CtrlK
BlogDocsLog inGet started
Tessl Logo

data-loading

Discover connected data sources, add new data connectors through a user-confirmed form, inspect table metadata, and run bounded read-only probes when the current workspace data is insufficient.

63

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./py-src/data_formulator/analyst/skills/data-loading/SKILL.md

The canonical home for this skill is data-loading in microsoft/data-formulator

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, highly actionable instruction-only skill with clear multi-step workflows and explicit grounding guardrails. It scores slightly below the top on conciseness and progressive disclosure only because a few passages could be trimmed and the content is entirely inline with no external references.

DimensionReasoningScore

Conciseness

The body is efficient and avoids explaining generic concepts, limiting exposition to skill-specific model details (workspace tables vs. connected sources); a few sentences could still be tightened, fitting 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Concrete, executable guidance throughout — named tools, 'you MUST call propose_connection in this same turn', exact fields to pass, and grounding rules — fully covers the common cases as an instruction-only skill.

5 / 5

Workflow Clarity

Numbered sequences for adding a connector and the discovery flow include checkpoints (reconcile against workspace tables, the form is only a proposal pending user click, plan pauses for choice), with only minor validation gaps, matching 'clear sequence with most checkpoints present'.

4 / 5

Progressive Disclosure

No bundle files exist and the content is self-contained, organized into clear sections (Adding a connector, Discovery sequence, Proposing loading options, Grounding rules); well-structured with only minor organization gaps, fitting 'good structure; most content appropriately placed'.

4 / 5

Total

17

/

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.

The description is specific and distinct, clearly stating what the skill does and giving an explicit when condition. It could be improved with more natural user-facing trigger phrases and synonyms alongside the somewhat technical vocabulary.

Suggestions

Add natural trigger phrases users would actually say (e.g., 'connect a database', 'what data is available', 'warehouse', 'cloud source') that are currently only in when_to_use.

Replace or augment jargon like 'read-only probes' and 'table metadata' with plain-language equivalents to broaden trigger coverage.

List a couple more concrete when-conditions beyond 'workspace data is insufficient' to reach the explicit multi-trigger level.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Discover connected data sources, add new data connectors through a user-confirmed form, inspect table metadata, and run bounded read-only probes' — matching the 'several specific actions; minor gaps' anchor, just short of the fully comprehensive 5.

4 / 5

Completeness

A clear 'what' is present and an explicit 'when' clause ('when the current workspace data is insufficient') exists, but the trigger is a single condition rather than the multiple concrete trigger phrases of the 5 anchor, placing it at 4.

4 / 5

Trigger Term Quality

Relevant keywords like 'data sources', 'data connectors', and 'table metadata' appear, but 'probes' is jargon and common natural variations/synonyms users would say are thin, fitting 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

The connected-data-discovery niche is clear and unlikely to fire for unrelated skills, with only minor overlap risk against general data-analysis skills, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

15

/

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.

Validation15 / 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
microsoft/data-formulator
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.