ask

Query the bundled research knowledge graph for methodology guidance. Routes questions through a 3-tier knowledge base — WHY (research claims), HOW (guidance docs), WHAT IT LOOKS LIKE (domain examples) — plus structured reference documents. Returns research-backed answers grounded in specific claims with practical application to the user's system. Triggers on "/ask", "/ask [question]", "why does my system...", "how should I...".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 skill body is highly actionable with concrete tool calls and well-sequenced workflows, but it is verbose with redundant re-explanation of the tier-routing logic and monolithic — no bundle files exist despite content (reference doc listings, worked examples, vocabulary tables) that would naturally be split out.

Suggestions

De-duplicate the WHY/HOW/WHAT routing logic: explain the tier model once and have the Classification, Search Strategy, and Worked Examples sections reference it rather than restating it.

Move the large Reference Documents listing (lines ~85-117) and the worked examples into separate reference files under ./references/ and link to them, so SKILL.md stays a lean overview.

Trim the tier-content bullet lists ('What it contains', 'Documents include', 'Examples include') to the essentials Claude cannot infer.

Dimension	Reasoning	Score
Conciseness	The ~380-line body is mostly actionable operational guidance rather than concepts Claude already knows, but the WHY/HOW/WHAT routing and multi-tier logic is re-explained across the Classification, Search Strategy, Worked Examples, and Domain-Aware sections, so it could be tightened significantly.	2 / 3
Actionability	Provides concrete executable MCP calls with arguments (e.g. 'mcp__qmd__deep_search query=... collection="methodology" limit=10'), specific file paths, an executable bash loop, and detailed worked examples with real queries and answers — copy-paste ready guidance.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (EXECUTE NOW steps 1-6, Search Strategy steps 1-5, Domain-Aware steps 1-4) with a fallback chain for qmd lookups and an anti-patterns table acting as a checklist; the task is non-destructive so no validate-retry loop is required.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the body is a monolithic inline document with no bundle files (references/, scripts/, assets/ are absent) and large inline reference listings, vocabulary tables, and worked examples that would benefit from being split into separate files.	2 / 3
	Total	10 / 12 Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states concrete capabilities and provides explicit trigger guidance with natural phrasings. The main weakness is that the natural-language triggers are somewhat generic and could overlap with other system-debugging or advisory skills.

Suggestions

Tie the natural triggers more tightly to the methodology/knowledge-system niche (e.g. 'why does my vault/system use...', 'how should I configure my knowledge system...') to reduce overlap with generic debugging skills.

Consider adding a negative boundary (e.g. 'Not for general coding or file questions') to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Query the bundled research knowledge graph', 'Routes questions through a 3-tier knowledge base', 'Returns research-backed answers grounded in specific claims with practical application' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (query/route through 3 tiers/return research-backed answers) and 'when' via the explicit 'Triggers on ...' clause, matching the anchor for clearly answering both what AND when.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would say — 'why does my system...', 'how should I...' — alongside the '/ask' command forms, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche (methodology research knowledge graph) is distinct, but the natural triggers 'why does my system...' and 'how should I...' are generic enough to overlap with other skills, so it sits at 'somewhat specific but could still overlap' rather than the clearly-distinct anchor.	2 / 3
	Total	11 / 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: skills/ask/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.