aps-doc-staging

Expert documentation generation for staging transformation layers. Auto-detects SQL engine (Presto/Trino vs Hive), documents transformation rules, PII handling, deduplication strategies, and data quality rules. Use when documenting staging transformations.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body establishes a strong codebase-access gate and a usable template, but is verbose and repetitive, relies on placeholder-heavy guidance, and lacks validation feedback loops for the documentation workflow. Splitting the template into a reference file and tightening redundancy would lift several dimensions.

Suggestions

Move the large documentation template into a separate reference file (e.g., references/TEMPLATE.md) and link to it from SKILL.md to improve progressive_disclosure and conciseness.

Add explicit validation/feedback checkpoints to the workflow — e.g., verify extracted SQL compiles and table/column names match the config before finalizing the doc — to raise workflow_clarity.

Replace '{placeholder}' template fields with at least one fully worked, real example document so the guidance is executable and copy-paste ready, improving actionability.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but repetitive: 'NO generic placeholders' is restated in the access gate, Template Usage Notes, and Summary, and the Summary restates the intro. Not 1 because it avoids explaining concepts Claude already knows; not 3 because of the redundancy.	2 / 3
Actionability	Gives a concrete template structure and tooling hints (Glob, .dig/.sql/.yml), but the core guidance is a template of '{placeholder}' fields rather than executable, copy-paste-ready instructions. More concrete than score 1, but placeholders keep it below 3.	2 / 3
Workflow Clarity	Provides a sequenced pre-flight (ask path → Glob verify → STOP if unreadable), but lacks validation/feedback checkpoints for the documentation work itself; per the rubric, missing validation steps cap this at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the ~210-line SKILL.md is monolithic with a large inline template that could be a separate reference file. Some structure exists, but content that should be separate is inline, so it sits at 2.	2 / 3
	Total	8 / 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.

A clear, third-person description that states concrete capabilities and an explicit 'Use when' trigger, with a well-scoped niche. Its main weakness is limited trigger-term variation, which keeps trigger quality at 2.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Auto-detects SQL engine (Presto/Trino vs Hive)', 'documents transformation rules, PII handling, deduplication strategies, and data quality rules'. Not 2 because it enumerates five distinct actions rather than just naming the domain.	3 / 3
Completeness	Explicitly states what it does (documents transformation rules, PII handling, etc.) and when to use it ('Use when documenting staging transformations'). Clear 'what' and 'when' with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes the trigger 'Use when documenting staging transformations' but offers only one phrasing; lacks common variations a user might say (e.g., ETL docs, data cleaning docs, staging layer). Not 3 because coverage is narrow, not 1 because relevant keywords are present.	2 / 3
Distinctiveness Conflict Risk	Narrow niche — staging transformation layers with specific SQL-engine detection (Presto/Trino vs Hive) — making it unlikely to trigger 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.