aps-doc-golden

Expert documentation generation for golden layers. Detects SCD types, documents business rules, metric definitions, aggregation logic, and data quality scoring. Use when documenting golden layer tables.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

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 skill delivers a concrete, well-structured documentation template with a strong upfront validation gate, but it is verbose and monolithic — the large templates are inlined rather than progressively disclosed into separate reference files.

Suggestions

Move the large parent-page and child-page template blocks into separate reference files (e.g. references/parent_template.md, references/attribute_template.md, references/behavior_template.md) and keep SKILL.md as an overview that links to them, improving progressive disclosure and token efficiency.

Tighten the repeated placeholder scaffolding (e.g. the per-attribute block) into a single concise schema rather than restating full markdown structure multiple times.

Dimension	Reasoning	Score
Conciseness	The body is mostly purposeful but runs ~380 lines of repeated placeholder-laden template blocks ('{table_name}', '{X} attributes') that could be tightened; it earns its place as a template skill but is padded rather than lean.	2 / 3
Actionability	For an instruction-only skill the guidance is highly concrete: an exact, copy-paste-ready template structure plus explicit directives ('Read actual .dig workflows and .sql files', 'Dynamically discover all attribute and behavior tables', 'NO generic placeholders'). The scoring note exempts instruction-only skills from requiring executable code when guidance is actionable.	3 / 3
Workflow Clarity	Provides an explicit validation gate before risky work — 'Ask for codebase path if not provided', 'Use Glob to verify files exist', 'STOP if cannot read files' — with a clear sequencing and a hard checkpoint, satisfying the feedback-loop requirement for batch/destructive-style operations.	3 / 3
Progressive Disclosure	No bundle files (references/, scripts/, assets/) exist and the entire large template is inline in SKILL.md; sections are organized, but the multi-hundred-line parent/child templates are monolithic and would benefit from being split into one-level-deep reference files rather than kept inline.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 specific, third-person, and clearly states both what it does and when to use it. Its main weakness is trigger-term breadth: the keywords are domain jargon that may not match a user's natural phrasing.

Suggestions

Broaden trigger terms with more natural phrasings a user might say, e.g. 'Use when documenting data warehouse golden layer tables, customer 360 tables, or SCD implementations, or generating Confluence documentation for analytics-ready tables.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Detects SCD types, documents business rules, metric definitions, aggregation logic, and data quality scoring' — matching the level-3 anchor of naming several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' ('Expert documentation generation for golden layers. Detects SCD types...') and 'when' ('Use when documenting golden layer tables.'), with a clear explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Relevant domain terms ('golden layers', 'golden layer tables', 'SCD') are present, but these are niche jargon and common natural variations a user might say (e.g. 'data warehouse', 'CDP', 'Confluence docs') are missing, so coverage is partial rather than strong.	2 / 3
Distinctiveness Conflict Risk	Targets a distinct niche — golden layer analytics documentation — with triggers ('golden layer tables', 'SCD types') that are unlikely to fire for unrelated skills.	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: treasure-data/td-skills
Commit: 50d5a57

Reviewed: 8 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.