CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

52

Quality

56%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

Optimize this skill with Tessl

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

Quality

Content

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, repeating the same core message ('use real data, no placeholders') throughout multiple sections. The template structure is useful in concept but is presented as a massive inline placeholder skeleton rather than actionable guidance with concrete examples. The skill would benefit greatly from condensing, splitting the template into a separate reference file, and providing at least one concrete worked example of a transformation documentation output.

Suggestions

Reduce redundancy by consolidating the repeated 'no placeholders, only real data' messaging into a single concise constraint section instead of repeating it in 4+ places.

Move the large documentation template to a separate TEMPLATE.md file and reference it from SKILL.md to improve progressive disclosure and reduce the main file's length.

Add at least one concrete, complete example showing a small staging transformation (e.g., a real date standardization SQL snippet) and the corresponding documentation output, rather than only showing placeholder patterns.

Add explicit validation steps in the workflow, such as verifying extracted SQL parses correctly and checking that all config-referenced tables have corresponding documentation sections.

DimensionReasoningScore

Conciseness

Extremely verbose with significant redundancy. The template is a massive placeholder-filled skeleton that repeats 'Real SQL examples' and 'actual codebase' dozens of times. The 'When to Use' section, the mandatory codebase access warning, the template usage notes, and the summary all repeat the same points. Much of this could be condensed to a fraction of the size.

1 / 3

Actionability

Provides a detailed template structure and mentions specific file types (.dig, .sql, .yml), but contains no executable code, no concrete SQL examples, and no real commands beyond 'Use Glob to verify SQL files exist.' The template is full of placeholders like '{Real SQL examples}' rather than showing actual transformation patterns Claude could follow.

2 / 3

Workflow Clarity

There is a sequence implied: get codebase access → verify files exist → read files → follow template. However, the workflow for actually generating the documentation lacks explicit validation checkpoints. There's no step to verify extracted SQL is valid, no feedback loop for incomplete codebases, and the 'STOP if cannot read files' is the only checkpoint.

2 / 3

Progressive Disclosure

Monolithic wall of text with no references to external files despite the content being long enough to warrant splitting. The massive template could be a separate file. There are no bundle files to support the skill, and the entire template is inlined, making the skill unwieldy at ~180+ lines.

1 / 3

Total

6

/

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.

This is a strong, well-crafted description that clearly defines a specific niche (staging transformation documentation) with concrete capabilities. The 'Use when' clause is present and explicit, though the trigger terms lean heavily technical and could miss some natural user phrasings. The description is concise and avoids fluff while maintaining good specificity.

Suggestions

Expand trigger terms to include more natural user phrases such as 'staging layer docs', 'ETL documentation', 'data pipeline documentation', or 'dbt staging models' to improve discoverability.

DimensionReasoningScore

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 'when' clause is explicit though somewhat narrow.

3 / 3

Trigger Term Quality

Includes some relevant keywords like 'staging', 'transformation', 'SQL', 'Presto/Trino', 'Hive', 'PII', 'deduplication', and 'data quality rules'. However, these are fairly technical/domain-specific terms and the description misses more natural user phrases like 'document my ETL', 'staging layer docs', 'data pipeline documentation', or 'dbt staging'.

2 / 3

Distinctiveness Conflict Risk

Highly specific niche: staging transformation layer documentation with SQL engine detection. This is unlikely to conflict with other skills due to its narrow, well-defined domain focus on staging layers specifically.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
treasure-data/td-skills
Reviewed

Table of Contents

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.