CtrlK
BlogDocsLog inGet started
Tessl Logo

data-table-manager

Load before calling data-tables 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 build-workflow).

76

Quality

96%

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

92%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 body is a strong instruction-only skill: an actionable default procedure with genuine validation checkpoints for destructive and batch operations, concrete parameters and naming rules throughout, and a clean one-level-deep split into the playbook reference. The only weakness is minor redundancy in the Routing section and a few rationale asides that could be trimmed.

Suggestions

Merge the two Routing paragraphs that both state the workflow-builder load order ("For workflow builds that create or write Data Tables, load this skill, then workflow-builder" vs "Also load this skill before planning or building a workflow whose trigger ... create, inspect, or write Data Table records") into one statement.

Trim rationale asides in Diagnosing Lookup Failures (e.g., "rows can carry very large values (inline base64 images, raw payloads), and one broad result can crowd out everything else") to keep only the operative rule, moving the reasoning to the playbook if it is worth keeping.

DimensionReasoningScore

Conciseness

The body is mostly lean, dense rule lists that assume competence ("Use only supported types: string, number, boolean, date"), with no padding explaining concepts Claude already knows. Minor trimming is possible: the Routing section states the workflow-builder load order in two near-duplicate paragraphs, and the lookup-failure prose carries rationale asides ("rows can carry very large values (inline base64 images, raw payloads)..."). This sits between the 4 anchor (efficient with minor over-explanation) and 5 (every token earns its place).

4 / 5

Actionability

The guidance is fully executable for an instruction-only skill: concrete tool calls ("data-tables(action=\"list\")"), specific parameter values ("maxRows=20", "batches of at most 100", "limit: 1" with count), the complete operator list ("eq, neq, like, ilike, gt, gte, lt, lte"), and exact naming/type examples ("customer_email", "external_id"). Specific examples cover the common cases (import, query, delete, rename, schema repair), matching the 5 anchor.

5 / 5

Workflow Clarity

The six-step Default Procedure is a clear checklist with explicit validation checkpoints for destructive and batch operations ("Inspect schema before writes, deletes, column changes", "query matching rows first", "never perform a broad row mutation ... without showing the match count"), plus feedback loops for error recovery (only strictly narrower follow-up queries after 0-row results, stop after two probes) and explicit stop conditions on approval denial. The destructive/batch cap does not apply because validation is present, so this matches the 5 anchor rather than 4.

5 / 5

Progressive Disclosure

The body is a well-organized overview with clear section headers, and the single bundle reference (references/data-table-playbook.md) was verified to exist, contain the promised material (tool recipes, schema patterns, import edge cases), and be exactly one level deep with no nested references. The 'More Detail' section signals it clearly with its contents enumerated, matching the 5 anchor.

5 / 5

Total

19

/

20

Passed

Description

100%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.

The description is exemplary: it clearly states both what the skill does and when to load it, uses natural verbatim user phrasings as triggers with synonyms and file extensions, and stays tightly scoped to a distinct niche. It reads in imperative/third-person voice with no vague padding.

DimensionReasoningScore

Specificity

The description enumerates a comprehensive set of concrete actions — "list, show, create, inspect, import, seed, query, update, clean up, rename columns in, or delete data tables and rows" — plus concrete formats ("CSV/XLSX/JSON attachments") and a workflow-planning case. Coverage is comprehensive with no minor gaps, so it matches the 5 anchor rather than 4.

5 / 5

Completeness

It explicitly answers "what" via the enumerated operations with the data-tables/parse-file tools, and "when" with an explicit trigger clause ("Use for natural standalone requests like ... and whenever the user asks to ..."). Both are concrete and explicit, matching the anchor-5 example structure; the presence of the explicit trigger clause also avoids the 'Use when' cap.

5 / 5

Trigger Term Quality

It quotes natural user phrasings verbatim ("what data tables do I have?", "show/list my tables", "what columns are in this table?"), covers synonyms across CRUD verbs, and includes file extensions (CSV/XLSX/JSON). This is comprehensive natural-term coverage including synonyms and extensions, matching the 5 anchor.

5 / 5

Distinctiveness Conflict Risk

Every trigger is anchored to the specific niche of Data Tables via the "data tables" noun, the data-tables/parse-file tool names, and the workflow-builder routing note. A generic request like "analyze this CSV" would not match since every trigger requires data tables, so conflict risk is minimal and the niche is distinct.

5 / 5

Total

20

/

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
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.