This skill should be used when the user says "dev setup", "arn spark dev setup", "development environment", "configure dev environment", "dev container", "configure CI", "set up CI", "onboard developer", "developer setup", "set up docker", "configure development", "how do I set up this project", "development setup", "onboard me", "get this project running", "set up my machine", "new developer setup", "how do I get started", "developer onboarding", or wants to define a standardized development environment for their project (producing dev environment infrastructure files and a dev-setup document) or follow an existing environment standard to get onboarded as a new developer.
71
64%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/arn-spark/skills/arn-spark-dev-setup/SKILL.mdQuality
Discovery
82%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 excels at trigger term coverage with an exhaustive list of natural phrases users would say, and it clearly addresses both what the skill does and when to use it. However, the actual capability description is somewhat vague—it could benefit from more concrete actions beyond 'producing dev environment infrastructure files.' The broad trigger list, while comprehensive, introduces some overlap risk with more specialized skills like Docker or CI configuration.
Suggestions
Add more specific concrete actions, e.g., 'Generates Dockerfiles, docker-compose.yml, .devcontainer configs, CI pipeline files, and developer onboarding documentation'
Consider narrowing or qualifying overlapping triggers like 'set up docker' and 'configure CI' to reduce conflict with specialized skills, e.g., 'when setting up Docker as part of a full development environment'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions some actions like 'define a standardized development environment', 'producing dev environment infrastructure files and a dev-setup document', and 'get onboarded as a new developer', but these are somewhat vague and not a comprehensive list of concrete actions (e.g., what specific files are produced, what tools are configured). | 2 / 3 |
Completeness | The description explicitly answers both 'what' (define a standardized development environment, produce dev environment infrastructure files and a dev-setup document, onboard as a new developer) and 'when' (with a comprehensive list of trigger phrases and use cases). The 'Use when' guidance is effectively embedded via the explicit trigger phrase list. | 3 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger phrases users would actually say, such as 'dev setup', 'how do I get started', 'set up docker', 'configure CI', 'onboard me', 'new developer setup', and many more variations covering a wide range of how users might express this need. | 3 / 3 |
Distinctiveness Conflict Risk | While the dev setup/onboarding niche is fairly specific, some trigger terms like 'set up docker', 'configure CI', and 'how do I get started' could overlap with Docker-specific skills, CI/CD pipeline skills, or general project help skills. The broad scope of triggers increases conflict risk. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured conversational skill with excellent workflow clarity and comprehensive error handling, but it suffers significantly from verbosity. The content reads more like a product specification than a concise skill instruction — many sections spell out exact dialogue text, repeat mode-detection logic, and include tables that Claude could derive from context. Actionability is moderate since the skill delegates most concrete work to an agent without showing what that agent produces.
Suggestions
Cut content by 40-50%: remove verbatim dialogue strings (Claude can generate natural conversation), collapse the probing questions table into a brief list, and eliminate the agent invocation guide table (Claude can determine when to invoke agents from the workflow steps alone).
Add at least one concrete example of a generated artifact (e.g., a minimal devcontainer.json, a setup script snippet, or a CI workflow fragment) so Claude has a tangible reference for what the builder agent should produce.
Move the Error Handling section and Agent Invocation Guide into separate reference files to reduce the main skill's length and improve progressive disclosure.
Consolidate the duplicate mode-detection logic that appears in both Step 1 and the Error Handling section ('Dev setup already configured') into a single location.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It over-explains conversational flows, repeats information across sections (e.g., mode detection appears in Step 1 and Error Handling), includes extensive tables of deferral responses Claude could handle implicitly, and spells out UI text verbatim that Claude could generate naturally. Many sections like the probing questions table and agent invocation guide add bulk without proportional value. | 1 / 3 |
Actionability | The skill provides clear conversational structure with specific questions to ask and options to present, and references concrete tools (arn-spark-dev-env-builder agent, AskUserQuestion). However, it lacks executable code examples — no actual setup script snippets, no concrete devcontainer.json examples, no CI workflow samples. The actionability relies heavily on delegating to an agent whose behavior is not shown. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with numbered steps for both Define and Onboard modes. It includes explicit verification checkpoints (Step 8, Step O4), error recovery paths (setup script fails → retry → manual fallback after 3 attempts), confirmation gates before generation (Step 4 confirmation), and a clear decision tree for mode detection. Feedback loops are present for destructive/batch operations. | 3 / 3 |
Progressive Disclosure | The skill references external files (dev-setup-template.md, dev-setup-checklist.md) appropriately, and delegates to agents for file generation. However, the SKILL.md itself is monolithic — the Define Mode, Onboard Mode, Agent Invocation Guide, and Error Handling sections could benefit from being split into separate reference files. The bundle files were not provided, so referenced paths cannot be verified. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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 | |
1fe948f
Table of Contents
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.