external-context

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

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/external-context/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

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

The body provides a clear, actionable three-step protocol with concrete agent-invocation templates and output contracts, and it is appropriately self-contained. Its main weaknesses are absent validation/feedback steps for failed or low-quality agent results and slight redundancy in the Configuration section.

Suggestions

Add a validation step after parallel invocation, e.g. "If a facet agent fails or returns no citations, re-run that facet once with a refined query before synthesis".

Remove the duplicated "Maximum 5 parallel document-specialist agents" statement and merge the Configuration section into the relevant protocol step to trim redundancy.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with template blocks that earn their place, but "Maximum 5 parallel document-specialist agents" is stated twice and the Configuration section mostly restates prior content — minor trimmable instances matching the score-4 anchor.	4 / 5
Actionability	Concrete Task() invocation strings plus explicit decomposition and output-format templates give mostly executable guidance; placeholders like "<facet 1 description>" are inherent to a parameterized skill, but handling of agent returns is left implicit, keeping it below fully copy-paste-ready.	4 / 5
Workflow Clarity	The decompose -> fan out -> synthesize sequence is clearly listed, but there are no validation checkpoints or feedback loops (e.g. what to do when an agent fails or returns unsourced results); parallel agent fan-out is a batch operation, so the missing feedback loop caps workflow clarity at 3 per the rubric's scoring notes.	3 / 5
Progressive Disclosure	The skill is self-contained with no bundle files and well-organized sections (Usage, Protocol steps, Configuration), and all content is appropriately inline; at roughly 80 lines it exceeds the under-50-line simple-skill threshold that would allow a 5, fitting the good-structure anchor at 4.	4 / 5
	Total	15 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 states a clear, concrete capability but omits any usage trigger, capping completeness at 3 and leaving keyword coverage without natural user phrasings or synonyms. It is a serviceable but incomplete description in the middle of the scale.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to research a topic online, look up external documentation, or gather citations from the web."

Add natural user phrasings and synonyms such as "search the web", "find official docs", or "look up references" to improve trigger-term coverage.

Slightly expand the action list (e.g. "decomposes queries into facets, fans out searches, synthesizes cited findings") to raise specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Invoke parallel document-specialist agents for external web searches and documentation lookup" names the domain and the mechanism (parallel agent invocation), matching the anchor for 1-2 concrete actions without comprehensive coverage; it does not list several distinct actions needed for a 4.	3 / 5
Completeness	The "what" is clear (invoke parallel document-specialist agents for external web searches and documentation lookup), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	"web searches" and "documentation lookup" are relevant keywords, but common natural variations users would say ("search the web", "look up docs", "find official documentation") are missing, matching the anchor for some relevant keywords without synonyms.	3 / 5
Distinctiveness Conflict Risk	The external-context fan-out niche via document-specialist agents is mostly distinct with only minor overlap risk against a general web-research skill; it lacks the distinct trigger phrases of a 5.	4 / 5
	Total	13 / 20 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
Path: skills/external-context/SKILL.md
Commit: dc7ba1d

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.