create-data-context

Create, update, inspect, or repair Data Analytics semantic layers. Use when the user asks to save data context or create a semantic layer that future Data Analytics work can inspect and cite.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/opencode/src/skill/builtin/.bundle/data-analytics/workflows/create-data-context/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is well-structured with a clear workflow and good intent to keep generated output compact, but execution details are uneven: validation is described generically while concrete validation scripts sit unreferenced in the bundle, and several reference files are not navigated from the main body. There is also redundancy between the Creating/Updating and Output Contract sections.

Suggestions

Point the "validate" steps at the bundled `scripts/validate_data_context_contract.py` (and preflight script) with explicit run conditions and a validate-fix-retry loop, turning vague validation into an actionable checkpoint.

Link the unreferenced bundle files from the body (e.g., cite `connector-playbook.md` for connector sourcing and `source-intake.md` for intake structure) so all references are discoverable from SKILL.md.

Merge the Output Contract section into the Creating/Updating section (or trim it to a short checklist) to remove the duplicated return-guidance and tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and mostly free of concepts Claude already knows, but the Output Contract section restates the return-guidance from the preceding section and the Runtime Routing table leans on dense runtime jargon (surface/mode, install surfaces) that could be tightened.	2 / 3
Actionability	It gives concrete paths and a clear routing table (e.g., write to `references/source-inventory.md`, default to `$CODEX_HOME/skills/<area>-semantic-layer`), but validation is hand-waved as "validate" even though a validation script exists in the bundle and is never referenced.	2 / 3
Workflow Clarity	The section flow (intake -> source list -> build -> validate -> persist -> offer refresh -> output) is clearly sequenced, but validation checkpoints are generic ("validate", "verify... when possible") rather than concrete, and no validate-fix-retry loop is specified.	2 / 3
Progressive Disclosure	References are one level deep and the body correctly pushes detail to `skill-template.md` and `weekly-polling-automation.md`, but three bundle files (`connector-playbook.md`, `source-intake.md`, `automation.md`) are not signaled from the body, weakening navigation.	2 / 3
	Total	8 / 12 Passed

Description

85%

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: it names four concrete actions and pairs them with an explicit Use-when trigger, giving clear what/when guidance and a distinct niche. The main weakness is limited trigger-term coverage, offering only two phrasings rather than the common variations a user might naturally say.

Suggestions

Broaden trigger terms to include variations users naturally say, e.g. "define metrics", "document the data model", or "set up a source of truth".

Consider naming the inspect/repair triggers more explicitly (e.g., "Use when reviewing or fixing an existing semantic layer") so maintenance requests also surface the skill.

Dimension	Reasoning	Score
Specificity	The phrase "Create, update, inspect, or repair Data Analytics semantic layers" lists four concrete, distinct actions, matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It states what the skill does ("Create, update, inspect, or repair... semantic layers") and gives an explicit "Use when..." trigger clause, clearly answering both what and when.	3 / 3
Trigger Term Quality	It includes natural triggers like "save data context" and "create a semantic layer", but coverage is narrow and misses common variations a user might say (e.g., "define metrics", "document the data model", "canonical metric").	2 / 3
Distinctiveness Conflict Risk	The "Data Analytics semantic layers" niche with the specific "save data context / create a semantic layer" trigger carves out a clear niche unlikely to fire for ordinary data-analysis requests.	3 / 3
	Total	11 / 12 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
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/data-analytics/workflows/create-data-context/SKILL.md
Commit: ff87d47

Reviewed: about 13 hours 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.