CtrlK
BlogDocsLog inGet started
Tessl Logo

modify-agent

Modify TypeScript LangChain agent configuration and behavior. Use when: (1) User wants to change agent settings, (2) Add/remove tools, (3) Update system prompt, (4) Change model parameters.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent-langchain-ts/.claude/skills/modify-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 content is highly actionable with concrete code for every common modification and good section structure. It loses points on conciseness (basic-concept explanations) and workflow clarity (catalog format with no explicit validation feedback loop).

Suggestions

Trim or move the "TypeScript Best Practices" and "Debugging" sections into a separate reference file; Claude already knows async/await and console.log patterns.

Turn "Testing Changes" into an explicit validate-then-proceed loop: e.g. "Run npm run build; if it reports type errors, fix them and re-run before deploying."

Consider splitting the large 10-item modification catalog into a concise overview in SKILL.md with the rarer modifications (streaming config, MLflow tracing, API endpoints) moved to a reference file.

DimensionReasoningScore

Conciseness

The body is mostly efficient task-oriented code snippets, but the "TypeScript Best Practices" and "Debugging" sections explain concepts Claude already knows (async/await good-vs-bad, module organization, adding console.log), which is unnecessary padding.

3 / 5

Actionability

Each modification ships copy-paste-ready TypeScript/YAML/bash with exact file paths (src/agent.ts, src/tools.ts, .env, app.yaml), and the testing section gives concrete commands, fully covering the common cases.

5 / 5

Workflow Clarity

Modifications are presented as a numbered catalog rather than a sequenced workflow, and the "Testing Changes" section lists run/test/build commands without an explicit validation checkpoint or error-recovery feedback loop.

3 / 5

Progressive Disclosure

The single body is well-organized with clear section headers and uses one-level-deep, clearly signaled references to sibling skills (add-tools, deploy) and external docs; minor gaps are the inlined TypeScript-best-practices and debugging content that could live in separate reference files.

4 / 5

Total

15

/

20

Passed

Description

88%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 strong: it states a clear niche, lists multiple concrete actions, and provides an explicit numbered "Use when" trigger clause. The only gap is slightly thin trigger-term synonym coverage.

DimensionReasoningScore

Specificity

"Modify TypeScript LangChain agent configuration and behavior" names the domain and the "Use when" clause lists four concrete actions (change settings, add/remove tools, update system prompt, change model parameters), matching the comprehensive-coverage anchor.

5 / 5

Completeness

It explicitly states what the skill does (modify TS LangChain agent config/behavior) and gives an explicit "Use when:" clause with four numbered trigger conditions, satisfying both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Phrases like "change agent settings", "Add/remove tools", "Update system prompt", and "Change model parameters" are natural user requests with good coverage, but synonyms and concrete tokens (e.g. "temperature", "LangGraph", file names) a user might actually say are missing, so it sits below the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"TypeScript LangChain agent" is a clear niche distinct from generic skills, but the body references sibling skills (add-tools, deploy, run-locally) that overlap adjacent tasks, so minor overlap risk keeps it just below 5.

4 / 5

Total

18

/

20

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.