CtrlK
BlogDocsLog inGet started
Tessl Logo

aps-doc-master-segment

Generate Confluence-ready technical documentation for CDP Parent Segments. Produces structured docs covering attribute schemas, behavior definitions, star schema relationships, and data lineage. Use when you need to write docs, create specs, or explain parent segment architecture.

55

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./aps-doc-skills/master-segment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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.

A highly actionable, well-sequenced instruction set undermined by heavy redundancy — the MCP/tdx fallback logic is repeated five times — and by a monolithic structure that inlines a 240-line template with no external references. Consolidating the duplicated access instructions and splitting the template into a reference file would lift both weak dimensions.

Suggestions

State the TD-MCP-preferred / tdx-fallback logic once (e.g., in a short 'Database Access' section) and have Phases 1–2 reference it instead of repeating the if/else branches verbatim.

Move the ~240-line documentation template to references/template.md and link to it, keeping SKILL.md as an overview of the three phases.

Add one concrete TD MCP tool invocation example and a sample SQL query so the preferred access path is as executable as the tdx path.

DimensionReasoningScore

Conciseness

The TD-MCP-vs-tdx fallback is restated roughly five times (Methods 1/2, 'Before proceeding', Phases 1 and 2, Key Principles, Summary, and 'Fallback Strategy'), and the 'When to Use' section duplicates the frontmatter description. This repetition is pervasive padding, though the file avoids explaining concepts Claude already knows.

2 / 5

Actionability

Provides concrete tdx commands ('tdx use database cdp_audience_<id>', 'tdx describe <table>'), explicit SQL ('SHOW TABLES IN', 'DESCRIBE'), and a detailed template with conditional generation rules. Minor gaps: the preferred MCP path is vague ('mcp__treasuredata__* tools' with no actual tool calls) and 'Working SQL examples' is mandated without any example shown.

4 / 5

Workflow Clarity

Phases 1–3 (discovery → schema extraction → generation) are clearly sequenced with checkpoints ('Confirm master segment database exists', 'STOP if cannot access database'). No error-recovery guidance exists for failure cases like an empty schema or ambiguous master table, keeping it below a 5; the operations are read-only queries, so the destructive/batch cap does not apply.

4 / 5

Progressive Disclosure

No bundle files exist and the ~240-line documentation template is inlined directly in SKILL.md where it clearly belongs in a references/ file. Real section headers and a navigable structure keep this above the minimal-structure anchor.

3 / 5

Total

13

/

20

Passed

Description

67%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.

A solid description with explicit what/when structure and a well-defined niche. Its main weakness is trigger coverage: it omits 'master segment' — the term the skill body itself uses most — along with other natural user phrasings.

Suggestions

Add 'master segment' and 'CDP audience' to the 'Use when' clause, since the body treats them as synonyms for Parent Segment and users will say them.

Mention the concrete mechanism (querying CDP audience database schemas via TD MCP or tdx) so the what-clause covers the skill's actual work, not just its output.

DimensionReasoningScore

Specificity

Lists several concrete actions and output areas ('Generate Confluence-ready technical documentation', 'attribute schemas, behavior definitions, star schema relationships, and data lineage') with minor gaps — it never mentions the database-schema querying or SQL examples the skill actually performs.

4 / 5

Completeness

Explicitly answers both what (generates structured docs covering four named areas) and when ('Use when you need to write docs, create specs, or explain parent segment architecture'), though the when-clause is generic and could use more concrete trigger phrasing.

4 / 5

Trigger Term Quality

Includes some relevant keywords ('write docs', 'create specs', 'Confluence', 'parent segment') but misses common variations — 'master segment' (the skill's own primary term), 'CDP audience', and 'segment documentation' never appear as triggers.

3 / 5

Distinctiveness Conflict Risk

Clear niche (CDP Parent Segments documentation for Confluence) makes wrong-skill triggering unlikely, but the broad 'write docs, create specs' phrasing creates minor overlap with generic documentation skills.

4 / 5

Total

15

/

20

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.

Validation — 16 / 16 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.