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

56%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./aps-doc-skills/staging/SKILL.md

Quality

Discovery

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.

This is a strong, well-crafted description that clearly identifies a specific niche (staging transformation layer documentation) with concrete capabilities. It includes an explicit 'Use when' clause and is highly distinctive. The main weakness is that trigger terms lean heavily technical, which could miss some natural user phrasings.

Suggestions

Expand trigger terms to include more natural user phrases such as 'stg_ tables', 'staging models', 'data warehouse staging docs', or 'ETL documentation' to improve discoverability.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: auto-detects SQL engine (Presto/Trino vs Hive), documents transformation rules, PII handling, deduplication strategies, and data quality rules. These are concrete, well-defined capabilities.	3 / 3
Completeness	Clearly answers both 'what' (auto-detects SQL engine, documents transformation rules, PII handling, deduplication strategies, data quality rules) and 'when' ('Use when documenting staging transformations'). The 'Use when...' clause is present and explicit, though it could be slightly more detailed with additional trigger scenarios.	3 / 3
Trigger Term Quality	Includes some relevant keywords like 'staging', 'transformation', 'SQL', 'Presto/Trino', 'Hive', 'PII', 'deduplication', and 'data quality rules', but these are fairly technical terms. Missing more natural user phrases like 'document my staging layer', 'stg_ tables', or 'data warehouse documentation'.	2 / 3
Distinctiveness Conflict Risk	Highly specific niche: staging transformation layer documentation with SQL engine detection. The combination of 'staging', 'transformation layers', and specific technical concerns (PII, deduplication) makes this very unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Implementation

27%

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

This skill is excessively verbose, with a large inline template full of placeholder comments that add little actionable value. The repeated emphasis on 'real data, no placeholders' is ironic given the template itself is entirely placeholders. The content would benefit greatly from being condensed, splitting the template into a separate file, and adding concrete executable examples of SQL extraction or transformation documentation.

Suggestions

Move the documentation template to a separate TEMPLATE.md file and reference it from SKILL.md with a brief description of its structure.

Replace the repetitive '{Real SQL examples from transformation files}' placeholders with 1-2 concrete before/after examples showing how actual SQL gets transformed into documentation.

Consolidate the redundant sections—the 'When to Use', 'Summary', and 'Template Usage Notes' all repeat the same information. Keep one concise overview.

Add explicit validation steps: e.g., after generating documentation, verify all table names exist in the codebase, verify SQL examples are syntactically valid, check that all config entries are documented.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with significant redundancy. The template is a massive placeholder-filled skeleton that repeats 'Real SQL examples' and 'from actual codebase' dozens of times. The 'MANDATORY: Codebase Access Required' section over-explains obvious constraints. The summary repeats what was already stated. Much of this content could be condensed to a fraction of its size.	1 / 3
Actionability	The template provides a concrete structure to follow, and the workflow mentions specific file types (.dig, .sql, .yml) and tools (Glob). However, there are no executable code examples, no actual SQL snippets, no real commands to run, and the template is entirely placeholders rather than concrete, copy-paste-ready guidance.	2 / 3
Workflow Clarity	There is a rough sequence (ask for path → verify files exist → read files → generate documentation following template), but validation checkpoints are minimal. There's no explicit feedback loop for verifying documentation accuracy against the codebase, no checklist for completeness verification, and the steps for the actual documentation process are implicit rather than explicitly sequenced.	2 / 3
Progressive Disclosure	The entire skill is a monolithic wall of text with no references to external files. The massive template (which constitutes the bulk of the content) should be in a separate reference file. There's no layering—everything is dumped inline with no navigation structure or separation of overview from detailed reference material.	1 / 3
	Total	6 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: treasure-data/td-skills
Commit: 79bb9b8

Reviewed: 2 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.