patterns

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

Quality

61%

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

65%

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-organized, concise index that names specific Langroid APIs and decision criteria per pattern, but it ships no executable code and every reference link is dead because the referenced markdown files are absent from the bundle. Fixing the missing reference files is the highest-impact improvement.

Suggestions

Add the missing reference files referenced in the body (task-return-tool.md, agent-tool-handler-with-state.md, agent-handler-validation-with-state.md, done-sequences-specific-tool.md, run-batch-tasks.md, mcp-tool-integration.md, quiet-mode.md) so each '- Reference:' link resolves.

For batch processing (run_batch_tasks) and task termination, add explicit validation/verification checkpoints so workflow_clarity can reach 3.

Include at least one short inline executable snippet per pattern (or confirm the reference docs contain complete, runnable code) to lift actionability beyond deferring to broken references.

Dimension	Reasoning	Score
Conciseness	The body is a lean index: each entry says what a pattern does and points to a reference, without explaining framework concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	It names concrete APIs (TaskConfig, done_sequences, run_batch_tasks(), @mcp_tool, quiet_mode(), DoneTool/AgentDoneTool) but provides no executable code, deferring it to reference docs, matching 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	The scan-index-then-consult-reference flow is sequenced, and each pattern lists 'use when' decision criteria, but entries involving batch (run_batch_tasks) and terminating tasks lack explicit validation/checkpoint guidance, capping clarity at 2.	2 / 3
Progressive Disclosure	Structure is clean (a one-level index with clearly signaled '- Reference:' links), but none of the referenced files (e.g. ./task-return-tool.md) actually exist in the bundle, so the references don't resolve and navigation breaks.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 clearly scopes the skill to a distinct framework niche and lists covered areas, but it omits explicit 'Use when' trigger guidance and leans on category names rather than concrete actions. Adding a trigger clause would raise both completeness and trigger-term quality.

Suggestions

Append a 'Use when ...' clause naming natural user triggers, e.g. 'Use when the user is building or debugging Langroid multi-agent agents, tools, tasks, or integrations.'

Replace abstract categories with concrete actions where possible (e.g. 'configure agents, define tool handlers, control task termination, batch-process inputs') to lift specificity.

Include natural term variations users might say ('Langroid', 'Langroid agents', 'Langroid tasks', 'Langroid tools') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('Langroid multi-agent LLM framework') and lists covered categories ('agent configuration, tools, task control, and integrations'), but these are topic areas rather than multiple concrete actions, matching the 'names domain and some actions' anchor.	2 / 3
Completeness	It states what the skill covers but never states when to invoke it; per the guidelines a missing 'Use when...' clause caps completeness at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	'Langroid' is the key term a user would say, plus 'multi-agent' and 'LLM', but it lacks common natural variations and offers no trigger phrasing like 'Use when working with Langroid', fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Scoping to the 'Langroid multi-agent LLM framework' carves out a clear niche with distinct triggers unlikely to collide with other skills, matching the top anchor.	3 / 3
	Total	9 / 12 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: 45ee0e2

Reviewed: 2 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.