reference-builder

Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/reference-builder/SKILL.md

Quality

Content

50%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-sectioned but verbose instruction skill: it offers one concrete entry-format template and a process sequence, yet most guidance is abstract placeholders and high-level best practices with no validation feedback loop or external reference files. It reads more like a checklist of documentation concepts than lean, executable instruction.

Suggestions

Cut the role-preamble and closing 'Remember' lines and replace abstract category lists with a single concrete worked example to improve conciseness and actionability.

Add an explicit validation feedback loop to the Reference Building Process (e.g., 'Validate entry against the actual interface; if mismatched, correct and re-validate') to lift workflow_clarity above 3.

Move the type-specific reference details (API/Configuration/Schema sections) into a separate REFERENCES.md and link to it from the body, so progressive disclosure reaches one-level-deep signaling.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with clear section headers, but includes padded material Claude already knows — the role preamble 'You are a reference documentation specialist...' and the closing 'Remember: Your goal is to create reference documentation that answers every possible question...' — plus abstract enumeration of categories; fits 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	The 'Entry Format' block is a concrete, copyable template, but much of the body is placeholder-laden ('[Feature/Method/Parameter Name]', '[Comprehensive description...]') and high-level hints ('Document behavior, not implementation'), leaving guidance partially concrete but incomplete — matching the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	The 'Reference Building Process' gives a clear 6-step sequence including a 'Validation' step, but validation is implicit/vague with no explicit feedback loop (validate -> fix -> retry) or checkpoint gating, fitting 'steps listed but validation gaps; checkpoints implicit'.	3 / 5
Progressive Disclosure	No bundle files exist and the ~187-line body inlines content (type-specific guidance, the full entry-format template) that could live in separate referenced files; structure is present via headers but references are absent and not signaled, matching 'some structure but could be better organized'.	3 / 5
	Total	12 / 20 Passed

Description

83%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 is strong: it states concrete capabilities and provides explicit, proactive trigger guidance covering both what the skill does and when to use it. Main weakness is slightly abstract action wording and a lack of synonym/extension coverage in trigger terms.

Suggestions

Add concrete synonym and file-extension triggers (e.g., 'API reference, .yaml/.json config specs, OpenAPI/Swagger docs') to lift trigger_term_quality toward 5.

Replace abstract verbs ('Creates exhaustive technical references') with more granular concrete actions to sharpen specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Creates exhaustive technical references and API documentation', 'Generates comprehensive parameter listings, configuration guides, and searchable reference materials' — with only minor gaps in coverage, fitting the 'lists several specific actions' anchor; not a 5 because the actions are still somewhat abstract rather than fully granular.	4 / 5
Completeness	Explicitly answers both 'what' ('Creates exhaustive technical references...Generates comprehensive parameter listings, configuration guides') and 'when' ('Use PROACTIVELY for API docs, configuration references, or complete technical specifications') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user-facing terms like 'API docs', 'configuration references', and 'complete technical specifications', giving good keyword coverage; not a 5 because it lacks common synonyms and file/extension variants users might say.	4 / 5
Distinctiveness Conflict Risk	The 'exhaustive technical references / API documentation' niche is mostly distinct from other skills with only minor overlap risk against general documentation skills; not a 5 because 'API docs' and 'configuration references' could still collide with adjacent doc-generation skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/reference-builder/SKILL.md
Commit: 3eff4af

Reviewed: 7 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.