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

63%

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

77%

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

The content is highly actionable with a clear, well-sequenced multi-phase workflow and explicit validation/rollback checkpoints. Its weaknesses are length and repetition (the identical per-step template and verbose prompts) and the absence of any progressive disclosure into separate reference files.

Suggestions

Tighten the repeated per-step template: collapse the identical 'Use Task tool / Context / Prompt / Output' scaffolding and trim buzzword-stuffed prompts to the essential instruction.

Move the per-step prompt text and the Configuration Options block into a references file (e.g., phases.md) so SKILL.md is a concise overview pointing one level deep.

Remove the extended-thinking paragraph and Coordination Notes that restate general knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	The body is long and repetitive — 16 steps follow an identical Task-tool/Context/Prompt/Output template with verbose, buzzword-stuffed prompts, plus an extended-thinking paragraph and coordination notes that largely restate what Claude knows. Not 1 because it avoids explaining basic concepts; not 3 because it could be substantially tightened and sheds padding.	2 / 3
Actionability	Each step provides a concrete Task-tool invocation with a specific subagent_type and a copy-paste-ready prompt plus expected output. This matches the 'fully executable, copy-paste ready' anchor rather than the pseudocode/incomplete anchor (2).	3 / 3
Workflow Clarity	There is a clear six-phase, sixteen-step sequence with explicit context threading, a dedicated Pre-Launch Validation phase, success criteria, and a gradual-rollout/monitoring phase with automated rollback as a feedback loop. Not 2 because explicit validation and rollback checkpoints are present rather than missing.	3 / 3
Progressive Disclosure	The skill is a single monolithic SKILL.md with no references, scripts, or assets, and the body contains no file references; the 16 detailed step prompts and config block are inline content that could be split out. Not 1 because it is organized into clear phases/sections; not 3 because, at well over 50 lines, it is monolithic rather than an overview with one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 states what the skill does reasonably clearly but is missing any explicit 'Use when...' trigger guidance, which caps its completeness and distinctiveness. It uses moderately natural keywords but leans on buzzword-heavy phrasing rather than concrete enumerated actions.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when planning A/B tests, instrumenting features for analytics, or running data-driven experiments').

Replace generic verbs like 'analysis, implementation, and experimentation' with concrete actions such as 'design experiments, instrument analytics events, run gradual rollouts, and analyze test results'.

Use third-person concrete action phrases and include common user-facing terms (e.g., 'A/B tests', 'experimentation', 'feature flags') to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	It names the domain ('data insights, A/B testing, and continuous measurement') and some actions ('Build features guided by...', 'analysis, implementation, and experimentation'), but the actions are general rather than a list of multiple concrete specific actions. Not 3 because it lacks concrete enumerated actions; not 1 because it does name a domain and actions.	2 / 3
Completeness	It clearly answers 'what' (build features guided by data, A/B testing, measurement) but has no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the guidelines. Not 3 because 'when' is absent; not 1 because 'what' is clear.	2 / 3
Trigger Term Quality	Relevant keywords like 'A/B testing' and 'data insights' appear, but phrasing such as 'continuous measurement' and 'specialized agents' is somewhat jargon-heavy and misses common user-facing variations. Not 3 because coverage of natural user terms is incomplete; not 1 because relevant keywords are present.	2 / 3
Distinctiveness Conflict Risk	It is somewhat specific to data-driven feature development but could overlap with general feature-development skills. Not 3 because it lacks distinct explicit triggers that set it apart; not 1 because it is not as generic as 'helps with code and documents'.	2 / 3
	Total	8 / 12 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: e63f7dd

Reviewed: about 5 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.