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.
65
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./agent-langchain-ts/.claude/skills/run-locally/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.
This is a solid description with a clear 'Use when' clause and good trigger terms that users would naturally say. Its main weakness is that the capability description is somewhat thin—it could benefit from listing more specific actions (e.g., configuring environment, running specific test suites). Some trigger terms like 'debugging issues' and 'start server' are generic enough to potentially conflict with other development skills.
Suggestions
Add more specific concrete actions beyond 'run and test', such as 'configure environment variables, start the development server, run test suites, inspect agent responses'.
Narrow generic triggers like 'debugging issues' and 'start server' by scoping them to the LangChain context, e.g., 'debugging LangChain agent issues' or 'start LangChain dev server'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TypeScript LangChain agent) and some actions (run, test locally), 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 this need. | 3 / 3 |
Distinctiveness Conflict Risk | The specificity of 'TypeScript LangChain agent' helps distinguish it, but triggers like 'run locally', 'test agent', 'start server', and 'debugging issues' are quite generic and could overlap with other local development or testing skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
72%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, highly actionable skill with excellent concrete examples and commands throughout. Its main weaknesses are moderate verbosity (explaining things Claude already knows like console.log debugging and what tsx watch does) and missing validation checkpoints in multi-step workflows. The progressive disclosure and cross-referencing to other skills/guides is well done.
Suggestions
Remove sections Claude already knows: basic debugging with console.log, what tsx watch does, VS Code debugger instructions, and the performance monitoring section — these add token cost without teaching anything new.
Add explicit validation checkpoints after starting servers (e.g., 'Verify: curl http://localhost:5001/health should return 200') before proceeding to testing steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary content like explaining what `tsx watch` does, basic debugging advice (console.log, VS Code debugger), and performance monitoring tips that Claude already knows. The troubleshooting section is useful but some entries could be tightened. | 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 are fully executable with proper JSON payloads. | 3 / 3 |
Workflow Clarity | Steps are clearly listed and sequenced (start servers, test endpoints, run tests), but there are no explicit validation checkpoints or feedback loops. For example, after starting servers there's no 'verify servers are running' step, and the testing workflow doesn't include what to do when tests fail beyond the troubleshooting section at the end. | 2 / 3 |
Progressive Disclosure | Good structure with clear sections progressing from basic (start servers) to advanced (E2E tests, performance monitoring). References to external files are one-level deep and well-signaled (MLflow guide, Troubleshooting guide, quickstart skill, add-tools skill, tests/e2e/README.md). | 3 / 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
- databricks/app-templates
- Commit
1c88215
- 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.