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 rough sense of what the skill does—invoking parallel agents for web searches and documentation lookup—but lacks specificity in concrete actions and entirely omits explicit trigger guidance ('Use when...'). The language leans toward technical jargon ('document-specialist agents') rather than natural user terms, reducing its effectiveness for skill selection.

Suggestions

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

Replace jargon like 'document-specialist agents' with user-facing language and add natural keyword variations such as 'search online,' 'find docs,' 'look up references,' 'external documentation.'

List specific concrete actions the skill performs, e.g., 'Searches external websites, retrieves API documentation, fetches reference materials from multiple sources in parallel.'

Dimension	Reasoning	Score
Specificity	Names the domain (document lookup, web searches) and mentions 'parallel document-specialist agents,' but doesn't list concrete actions beyond 'searches' and 'lookup.' It's somewhat specific but not comprehensive in detailing what operations are performed.	2 / 3
Completeness	Describes what it does (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. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'web searches,' 'documentation lookup,' and 'agents,' but misses common user-facing variations (e.g., 'search the web,' 'find docs,' 'look up API reference,' 'Google'). 'Document-specialist agents' is more technical jargon than natural user language.	2 / 3
Distinctiveness Conflict Risk	The mention of 'parallel document-specialist agents' and 'external web searches' provides some distinctiveness, but 'documentation lookup' is broad enough to overlap with many documentation or search-related skills. The niche is not clearly carved out.	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 subagents, 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 the referenced 'document-specialist' subagent type is never defined or linked. The content is moderately concise but could be tightened.

Suggestions

Add error handling and validation steps: what to do when a subagent returns no results, times out, or returns low-quality/conflicting information

Define or link to the 'oh-my-claudecode:document-specialist' agent specification so the dependency is clear and navigable

Provide concrete guidance on synthesis logic — how to handle conflicting sources, how to rank/prioritize findings, and when to discard low-quality results

Tighten the output template section — Claude can generate markdown formats without a full template; focus on the key structural requirements instead

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes some redundancy — the examples section and the synthesis output template are somewhat verbose. The protocol steps are clear but the markdown template formatting adds bulk without being strictly necessary for Claude to understand the task.	2 / 3
Actionability	Provides a clear protocol with specific steps 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 conflicting or overlapping 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 subagent returns no results, times out, or returns conflicting information? For a multi-agent orchestration task, missing feedback loops and error recovery caps this at 2.	2 / 3
Progressive Disclosure	The content is reasonably structured with clear sections, but everything is inline in a single file. The document-specialist subagent type is referenced but never defined or linked to — there's no reference to where that agent's behavior is specified. For a skill that depends on another agent type, a reference to its 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: 679b418

Reviewed: 3 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.