workflow-multi-cli-plan

Multi-CLI collaborative planning with codebase context gathering, iterative cross-verification, and execution handoff.

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/workflow-multi-cli-plan/SKILL.md

Quality

Content

55%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is highly actionable with excellent workflow clarity — every phase has concrete code, clear sequencing, and explicit validation checkpoints. However, it suffers severely from poor conciseness and progressive disclosure: the entire content is a monolithic wall of detailed code blocks, JSON schemas, and agent prompt templates that should be split across referenced files. The token cost is very high for what could be a concise orchestration overview with pointers to detailed templates.

Suggestions

Extract the synthesis.json schema, agent prompt templates, and executionContext assembly into separate referenced files (e.g., schemas/synthesis.json, templates/discuss-agent-prompt.md, templates/planning-agent-prompt.md) and reference them from the main skill.

Reduce the main SKILL.md to a concise overview of the 5-phase flow with brief descriptions, keeping only the orchestrator's decision logic inline and moving detailed code to bundle files.

Remove redundant information — the agent roles table duplicates what's already clear from the execution flow diagram and phase descriptions.

Consider whether the full AskUserQuestion code block and TodoWrite patterns need to be inline, or could be referenced as standard patterns from a shared utilities file.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~300+ lines with extensive inline code blocks that could be in referenced files. The full synthesis.json schema, detailed agent prompt templates, and complete executionContext assembly are all inlined rather than referenced. Much of this (JSON schemas, agent prompt boilerplate) could be in separate files.	1 / 3
Actionability	The skill provides highly concrete, executable guidance throughout — specific JavaScript code for session initialization, agent invocation with full prompt templates, convergence decision logic, executionContext assembly, and execution handoff. Every phase has copy-paste ready code with specific variable names and file paths.	3 / 3
Workflow Clarity	The 5-phase workflow is clearly sequenced with an ASCII flow diagram, explicit convergence checks between rounds, user decision routing (approve/more analysis/cancel), validation checklists in agent prompts, and clear phase transition logic. The TodoWrite pattern provides progress tracking, and error handling covers failure modes with specific resolutions.	3 / 3
Progressive Disclosure	Despite being a complex multi-phase workflow, everything is crammed into a single monolithic file with no references to external documentation. The full synthesis.json schema, complete agent prompt templates, executionContext assembly, and configuration details are all inline. No bundle files are provided, yet the content clearly warrants splitting into separate files (e.g., schemas, agent prompt templates, configuration reference).	1 / 3
	Total	8 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is heavily laden with abstract jargon and buzzwords without conveying concrete actions or use cases. It lacks a 'Use when...' clause, natural trigger terms, and specific capability descriptions, making it very difficult for Claude to know when to select this skill over others.

Suggestions

Replace abstract terms with concrete actions, e.g., 'Coordinates tasks across multiple Claude CLI instances to plan and execute complex codebase changes' instead of 'Multi-CLI collaborative planning'.

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to coordinate multiple Claude instances, plan large refactors across files, or verify changes across different parts of a codebase.'

Include specific examples of what the skill does, such as 'Gathers context from multiple files, creates a shared plan, assigns subtasks to separate CLI sessions, and verifies results before merging.'

Dimension	Reasoning	Score
Specificity	The description uses abstract, buzzword-heavy language like 'collaborative planning', 'codebase context gathering', 'iterative cross-verification', and 'execution handoff' without describing concrete actions a user would understand. No specific tasks are listed.	1 / 3
Completeness	The 'what' is vague and abstract, and there is no 'when' clause or explicit trigger guidance at all. The description fails to answer either question clearly.	1 / 3
Trigger Term Quality	The terms used are technical jargon ('Multi-CLI', 'cross-verification', 'execution handoff') that users would almost never naturally say. There are no natural keywords a user would type when needing this skill.	1 / 3
Distinctiveness Conflict Risk	The mention of 'Multi-CLI' and 'cross-verification' gives it some distinctiveness from generic skills, but the overall vagueness of 'collaborative planning' and 'execution handoff' could overlap with many workflow or planning skills.	2 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: catlog22/Claude-Code-Workflow
Commit: 07491b0

Reviewed: 20 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.