wolf-scripts-agents

Agent coordination, orchestration, and multi-agent workflow management scripts

1.42x

Quality

28%

Does it follow best practices?

Impact

97%

1.42x

Average score across 6 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/agent-coordination/wolf-scripts-agents-majiayu000-claude-skill-regist/SKILL.md

Quality

Discovery

22%

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 too vague and abstract, relying on buzzwords like 'coordination' and 'orchestration' without specifying concrete actions or when the skill should be used. It lacks a 'Use when...' clause and does not list specific capabilities, making it difficult for Claude to reliably select this skill from a pool of alternatives.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to coordinate multiple agents, delegate subtasks across agents, or set up multi-agent pipelines.'

Replace abstract terms with concrete actions, e.g., 'Spawns sub-agents, routes tasks between agents, aggregates results from parallel agent runs, and manages agent lifecycle.'

Include natural trigger terms users might say, such as 'run multiple agents', 'fan-out tasks', 'agent pipeline', 'delegate to agents', or 'parallel execution'.

Dimension	Reasoning	Score
Specificity	The description uses abstract language like 'coordination', 'orchestration', and 'management' without listing any concrete actions. It does not specify what the skill actually does (e.g., spawn agents, route tasks, merge results).	1 / 3
Completeness	The description only vaguely addresses 'what' and completely omits 'when' — there is no 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Terms like 'agent', 'multi-agent', and 'orchestration' are somewhat relevant keywords a user might use, but the description lacks common variations or natural phrasing users would say (e.g., 'run multiple agents', 'delegate tasks', 'parallel agents').	2 / 3
Distinctiveness Conflict Risk	The 'multi-agent' and 'orchestration' terms provide some niche specificity, but 'coordination' and 'workflow management scripts' are broad enough to overlap with general workflow or scripting skills.	2 / 3
	Total	6 / 12 Passed

Implementation

35%

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

This skill is extremely verbose, containing extensive pseudocode, redundant good/bad examples, and over-explained rationale that inflates it well beyond what Claude needs. While it covers the coordination patterns comprehensively and provides useful CLI commands and configuration shapes, most code examples are illustrative rather than executable, and the document would benefit enormously from being split into an overview with references to detailed files. The 'Red Flags' and lengthy bad examples add little value for an AI agent.

Suggestions

Cut content by 60-70%: remove the Red Flags section, collapse good/bad examples to 1 brief example per pattern, remove explanatory prose about why coordination matters, and trim class definitions to only show the key methods with real implementations.

Make code examples executable: replace pseudocode class bodies (empty methods with comments like '// Persist state to disk/database') with actual working implementations or remove them entirely and just show the usage patterns.

Split into overview + reference files: move the detailed role file patterns, full class definitions, and message format specifications into separate reference files, keeping SKILL.md as a concise overview with links.

Add explicit error recovery steps: for the workflow orchestrator, show concrete code for what happens when a phase fails, how to inspect the error, and how to resume - not just 'resume from last phase'.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~600+ lines. Includes extensive pseudocode class definitions, lengthy good/bad examples with redundant explanations, 'Red Flags' section that over-explains obvious points, and a massive verification checklist. Much of this content (like explaining why manual coordination is bad) is unnecessary for Claude. The good/bad examples alone consume ~150 lines repeating what was already stated.	1 / 3
Actionability	Provides code examples but most are pseudocode or illustrative rather than executable - the WorkflowOrchestrator class has empty method bodies with comments, the MailboxClient methods have placeholder comments. Configuration objects and CLI commands are concrete, but the core patterns show API shapes rather than working implementations.	2 / 3
Workflow Clarity	The workflow orchestrator section describes sequential phases and state saving, and the integration example shows a complete flow with validation. However, explicit validation checkpoints and error recovery feedback loops are mostly absent - the orchestrator's executeWorkflow method is pseudocode with comments, and there's no concrete guidance on what to do when a phase fails mid-workflow beyond 'resume from last phase'.	2 / 3
Progressive Disclosure	References related skills (wolf-roles, wolf-governance, etc.) and lists file locations, which is good. However, the document itself is monolithic - the massive good/bad examples, the full role file patterns, and the complete class definitions should be in separate reference files. The content that is inline far exceeds what an overview should contain.	2 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (943 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: majiayu000/claude-skill-registry
Commit: d156cd1

Reviewed: about 4 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.