aps-doc-ingestion

Expert documentation generation for ingestion layers. Automatically detects connector types (REST API, Database, File, Streaming), documents authentication patterns, rate limiting strategies, and incremental load patterns. Use when documenting data source ingestion workflows.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

55%

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

The skill has an excellent validation-driven workflow for requiring real codebase access, but it is verbose and monolithic. Concept re-explanation inflates token cost and the large template/detection detail should live in separate reference files.

Suggestions

Move the per-connector 'Detects/Documents' detection tables and the full documentation template into separate reference files (e.g. references/template.md, references/connector-patterns.md) and link to them, so SKILL.md stays a lean overview.

Cut concept re-explanation: assume Claude knows what OAuth, Kafka, and incremental watermarking are and keep only the skill-specific extraction rules and required output fields.

Convert the placeholder-heavy template into a couple of concrete, copy-paste-ready worked examples drawn from a real (anonymized) ingestion workflow so the guidance is immediately executable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient intent but padded with 'Detects/Documents' YAML blocks that re-explain connector, authentication, and incremental-load concepts Claude already knows; could be tightened substantially.	2 / 3
Actionability	Provides a concrete template with real file types (.dig, .yml) and field names plus an explicit fallback message, but the bulk is template scaffolding with placeholders rather than copy-paste-ready executable guidance.	2 / 3
Workflow Clarity	The mandatory codebase-access section gives a clear sequenced workflow with validation checkpoints (ask for path -> Glob verify -> STOP if unreadable) and an explicit 'no generic placeholders' guardrail, a proper feedback loop.	3 / 3
Progressive Disclosure	Monolithic single-file body; no references/, scripts/, or assets/ bundle files exist and no external references are signaled, while the full template and per-connector detection detail are inlined rather than split out.	1 / 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 strong, specific description that clearly states both capability and trigger. Its only weakness is trigger-term breadth — it covers the core phrase but misses natural phrasings a user might actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named specifics: 'detects connector types (REST API, Database, File, Streaming)', 'documents authentication patterns, rate limiting strategies, and incremental load patterns'.	3 / 3
Completeness	Explicitly answers what (documentation generation + detection of connector/auth/rate-limit/incremental patterns) and when via 'Use when documenting data source ingestion workflows'.	3 / 3
Trigger Term Quality	Includes the trigger 'documenting data source ingestion workflows' but lacks common natural variations a user would say (e.g. 'connector documentation', 'ingestion docs', named connector mentions), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	Targeted niche (data source ingestion-layer documentation) with distinctive triggers; 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.