-first, but tighten-able by defining the base URL once and listing only the differing module paths.	2 / 3
Actionability	Quotes fully executable commands like 'curl -sL "https://codeberg.org/ziglang/zig/raw/branch/master/lib/std/mem.zig"' and 'pandoc -f html -t plain "https://ziglang.org/documentation/master/"' plus worked search examples ('grep -A10 "pub fn create"'), all copy-paste ready with no pseudocode.	3 / 3
Workflow Clarity	Quotes the routing guidance in Instructions ('Use raw Codeberg sources for std lib... Use pandoc for language reference... avoid' the JS-rendered docs) and a fallback loop in Troubleshooting ('pandoc fails... fall back to curl + raw Codeberg'); for a simple single-purpose fetch skill this is a clear, sequenced decision path with error recovery.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), and the body is a single ~150-line monolithic catalog where tables like 'Common Module Paths' and all command examples live inline in SKILL.md rather than being split into a one-level-deep reference file — well-organized by headers, but content that should be separate is inline.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 is well-crafted: it states a concrete capability, gives an explicit activation trigger with natural user vocabulary, and proactively disambiguates from a related skill. The only gap is specificity — it describes one capability rather than enumerating several concrete actions.

Suggestions

To lift specificity, enumerate the concrete sub-actions the skill performs, e.g. 'Fetches Zig language and standard library documentation via CLI — fetches std lib source, extracts doc comments, lists module contents, and pulls prose from the language reference.'

Dimension	Reasoning	Score
Specificity	Quotes 'Fetches Zig language and standard library documentation via CLI' — it names a concrete action and domain but describes a single capability rather than listing multiple distinct concrete actions, so it sits at the 'names domain and some actions' anchor rather than the 'lists multiple specific actions' anchor.	2 / 3
Completeness	Quotes both the 'what' ('Fetches Zig language and standard library documentation via CLI') and an explicit 'when' trigger ('Activates when needing Zig API details, std lib function signatures, or language reference content'), satisfying the equivalent of a 'Use when...' clause.	3 / 3
Trigger Term Quality	Quotes 'Zig API details, std lib function signatures, or language reference content' — these are natural terms a Zig user would actually say (including the vernacular 'std lib'), giving good coverage rather than just 'some relevant keywords'.	3 / 3
Distinctiveness Conflict Risk	Quotes 'that isn't covered in zig-best-practices', which explicitly disambiguates this Zig-docs-fetching niche from a sibling skill, giving distinct triggers unlikely to cause conflicts.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 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.