core

The analyst's built-in capabilities: data-inspection tools and the always-available actions (visualize and ask_user).

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

75%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 content is a well-structured, highly actionable reference for the analyst's core tools and the visualize/ask_user actions, with clear decision workflows and minimal padding. Its main limitation is that sizable reference catalogs live inline in SKILL.md with no bundle-file offloading.

Dimension	Reasoning	Score
Conciseness	The body is dense and almost entirely action-oriented with little padding of concepts Claude already knows; the few framing sentences ('Match the response to what the user asked for') could be trimmed, but overall every section earns its place.	4 / 5
Actionability	Provides concrete executable guidance — exact file paths by extension, allowed/forbidden libraries, the output_variable assignment rule, and exact chart_type names with encodings — though it stops short of a full copy-paste end-to-end example.	4 / 5
Workflow Clarity	The one-action-per-turn loop, the 'Choosing what to do' decision branches, and the report-skill handoff sequence are clearly laid out; there are no destructive/batch operations so explicit validate→fix→retry checkpoints are not required.	4 / 5
Progressive Disclosure	Sections are well organized with clear headers and the cross-skill references (load_skill('data-loading'), load_skill('report')) are explicitly signaled; the only gap is that the large chart-type and semantic-type reference tables are inlined in SKILL.md rather than split into bundle files.	4 / 5
	Total	16 / 20 Passed

Description

42%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 third-person and identifies the core capabilities and two named actions, but it is terse and lacks natural trigger terms and an explicit 'when to use' clause. It reads as a baseline tagline rather than a trigger-rich invocation summary.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when answering data questions, charting a transform, or pausing to ask the user a question').

Enumerate the concrete inspection tools (execute_python_script, inspect_source_data) instead of the generic 'data-inspection tools' to lift specificity.

Include natural synonyms/file cues users would actually say rather than only the internal action names.

Dimension	Reasoning	Score
Specificity	Names the domain ('the analyst's built-in capabilities') and a couple concrete actions ('visualize', 'ask_user') but leaves the actual tools generic as 'data-inspection tools' rather than enumerating them, so coverage is not comprehensive.	3 / 5
Completeness	It gives a clear 'what' (built-in inspection tools plus the visualize and ask_user actions) but no 'when'/Use-when trigger guidance inside the description field, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	The only candidate terms are the tool/action names 'visualize', 'ask_user', and 'data-inspection tools' — technical identifiers rather than natural phrases a user would say, with no synonyms or common variations.	2 / 5
Distinctiveness Conflict Risk	Tying it to 'the analyst's built-in capabilities' gives it a niche, but as the always-on baseline describing generic data-inspection and visualization it could still overlap with other data-analysis skills.	3 / 5
	Total	11 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: microsoft/data-formulator
Path: py-src/data_formulator/analyst/skills/core/SKILL.md
Commit: 5477f0e

Reviewed: 28 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.