external-context

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

Quality

63%

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

72%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 content is lean, actionable, and well-structured for a self-contained skill. Its main weakness is the absence of validation/feedback loops for the batch parallel-agent operation, which caps workflow clarity.

Suggestions

Add a validation checkpoint after parallel agents return (e.g., verify each facet yielded cited sources; re-invoke a facet if results are empty or uncited) to introduce a feedback loop.

Include brief error-recovery guidance for when a document-specialist agent fails or returns no sources.

Consolidate the two near-identical Task() example blocks into one parameterized example to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is efficient and avoids explaining concepts Claude already knows, using templates and concrete Task() calls; only minor instances (repeated near-identical Task() blocks, placeholder-heavy templates) could be trimmed, fitting the 'efficient, minor over-explanation' anchor below the fully lean anchor 5.	4 / 5
Actionability	Provides concrete, mostly-executable Task() invocations with subagent_type, model, and prompt text plus output-format templates, but uses placeholders like '<facet 1 description>' leaving minor gaps versus copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	Three steps are clearly sequenced (decompose, invoke in parallel, synthesize) but the workflow is a batch operation (up to 5 parallel agents) with no validation that agents returned useful results and no error-recovery feedback loop, so per the batch-operations cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	The skill is short and self-contained with well-organized sections (Usage, Protocol, Configuration) and no nested or external references; per the simple-skill guidance this matches the 'well-organized sections, no external references needed' anchor.	5 / 5
	Total	16 / 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 conveys a clear mechanism and domain but omits any explicit 'when to use' guidance, capping completeness and trigger quality. It is reasonably distinct from other skills but would benefit from concrete trigger phrases.

Suggestions

Add a 'Use when ...' clause naming concrete trigger situations (e.g., 'Use when the user needs current external documentation, library docs, or web references beyond your training data').

Include natural synonyms and variations such as 'look up docs', 'search the web', 'find references' to improve trigger-term coverage.

List the concrete outcomes (fetch docs, find examples, gather citations) to lift specificity from 1-2 actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of concrete actions ('Invoke parallel document-specialist agents', 'external web searches', 'documentation lookup') but coverage is not comprehensive, matching the '1-2 concrete actions' anchor rather than the multi-action anchor 4.	3 / 5
Completeness	Clearly states what the skill does but lacks any 'Use when...' trigger clause; per guidelines a missing explicit trigger caps completeness at 3, matching the 'clear what, when missing' anchor.	3 / 5
Trigger Term Quality	Contains relevant natural terms ('web searches', 'documentation lookup') but misses common variations and synonyms users might say, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (parallel document-specialist agents for external lookups) with minor overlap risk against general web-search skills, fitting the 'mostly distinct' anchor rather than the fully distinct anchor 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: 5aa678c

Reviewed: 8 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.