Name: run-locally
Rating: 68 (1 reviews)
Author: databricks

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.

Quality

83%

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

Quality

Content

75%Weight 40%Scale 1-5

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

The body is highly actionable with copy-paste commands and expected outputs, and is well structured with clear external references. The main weakness is conciseness — a few sections restate basics Claude already knows.

Suggestions

Trim the 'Watch Mode' and 'Debugging' sections: remove explanations of tsx watch and console.log/F5 basics that Claude already knows, keeping only the project-specific commands.

Add explicit validation checkpoints to the test and deploy workflows (e.g., verify servers are up before running integration tests; confirm build succeeded before deploy) rather than relying on the reactive Troubleshooting section.

Consider moving the full environment-variable listing and E2E deploy details into a referenced file to keep SKILL.md a leaner overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but several sections explain concepts Claude already knows (tsx watch behavior, console.log/F5 debugging basics) that could be trimmed without losing clarity.	3 / 5
Actionability	Fully executable, copy-paste-ready commands and curl payloads with expected SSE/JSON outputs covering the common cases (dev servers, both endpoints, tools, tests).	5 / 5
Workflow Clarity	Multi-step processes (start servers, test endpoints, run unit/integration/E2E tests, deploy sequence) are clearly sequenced, though validation checkpoints are mostly reactive (troubleshooting) rather than explicit validate-then-proceed steps.	4 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep, clearly signaled references (_shared/MLFLOW.md, _shared/TROUBLESHOOTING.md, sibling skills); no bundle files exist, so content stays inline, which is slightly long but navigable.	4 / 5
	Total	16 / 20 Passed

Description

91%Weight 40%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 concrete, complete, and rich with natural trigger phrases, cleanly answering both what and when. The only gap is that the action set is narrow (run/test) rather than comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ("Run and test the TypeScript LangChain agent locally"), with several specific triggers; coverage is good but actions are limited to running/testing rather than a broad set.	4 / 5
Completeness	Explicitly answers both what (run and test the TS LangChain agent locally) and when via a numbered Use-when clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say ("run locally", "test agent", "start server", "dev mode", "debugging issues") with synonyms and variations covered.	5 / 5
Distinctiveness Conflict Risk	Clear niche (local TS LangChain agent dev/test) with distinct triggers; minor overlap risk with a generic deploy or quickstart skill, but not enough to conflict.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks/app-templates
Path: agent-langchain-ts/.claude/skills/run-locally/SKILL.md
Commit: fdc1b49

Reviewed: 1 day 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.