CtrlK
BlogDocsLog inGet started
Tessl Logo

patterns

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

59

Quality

67%

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 ./plugins/langroid/skills/patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 concise, well-organized pattern index with concrete API references and clear trigger conditions, but it contains no inline executable code and its reference files are absent from the bundle, limiting both actionability and progressive disclosure.

Suggestions

Add at least a minimal copy-paste-ready code snippet to each pattern entry so the body is actionable without consulting external files.

Provide the referenced files (./task-return-tool.md, ./agent-tool-handler-with-state.md, etc.) in the bundle, or inline the essential code for each pattern.

For the batch-processing and task-termination patterns, add an explicit validation/checkpoint step (e.g., verify results, check for errors before proceeding) to strengthen the workflow.

DimensionReasoningScore

Conciseness

The body is a lean structured index where each entry is a tight what-and-when paragraph with a single reference pointer; there is no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

Concrete API symbols are named ("TaskConfig(done_sequences=...)", "run_batch_tasks()", "@mcp_tool", "get_tools_async()", "quiet_mode()"), but there are no executable code examples in the body itself—the actual code is deferred entirely to reference files.

3 / 5

Workflow Clarity

The dispatch workflow is clear (scan the index, match a pattern, consult its reference) and each entry has explicit "when" gating, but patterns involving batch processing and task termination lack inline validation checkpoints, which caps workflow clarity at 3.

3 / 5

Progressive Disclosure

The in-body structure is well organized with clearly signaled one-level-deep references, but the referenced files (e.g., ./task-return-tool.md, ./run-batch-tasks.md) do not exist in the bundle, so the disclosure path is broken.

3 / 5

Total

14

/

20

Passed

Description

70%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 clearly scopes the skill to Langroid design patterns and lists concrete capability areas, but it omits any "Use when..." trigger guidance, which limits its completeness. It is distinctive and reasonably specific.

Suggestions

Add a "Use when..." clause naming concrete trigger phrases (e.g., "Use when building multi-agent workflows in Langroid, configuring agent tools, or controlling task termination").

Include natural-language synonyms users might say (e.g., "Langroid agents", "multi-agent LLM", "tool handlers") alongside the domain terms.

Reframe the capability list as concrete actions (e.g., "Configure agents, define stateful tool handlers, control task termination, run batch tasks") rather than abstract categories.

DimensionReasoningScore

Specificity

Names the Langroid domain and lists several concrete capability areas ("agent configuration, tools, task control, and integrations"), but these are categories rather than the concrete actions the score-5 anchor requires.

4 / 5

Completeness

A clear "what" is present (design patterns covering four areas), but there is no "Use when..." trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Good keyword coverage of domain terms a Langroid user would say ("multi-agent LLM framework", "agent configuration", "task control", "MCP tools"), though it lacks natural-language synonyms or variations.

4 / 5

Distinctiveness Conflict Risk

Scoped tightly to the Langroid multi-agent LLM framework, giving it a clear niche with distinct triggers and minimal overlap with other skills.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pchalasani/claude-code-tools
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.