setup-dev
Set up and manage the Sentry development environment using devenv. Handles fresh setup, updating existing environments, starting dev services, and troubleshooting. Use when asked to "set up sentry", "setup dev environment", "get sentry running", "start dev server", "devenv setup", "devservices not working", "sentry won't start", or any development environment issue.
90
88%
Does it follow best practices?
Impact
93%
1.43xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It clearly specifies concrete capabilities (setup, update, start, troubleshoot), provides an extensive and natural set of trigger terms in an explicit 'Use when' clause, and is highly distinctive due to the specific product and tooling context. It follows the third-person voice convention and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'fresh setup', 'updating existing environments', 'starting dev services', and 'troubleshooting'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (set up and manage Sentry dev environment using devenv, handles fresh setup, updating, starting services, troubleshooting) and 'when' (explicit 'Use when...' clause with extensive trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'set up sentry', 'setup dev environment', 'get sentry running', 'start dev server', 'devenv setup', 'devservices not working', 'sentry won't start'. Covers both formal and informal phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Sentry development environment via devenv. The specific product name (Sentry), tool name (devenv), and targeted trigger terms make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill that provides a comprehensive guide to setting up the Sentry development environment. Its greatest strengths are the concrete, executable commands at every step and the excellent troubleshooting decision tree. The main weaknesses are its length (could be more concise by trimming coaching language and obvious explanations) and the monolithic structure that would benefit from splitting into overview + reference files.
Suggestions
Trim conversational coaching phrases like 'Don't panic', 'Tell the user:', and time estimate block quotes — these can be shortened to inline notes (e.g., '⏱️ ~10 min first run, ~30s after').
Split the troubleshooting decision tree and OrbStack socket fix details into separate referenced files to improve progressive disclosure and reduce the main document's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content earns its place — specific commands, tables, and troubleshooting are valuable. However, some sections include unnecessary explanations Claude would know (e.g., explaining what Docker images are, what Django migrations do) and some conversational coaching language ('Don't panic', 'Tell the user:') adds bulk. The time estimates and expectation-setting quotes, while useful for the user, are somewhat verbose. | 2 / 3 |
Actionability | Excellent actionability throughout — nearly every step has copy-paste-ready commands, specific file paths, exact URLs, concrete credentials, and precise error messages to match against. The troubleshooting table maps specific symptoms to specific fixes with exact commands. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints (detect state first, verify versions, handle chicken-and-egg problems, run devenv doctor). Feedback loops are present — e.g., if devenv update fails, reinstall; if direnv hangs, start Docker first then retry. The decision tree at the end provides error recovery paths for all common failure modes. | 3 / 3 |
Progressive Disclosure | The content is a monolithic document with all information inline. It references `references/orbstack-fix.md` and external AL MCP docs, but the main body is ~200+ lines that could benefit from splitting (e.g., troubleshooting into a separate file, OrbStack vs Colima details). No bundle files are provided to support the reference to `references/orbstack-fix.md`, though the day-to-day commands section serves as a good quick-start summary. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- getsentry/sentry
- Commit
552fb5c
- Reviewed
Table of Contents
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.