CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-sequenced runbook with concrete commands and validation via expected outputs. It loses points mainly on conciseness padding and a monolithic structure that underuses progressive disclosure.

Suggestions

Trim explanatory filler (Watch Mode benefits, Performance Monitoring, basic Debugging) that restates knowledge Claude already has.

Move the extensive Troubleshooting and per-tool curl examples into reference files under references/ and link to them from the main body to improve progressive disclosure.

Add a brief 'verify servers are up' checkpoint (e.g., curl the health endpoint) right after `npm run dev` before the testing section.

DimensionReasoningScore

Conciseness

Mostly efficient command reference, but padded sections ("Watch Mode" benefits, "Performance Monitoring", basic "Debugging" with console.log) explain things Claude already knows and could be trimmed.

2 / 3

Actionability

Copy-paste-ready curl/npm commands with concrete payloads and expected-response blocks give fully executable guidance throughout.

3 / 3

Workflow Clarity

Multi-step flows (dev servers, the 3-step agent testing, numbered E2E setup) are clearly sequenced, and the 'Expected response' blocks plus Troubleshooting provide validation checkpoints and error recovery.

3 / 3

Progressive Disclosure

External references are well-signaled and one level deep ([MLflow Tracing Guide](../_shared/MLFLOW.md), [Troubleshooting Guide](../_shared/TROUBLESHOOTING.md)), but the body is a largely monolithic ~300-line document with no bundle files and inline content (troubleshooting, all curl examples) that could be split out.

2 / 3

Total

10

/

12

Passed

Description

90%

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 cleanly answers both 'what' and 'when' with explicit, natural trigger phrases and a clear niche. Its only weakness is that the capability list is limited to 'run and test' rather than enumerating multiple concrete actions.

DimensionReasoningScore

Specificity

Names a concrete domain ("TypeScript LangChain agent locally") and two actions ("Run and test"), but only lists two actions so it is not comprehensive like the level-3 anchor.

2 / 3

Completeness

Explicitly states what it does ("Run and test the TypeScript LangChain agent locally") and when to use it via a literal "Use when: (1)... (2)... (3)..." clause.

3 / 3

Trigger Term Quality

Includes natural phrases a user would actually say ("'run locally'", "'test agent'", "'start server'", "'dev mode'") giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The narrow "TypeScript LangChain agent" niche with distinct local-dev triggers is unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
databricks/app-templates
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.