external-context

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

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

The body is well-structured and highly actionable with concrete Task invocations and templates, but it lacks validation/feedback checkpoints for its batch parallel-agent workflow and carries minor redundancy between the protocol and configuration sections.

Suggestions

Add an explicit validation step after parallel invocation, e.g. verify each facet returned citable sources and re-run any agent that returned empty or low-quality results before synthesis.

Remove the duplicated 'Maximum 5 parallel document-specialist agents' statement and fold the Configuration section into the relevant steps to tighten the token budget.

Include a brief error-handling note for when WebSearch/WebFetch fail or rate-limit during a facet search.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not explain concepts Claude already knows, but 'Maximum 5 parallel document-specialist agents' is restated in Step 2 and the Configuration section repeats Step 2's limits, so it could be tightened.	2 / 3
Actionability	It provides concrete, near-copy-paste-ready Task(...) invocations with real parameters (subagent_type, model, prompt) plus explicit decomposition and synthesis templates, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The three-step sequence (decompose, invoke in parallel, synthesize) is clear, but there are no validation or verification checkpoints for a batch operation of up to 5 parallel agents, capping workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Content is well-organized into clear sections (Usage, Protocol, Configuration), is self-contained, and has no nested or deeply-referenced bundle files, satisfying the simple-skill exception for a 3.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 is third-person and states the skill's purpose concretely, but it omits any explicit 'when to use' trigger guidance and leans on internal jargon ('document-specialist agents'), leaving every dimension at the mid-level.

Suggestions

Add a 'Use when...' clause with natural trigger terms, e.g. 'Use when the user asks to research a topic online, look up documentation, or compare technologies across sources.'

Replace jargon like 'document-specialist agents' with user-facing language ('parallel document research agents') and include common phrasings users would actually say.

Add one more concrete capability to broaden specificity beyond web searches and documentation lookup.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Invoke parallel document-specialist agents', 'web searches', 'documentation lookup') and the external-context domain, but the action list is not comprehensive like the level-3 anchor's three granular actions.	2 / 3
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness caps at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	'web searches' and 'documentation lookup' are somewhat natural, but 'document-specialist agents' is internal jargon a user would not say, and common variations ('search the web', 'look up docs') are missing.	2 / 3
Distinctiveness Conflict Risk	The external-context-via-parallel-agents niche is somewhat specific, but it could overlap with a general web-search skill and lacks explicit triggers to distinguish it.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 6c59219

Reviewed: about 6 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.