learn

Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".

Quality

88%

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

Quality

Content

77%

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

The body is a well-sequenced, actionable research workflow with strong error recovery, but it is longer than necessary due to repeated output formats and does not split detailed material into reference files. Conciseness and progressive disclosure are the weakest dimensions.

Suggestions

Dedupe the output format: define it once and reference it from Step 3, Step 5, and the Output Summary instead of repeating the block three times.

Move the detailed tool invocation patterns, provenance frontmatter schema, and error-handling table into a reference file (e.g. references/research-patterns.md) and link to it from SKILL.md to improve progressive disclosure.

Consider trimming or relocating the Skill Selection Routing table, which describes sibling skills rather than the /learn workflow itself.

Dimension	Reasoning	Score
Conciseness	Mostly operational and efficient, but the output format is repeated across Step 3, Step 5, and the Output Summary, and the Skill Selection Routing table is tangential — tightening opportunities keep it below the lean-every-token-earns-its-place level.	2 / 3
Actionability	Provides concrete, executable tool calls with parameters (mcp__exa__deep_researcher_start, mcp__exa__web_search_exa), a literal date command, a filename format, and a copy-paste-ready provenance frontmatter template rather than vague or pseudocode guidance.	3 / 3
Workflow Clarity	Clear 6-step sequence with a thorough Error Handling table and tool-cascade fallback feedback loops for error recovery; the operation is non-destructive so the missing-validation cap does not apply.	3 / 3
Progressive Disclosure	Sections are well organized, but with no bundle files everything lives inline in a ~245-line SKILL.md and content that could be split (tool patterns, provenance schema, error table) has no one-level-deep reference files; the under-50-line exception does not apply.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 strong: third-person imperative voice, concrete actions, explicit trigger clause, and a distinctive knowledge-graph research niche. It cleanly answers both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'investigate topics', 'files results with full provenance', 'chains to processing pipeline', 'grow your knowledge graph' — matching the multiple-specific-actions anchor rather than the domain-plus-some-actions level below.	3 / 3
Completeness	Explicitly states what the skill does (research, file results, chain to pipeline) and provides an explicit 'Triggers on ...' when-clause, answering both what and when.	3 / 3
Trigger Term Quality	Includes natural trigger phrases users would actually say — '/learn', '/learn [topic]', 'research this', 'find out about' — giving good coverage rather than only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche — growing a knowledge graph via research with the distinctive '/learn' command — making it unlikely to trigger for the wrong skill; not merely 'somewhat specific' as at level 2.	3 / 3
	Total	12 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skill-sources/learn/SKILL.md
Commit: 2acfd5c

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.