external-context

Invoke parallel document-specialist agents for external web searches and documentation lookup

Quality

41%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/external-context/SKILL.md

Quality

Discovery

32%

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 provides a general sense of the skill's purpose—invoking agents for web searches and documentation lookup—but is too vague and lacks explicit trigger guidance. It uses technical jargon ('parallel document-specialist agents') that users wouldn't naturally use, and the absence of a 'Use when...' clause makes it difficult for Claude to know when to select this skill over others.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to search the web, look up documentation, find API references, or research external sources.'

Replace technical jargon like 'parallel document-specialist agents' with user-facing language and list concrete actions such as 'searches external websites, retrieves API documentation, fetches reference materials.'

Specify what types of documentation or searches are supported (e.g., API docs, library references, web articles) to improve distinctiveness and reduce overlap with generic search skills.

Dimension	Reasoning	Score
Specificity	Names the domain (document-specialist agents, web searches, documentation lookup) and some actions (invoke, search, lookup), but lacks concrete specifics about what kinds of documents, what outputs are produced, or what formats are supported.	2 / 3
Completeness	Describes what it does at a high level (invoke agents for searches and documentation lookup) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'web searches' and 'documentation lookup,' but uses technical jargon like 'parallel document-specialist agents' that users would not naturally say. Missing common variations like 'search the web,' 'find docs,' 'look up API reference,' etc.	2 / 3
Distinctiveness Conflict Risk	'Web searches' and 'documentation lookup' are fairly broad and could overlap with general search skills or browsing skills. The mention of 'parallel document-specialist agents' adds some distinctiveness but is not clearly differentiated from other search or documentation tools.	2 / 3
	Total	7 / 12 Passed

Implementation

50%

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

This skill provides a clear high-level protocol for parallel document search via sub-agents, with a well-defined three-step workflow. However, it lacks error handling/validation checkpoints for the multi-agent orchestration, the Task tool invocation is pseudocode rather than fully executable, and it doesn't reference or link to the document-specialist agent it depends on.

Suggestions

Add error handling and validation steps: what to do when a sub-agent returns no results, times out, or returns low-quality findings (this is critical for multi-agent orchestration).

Link to or briefly describe the 'oh-my-claudecode:document-specialist' agent definition so the dependency is clear and navigable.

Make the Task tool invocation more concrete by showing the exact API or tool call format expected by the runtime, rather than pseudocode-style examples.

Remove the duplicate mention of the '5 parallel agents' constraint (appears in both Step 2 and Configuration).

Dimension	Reasoning	Score
Conciseness	The skill is reasonably concise but includes some unnecessary repetition (e.g., the maximum 5 agents constraint is stated twice) and the examples section under Usage, while helpful, adds moderate bulk. The markdown template examples are somewhat verbose but serve as output format specifications.	2 / 3
Actionability	The skill provides a clear protocol with step-by-step instructions and shows Task tool invocation syntax, but the code is pseudocode-like rather than truly executable. The Task tool parameters (subagent_type, model) appear to reference a custom framework without explaining the actual API, and the synthesis step is a template rather than concrete guidance on how to merge results.	2 / 3
Workflow Clarity	The three-step workflow (decompose → invoke → synthesize) is clearly sequenced, but there are no validation checkpoints or error handling. What happens if a sub-agent fails or returns no results? There's no feedback loop for retrying failed searches or handling partial results, which is important for a multi-agent orchestration task.	2 / 3
Progressive Disclosure	The content is reasonably well-structured with clear sections, but everything is inline in a single file. The skill references 'oh-my-claudecode:document-specialist' as a sub-agent type but provides no link or reference to its definition. For a skill that orchestrates other agents, a reference to the document-specialist skill definition would improve navigation.	2 / 3
	Total	8 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 3e94567

Reviewed: about 24 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.