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

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./aps-doc-skills/ingestion/SKILL.md

Quality

Content

52%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.

The skill delivers a concrete, usable documentation template and a sensible access-gating workflow, but it is padded with redundant detection catalogs that restate common knowledge and keeps all reference material inlined in a single ~380-line file instead of splitting it across bundle files.

Suggestions

Move the full parent/child documentation template and the connector-type/auth/rate-limiting/incremental catalogs into separate reference files (e.g., references/template.md, references/connector-detection.md) and link to them from SKILL.md to fix progressive disclosure.

Trim the detection catalogs down to the ingestion-specific signals Claude would not already infer (e.g., which .dig/.yml keys indicate incremental vs full-reload) instead of restating what REST, OAuth, or Kafka are.

Add explicit verification steps after generation (e.g., cross-check extracted table names against datasources.yml, confirm no placeholder tokens remain) as a validate->fix loop to back the 'NO generic placeholders' requirement.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the connector/auth/rate-limiting/incremental detection catalogs restate concepts Claude already knows (REST endpoint URLs, OAuth token flows, Kafka topics) as padded YAML-style lists, adding little beyond the domain framing.	2 / 5
Actionability	Provides a copy-paste-ready documentation template and a concrete codebase-access gate, but the detection sections are descriptive ('Detects from configuration:') rather than executable commands, and no actual Glob/read commands or runnable code are given.	4 / 5
Workflow Clarity	A clear checkpoint sequence guards the risky access step (ask for path -> Glob verify -> STOP if unreadable), but the documentation-generation process itself lacks validate->fix->retry loops for confirming extracted data is real despite the 'NO generic placeholders' mandate.	4 / 5
Progressive Disclosure	No bundle files exist and the SKILL.md is monolithic: ~120 lines of inlined documentation template plus large connector/auth/incremental catalogs that clearly belong in separate reference files, with no one-level-deep file references at all.	2 / 5
	Total	12 / 20 Passed

Description

80%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 strong, specific description that clearly states capability and includes an explicit 'Use when' trigger. It is held below top marks by a single narrow trigger phrase and a lack of synonyms/file extensions in the trigger term coverage.

Suggestions

Expand the 'Use when' clause with concrete trigger variations (e.g., 'Use when documenting data source ingestion workflows, when the user mentions .dig files or datasources.yml, or when generating Confluence docs for ingestion layers').

Add natural synonyms and file extensions users might say ('.dig', 'datasources.yml', 'Confluence ingestion docs') to improve trigger-term match likelihood.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across enumerated connector subtypes — 'detects connector types (REST API, Database, File, Streaming), documents authentication patterns, rate limiting strategies, and incremental load patterns' — giving comprehensive coverage of the domain's actions.	5 / 5
Completeness	Explicitly answers both what ('Expert documentation generation...documents authentication patterns, rate limiting...') and when ('Use when documenting data source ingestion workflows.'), though the 'when' is a single trigger phrase rather than several concrete trigger variations.	4 / 5
Trigger Term Quality	Good keyword coverage ('ingestion', 'data source', 'ingestion workflows', 'REST API', 'Database', 'Streaming') but missing common synonyms and file extensions (.dig, Confluence) that would round out natural user phrasing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (ingestion-layer documentation with connector-type detection) distinct from generic documentation skills, with only minor overlap risk with closely related doc-generation skills.	4 / 5
	Total	17 / 20 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
Path: aps-doc-skills/ingestion/SKILL.md
Commit: ff38137

Reviewed: 1 day 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.