run-locally
Run and test the TypeScript LangChain agent locally. Use when: (1) User wants to test locally, (2) User says 'run locally', 'test agent', 'start server', or 'dev mode', (3) Debugging issues.
90
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a well-structured skill description with explicit trigger guidance and a clear niche. Its main weakness is that the 'what' portion could be more specific about the concrete actions involved (e.g., installing dependencies, starting a dev server, running test suites). The trigger terms and completeness are strong.
Suggestions
Expand the capability description with more concrete actions, e.g., 'Install dependencies, start the development server, run test suites, and debug the TypeScript LangChain agent locally.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TypeScript LangChain agent) and some actions (run, test), but doesn't list multiple concrete actions beyond running and testing. It mentions 'start server' and 'dev mode' as triggers but not as distinct capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (run and test the TypeScript LangChain agent locally) and 'when' with an explicit 'Use when:' clause listing specific trigger scenarios including user phrases and use cases. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'run locally', 'test agent', 'start server', 'dev mode', and 'debugging issues'. These cover common variations of how a user would phrase their intent. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to a TypeScript LangChain agent with local testing/running context. The combination of 'TypeScript', 'LangChain', and 'locally' creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%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 with excellent structure and concrete, executable examples throughout. Its main weakness is some verbosity — sections like basic debugging tips (console.log, VS Code debugger), the performance monitoring section, and obvious troubleshooting items could be trimmed to respect token budget. Overall it serves its purpose well as a comprehensive local development guide.
Suggestions
Remove the basic debugging section (console.log advice, VS Code debugger steps) — Claude already knows these techniques and they consume tokens without adding value.
Trim the Performance Monitoring section, which is vague and adds little actionable guidance beyond 'add console.log statements'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete commands and examples, but includes some unnecessary content like explaining what `tsx watch` does, basic debugging advice (console.log, VS Code debugger), and a performance monitoring section that adds little value. The troubleshooting section is lengthy and some items (like 'Module not found' → 'npm install') are obvious to Claude. | 2 / 3 |
Actionability | Excellent actionability throughout — every section provides copy-paste ready commands, complete curl examples with expected responses, specific port numbers, and concrete bash commands for troubleshooting. The test commands, environment variable examples, and endpoint URLs are all fully executable. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced (e.g., E2E tests: deploy → set URL → run tests; production build: build → start). Testing is well-organized into unit/integration/E2E tiers with clear prerequisites. The troubleshooting section provides clear diagnostic steps with verification commands. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear section hierarchy. References to external resources are one-level deep and clearly signaled (MLflow Tracing Guide, Troubleshooting Guide, quickstart skill, add-tools skill, tests/e2e/README.md). The main content stays focused on running locally while appropriately deferring detailed topics to other files. | 3 / 3 |
Total | 11 / 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
- databricks/app-templates
- Commit
dfeb4ac
- 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.