CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

data-table-manager

Load before calling the data table tools or parse-file. Use for natural standalone requests like "what data tables do I have?", "show/list my tables", or "what columns are in this table?", and whenever the user asks to list, show, create, inspect, import, seed, query, update, clean up, rename columns in, or delete data tables and rows, especially from CSV/XLSX/JSON attachments. Also load before building or planning workflows that create or write to Data Tables (then load workflow-builder before workflow_builder_build_workflow).

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 high-quality tool-orchestration skill body: every rule is operational and tool-specific, procedures carry explicit validation and destructive-operation safeguards, and detail is appropriately deferred to a single well-described reference file. Remaining polish is tightening duplicated wrong-schema/re-issuing guidance and linking the reference by path.

DimensionReasoningScore

Conciseness

The body is dense with tool-specific rules (system-like name avoidance, type inference, batch limits, filter operators) and explains nothing Claude already knows, but "never redesign the surrounding workflow to fit a wrong schema" is repeated nearly verbatim across "Fixing A Wrong Schema" and "Workflow Boundary", and "Diagnosing Lookup Failures" could be tightened (e.g., the re-issue rules span multiple clauses).

4 / 5

Actionability

Guidance is fully executable for a tool-driven skill: exact tool names, parameters, and numeric limits throughout — "Preview first with maxRows=20", "batches of at most 100", "startRow / maxRows and nextStartRow", all filter operators, "query with limit: 1 and read count", and "column ID from get_data_table_schema". Specific guidance covers the common cases (import, mutation, delete, schema repair).

5 / 5

Workflow Clarity

The six-step Default Procedure is clearly sequenced with explicit validation checkpoints (list before acting, inspect schema before writes, query match count before broad mutations, stop-and-report on approval denial, 10-page import safety limit) and feedback loops (query -> confirm matches -> mutate with the same precise filter). Destructive and batch operations all have verification steps, so the workflow-clarity cap does not apply.

5 / 5

Progressive Disclosure

The body is a well-sectioned overview with one real one-level reference (references/data-table-playbook.md, verified to exist) signaled in "More Detail" with a summary of its contents. It falls short of a 5 because the pointer uses neither a path nor a link ("Load the `data-table-playbook` reference" rather than a markdown link), and schema-repair/import guidance is duplicated between the body and the playbook, so the split is not perfectly clean.

4 / 5

Total

18

/

20

Passed

Description

96%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 description: concrete action coverage, quoted natural trigger phrases, and explicit when-guidance for both standalone requests and workflow-build routing. The only weakness is modest overlap risk with attachment-parsing/spreadsheet skills from the CSV/XLSX/JSON trigger wording.

DimensionReasoningScore

Specificity

The description lists ~11 concrete actions ("list, show, create, inspect, import, seed, query, update, clean up, rename columns in, or delete data tables and rows") covering the full CRUD plus import lifecycle, so coverage is comprehensive rather than having only minor gaps.

5 / 5

Completeness

It explicitly answers both what (list/create/inspect/import/query/update/delete data tables and rows via the data table tools and parse-file) and when, with three concrete trigger clauses ("Use for natural standalone requests like...", "whenever the user asks to...", "Also load before building or planning workflows that create or write to Data Tables").

5 / 5

Trigger Term Quality

It quotes natural user utterances ("what data tables do I have?", "show/list my tables", "what columns are in this table?") and includes verb variations plus file extensions (CSV/XLSX/JSON attachments), giving comprehensive natural-term coverage including synonyms and formats.

5 / 5

Distinctiveness Conflict Risk

The Data Tables niche is distinct with an explicit routing boundary to workflow-builder, but triggers like "CSV/XLSX/JSON attachments" and generic column/table questions carry minor overlap risk with file-parsing or spreadsheet skills, so conflict risk is not minimal.

4 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

n8n-io/n8n

Path

packages/@n8n/instance-ai/skills/data-table-manager/SKILL.md

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.