data-engineering-data-driven-feature

Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation.

Quality

57%

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 ./skills/data-engineering-data-driven-feature/SKILL.md

Quality

Content

56%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-sequenced, actionable multi-phase workflow with concrete agent prompts and validation/monitoring phases, but it is padded with redundant boilerplate and inlined templates that hurt token efficiency and leave no progressive-disclosure structure to offload detail.

Suggestions

Remove the verbatim description repeat, the bracketed "Extended thinking" preamble, and the generic "Use/Do not use this skill when" + "Instructions" filler to reclaim tokens.

Move the 16 detailed prompt templates into reference files (e.g., references/prompts/) and keep only the phase overview plus a one-line pointer per step.

Make the validation/rollout feedback loops explicit (e.g., "If analytics validation fails: fix event schemas and re-run validation before proceeding to rollout").

Dimension	Reasoning	Score
Conciseness	The body repeats the description verbatim, carries a long bracketed "Extended thinking" preamble and generic filler sections ("Use this skill when", "Do not use this skill when", boilerplate "Instructions"), and inlines 16 full prompt templates, making it noticeably verbose with several padded sections.	2 / 5
Actionability	Each phase specifies a concrete `subagent_type`, a detailed prompt, and expected output, giving mostly executable orchestration guidance; only minor gaps remain since prompts are templates rather than exact commands.	4 / 5
Workflow Clarity	Six phases and 16 numbered steps form a clear sequence with context-passing and validation in Phase 4 plus monitoring/rollback in Phase 5; minor validation gaps remain because explicit "if validation fails → fix → retry" feedback loops for rollout are implicit rather than stated.	4 / 5
Progressive Disclosure	No bundle files exist and all detailed per-step prompt templates are inlined in a single ~180-line file with good section structure but no external references or split content to navigate to.	3 / 5
	Total	13 / 20 Passed

Description

58%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 conveys a clear, specific purpose with multiple concrete actions and a fairly distinct niche, but it lacks any explicit "when to use" trigger guidance and its keywords lean formal rather than natural user phrasing.

Suggestions

Add an explicit "Use when..." clause naming natural user triggers (e.g., building a feature to validate via A/B test, measuring feature impact, rolling out a feature experiment).

Include more common, user-spoken trigger terms and synonyms alongside the formal ones (e.g., "feature experiment", "rollout", "measure impact").

Tighten the niche phrasing to reduce overlap with generic feature-build skills, e.g., by foregrounding "experiment-validated feature development".

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ("Build features guided by data insights", "A/B testing", "continuous measurement", "analysis, implementation, and experimentation"); falls short of the comprehensive, fully-enumerated action list of a 5.	4 / 5
Completeness	Has a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance; per the rubric a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant terms like "data insights", "A/B testing", and "experimentation", but these are fairly formal and miss common user-spoken variations such as "roll out a feature" or "measure impact".	3 / 5
Distinctiveness Conflict Risk	The data-driven/A-B-tested feature niche is mostly distinct from generic skills, though "build features" is broad enough to risk minor overlap with general feature-development skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/data-engineering-data-driven-feature/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.