patterns

Design patterns for the Langroid multi-agent LLM framework. Covers agent configuration, tools, task control, and integrations.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/langroid/skills/patterns/SKILL.md

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 a well-structured pattern index with lean, decision-oriented entries and concrete API pointers, delegating full code examples to one-level-deep references. The main risks are that the referenced documents are absent from the bundle and the body offers no inline quick-start example.

Suggestions

Ensure the seven referenced pattern documents (e.g., task-return-tool.md, run-batch-tasks.md) actually ship with the skill bundle, ideally under references/ with matching paths.

Add a short quick-start snippet (one minimal agent+task example) inline so a user can act without opening a reference file.

Dimension	Reasoning	Score
Conciseness	The index assumes Claude's intelligence (no explanation of what Langroid or design patterns are) and each entry states non-obvious decision criteria, but 'Use this pattern when:' is repeated across entries and some (a)-(d) condition lists could be tightened, matching anchor 4 rather than 5.	4 / 5
Actionability	Concrete API specifics are given inline ('TaskConfig(done_sequences=["T[ToolName]"])', 'run_batch_tasks()', '@mcp_tool', 'quiet_mode()') with references to complete code examples, but there is no copy-paste code in the body itself and the referenced example files could not be verified, matching anchor 4.	4 / 5
Workflow Clarity	The navigation instruction ('Scan this index to find patterns matching your needs, then consult the corresponding document') is unambiguous and entries include explicit differentiating criteria (e.g., #2 vs #3 on retry/validation), but there is no quick-start path or guidance when no pattern matches, matching anchor 4.	4 / 5
Progressive Disclosure	Each pattern has a clearly signaled one-level-deep reference ('Reference: ./task-return-tool.md' etc.) in a well-organized index, matching the anchor-5 structure; however, none of the seven referenced files exist in the bundle (no references/ directory and no root .md files), so the references cannot be verified as real, holding this at anchor 4.	4 / 5
	Total	16 / 20 Passed

Description

65%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 distinctive and domain-specific thanks to the explicit Langroid framing, with reasonable trigger keywords. Its main weaknesses are the absence of any 'when to use' trigger guidance and the use of coverage-area nouns instead of concrete capability verbs.

Suggestions

Add an explicit trigger clause, e.g., 'Use when building or configuring Langroid agents, defining tool handlers, controlling task termination, or integrating MCP tools.'

Convert coverage nouns into concrete capability verbs, e.g., 'Configure agents and tools, control task termination via done_sequences, run batch tasks, and integrate MCP servers.'

Include natural user phrasings such as 'tool handler', 'agent state', or 'run_batch_tasks' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain precisely ('Design patterns for the Langroid multi-agent LLM framework') and lists four coverage areas ('agent configuration, tools, task control, and integrations'), but these are topic nouns rather than concrete actions, matching anchor 3 rather than 4.	3 / 5
Completeness	The 'what' is clear (design patterns covering agent configuration, tools, task control, and integrations), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	'Langroid', 'multi-agent', 'agent', 'tools', 'task control' are natural terms a user of this framework would say, giving good keyword coverage; a few natural synonyms (e.g., 'tool handler', 'pipeline', 'chatbot') are missing, so it falls short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Naming a specific niche framework ('Langroid multi-agent LLM framework') gives a clear niche with distinct triggers and minimal conflict risk with other skills, matching anchor 5.	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pchalasani/claude-code-tools
Path: plugins/langroid/skills/patterns/SKILL.md
Commit: 0ca7320

Reviewed: 13 days 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.