Name: 1k-group-think
Rating: 59.2 (1 reviews)
Author: OneKeyHQ

1k-group-think

Spawns a team of 3 AI agents with different analytical perspectives to collaboratively analyze a problem, propose solutions, and debate trade-offs. Use when facing bugs, design decisions, architecture choices, or any task that benefits from multiple viewpoints. Agents discuss with each other, then present a comparison table for the user to decide. Triggers on "group think", "multi-agent", "team analysis", "3 agents", "collaborative analysis", "debate solutions".

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.skillshare/skills/1k-group-think/SKILL.md

Quality

Content

53%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 a clear sequenced workflow, but it is verbose — re-explaining concepts and duplicating rules across sections — and inlines a large prompt template that would be better placed in a separate referenced file. Tightening repetition and moving the agent prompt template to a bundle file would materially improve it.

Suggestions

Deduplicate the rule statements: the 'Important Rules' section restates guidance already given in 'Critical: Team Members vs Subagents' and the workflow steps — consolidate into one location.

Move the 90-line agent prompt template into a references file (e.g. references/agent-prompt.md) and link to it, reducing SKILL.md to an overview and improving progressive disclosure.

Trim over-explanation of agent-team lifecycle mechanics (idle behavior, subagent vs team member distinctions) that Claude can infer from tool documentation.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the 90-line agent prompt template and several repeated rule blocks ('Important Rules' restating earlier 'Critical' and step-level guidance) pad the skill with content that could be condensed, including some over-explanation of agent-team mechanics Claude can infer.	2 / 5
Actionability	Provides concrete, copy-paste-ready guidance including the Task/TeamCreate/TaskCreate tool invocation forms, agent prompt template, and comparison table skeleton, with only minor gaps around exact SendMessage field formats.	4 / 5
Workflow Clarity	An explicit 8-step sequence with checkpoints (clarify, explore, create team, create tasks, spawn, monitor, present, cleanup) and validation-style facilitation steps (nudge agents, verify cross-agent messaging), though some error-recovery loops are only sketched.	4 / 5
Progressive Disclosure	No bundle files exist in references/scripts/assets, and the skill inlines the entire long agent prompt template and API reference-style material that would benefit from being split into a separate referenced file; references are not used to offload detail.	3 / 5
	Total	13 / 20 Passed

Description

82%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.

A strong description that clearly communicates both what the skill does and when to use it, supported by several natural trigger terms. Minor gains are possible by tightening the over-broad 'any task' clause and listing more granular actions.

Dimension	Reasoning	Score
Specificity	Names the domain (multi-agent analysis) and several concrete actions ('analyze a problem, propose solutions, and debate trade-offs', 'present a comparison table'), but the actions are fairly high-level and could be more granular.	4 / 5
Completeness	Explicitly answers both 'what' (spawns 3 agents to analyze, propose, debate) and 'when' ('Use when facing bugs, design decisions, architecture choices, or any task that benefits from multiple viewpoints') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes multiple natural phrases users would say ('group think', 'multi-agent', 'team analysis', '3 agents', 'collaborative analysis', 'debate solutions') — good coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The multi-agent team analysis niche is distinct from typical skills and unlikely to trigger wrongly, though the broad 'any task that benefits from multiple viewpoints' clause introduces minor overlap risk with general planning skills.	4 / 5
	Total	17 / 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: OneKeyHQ/app-monorepo
Path: .skillshare/skills/1k-group-think/SKILL.md
Commit: 3cff1b4

Reviewed: about 17 hours 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.