external-context
Invoke parallel document-specialist agents for external web searches and documentation lookup
61
52%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/external-context/SKILL.mdQuality
Discovery
17%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 overly technical and lacks user-facing language that would help Claude match it to natural user requests. It fails to provide explicit trigger conditions and uses jargon ('parallel document-specialist agents') instead of terms users would actually use. The core functionality is somewhat clear but insufficiently detailed.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'search documentation', 'find API reference', 'look up docs', 'research external sources'
Replace technical jargon ('parallel document-specialist agents') with user-friendly language describing the actual benefit (e.g., 'Searches multiple documentation sources simultaneously')
Specify concrete actions and outputs, such as 'retrieves API references, finds code examples, summarizes technical documentation'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (document-specialist agents) and two actions (web searches, documentation lookup), but lacks comprehensive detail about what specific operations are performed or what outputs are produced. | 2 / 3 |
Completeness | Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Uses technical jargon ('parallel document-specialist agents') that users would not naturally say. Missing common terms like 'search docs', 'find documentation', 'look up', 'API docs', or 'reference'. | 1 / 3 |
Distinctiveness Conflict Risk | 'External web searches' is generic and could overlap with general search skills. 'Documentation lookup' provides some specificity but the scope remains unclear—could conflict with API reference skills or general research skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that efficiently communicates a parallel agent orchestration pattern. The actionable examples and clear output formats are strengths. The main weakness is the lack of error handling or validation guidance for when document-specialist agents return incomplete or conflicting results.
Suggestions
Add guidance for handling agent failures or empty results (e.g., 'If a facet returns no results, note this in synthesis and consider broadening the search terms')
Include a brief validation step before synthesis to check that agent results contain actual citations/URLs
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only the necessary structure and examples without explaining what Claude already knows (web searches, parallel agents, markdown formatting). | 3 / 3 |
Actionability | Provides concrete, copy-paste ready examples including exact Task tool invocations with parameters, specific output format templates, and clear usage examples with real-world queries. | 3 / 3 |
Workflow Clarity | The 3-step workflow is clearly sequenced (decompose → invoke → synthesize), but lacks validation checkpoints or error handling guidance for when agents fail or return poor results. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines), the content is well-organized with clear sections (Usage, Protocol steps, Configuration) and doesn't require external file references. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%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
48ffaac
- Reviewed
Table of Contents
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.