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

33%

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

31%Scale 1-5

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

This skill is an overly verbose orchestration template that reads more like a product management playbook than actionable Claude instructions. It delegates everything to subagents via prompt templates without providing any concrete code, commands, or executable examples. The structure is logical but lacks validation feedback loops, and the single referenced resource file doesn't exist in the bundle.

Suggestions

Replace verbose subagent prompt descriptions with concise task specifications—remove explanations of well-known tools and concepts (Amplitude, Mixpanel, feature flags, etc.) that Claude already understands.

Add concrete, executable examples: sample event schema JSON, a real feature flag configuration snippet, an actual statistical power calculation script, or a sample analytics validation test.

Add explicit validation checkpoints with feedback loops, especially before production rollout (e.g., 'If sample ratio mismatch > 1%, halt experiment and investigate assignment logic').

Either provide the referenced 'resources/implementation-playbook.md' bundle file or remove the reference; split the configuration options and success criteria into separate reference files to reduce the monolithic structure.

Dimension	Reasoning	Score
Conciseness	The skill is heavily verbose with extensive explanations Claude already knows (what Amplitude/Mixpanel do, what A/B testing is, what feature flags are). The extended thinking block is unnecessary filler. Many prompts contain redundant context about well-known concepts. The 16-step process could be significantly condensed.	2 / 5
Actionability	Despite being long, the skill provides no executable code, no concrete commands, and no real examples. Every step is a prompt template delegating to a subagent with vague instructions like 'Perform exploratory data analysis.' The YAML config block is illustrative but not actionable—there's no code showing how to use it. The referenced 'resources/implementation-playbook.md' is not provided.	2 / 5
Workflow Clarity	The 6-phase, 16-step sequence is clearly ordered and logically structured. However, validation checkpoints are weak—step 10 validates analytics but there are no feedback loops for error recovery in most phases. The gradual rollout mentions automated rollback but doesn't specify concrete criteria or steps for when things go wrong. For a workflow involving destructive/batch operations (production rollouts), the lack of explicit validation gates caps this at 3.	3 / 5
Progressive Disclosure	The skill references 'resources/implementation-playbook.md' but no bundle files are provided, making this a dead reference. The entire 16-step process is inlined as a monolithic document (~200+ lines) with no content split into supporting files. The configuration options, success criteria, and coordination notes could all be separate references. The content that should be in separate files is all inline.	2 / 5
	Total	9 / 20 Passed

Description

36%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 too abstract and buzzword-heavy, reading more like a marketing tagline than a functional skill description. It lacks concrete actions, specific trigger terms users would naturally use, and entirely omits a 'Use when...' clause. The mention of 'specialized agents' is vague and doesn't help Claude determine when to select this skill.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases like 'Use when the user wants to run A/B tests, analyze experiment results, set up feature flags, or make data-driven product decisions.'

Replace abstract language with specific actions, e.g., 'Designs A/B test configurations, analyzes experiment metrics, implements feature flags, and generates statistical significance reports.'

Include natural user terms and synonyms such as 'experiment', 'feature flag', 'metrics', 'conversion', 'statistical significance', 'split test', and 'analytics dashboard'.

Dimension	Reasoning	Score
Specificity	Names the domain (data-driven feature development) and mentions A/B testing, analysis, implementation, and experimentation, but these are high-level concepts rather than concrete actions. No specific operations like 'create experiment configs', 'parse analytics data', or 'generate statistical reports' are listed.	2 / 5
Completeness	The 'what' is vaguely present (build features guided by data insights using specialized agents) but lacks specificity. There is no 'when' clause at all — no 'Use when...' or equivalent trigger guidance, which per the rubric should cap completeness at 3, and the weak 'what' brings it down to 2.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'A/B testing', 'data insights', 'measurement', and 'experimentation', but misses natural user phrases like 'run an experiment', 'feature flag', 'metrics', 'analytics', 'hypothesis testing', or 'conversion rate'. The terms used are somewhat abstract.	3 / 5
Distinctiveness Conflict Risk	The combination of A/B testing, data-driven development, and specialized agents provides some distinctiveness, but 'build features' and 'analysis' are broad enough to overlap with general development skills, analytics skills, or feature management skills.	3 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/data-engineering-data-driven-feature/SKILL.md
Commit: 57c135b

Reviewed: 3 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.