recommend

Get research-backed architecture advice for your knowledge system. Describe your use case, constraints, and goals — get specific recommendations grounded in TFT research with rationale for each decision. Triggers on "/recommend", "what would you recommend", "architecture advice", "knowledge system for".

Quality

88%

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 body is a well-sequenced, highly actionable advisory workflow with strong validation structure, but it is verbose and monolithic — much of the templated detail and exposition could be tightened or moved into reference files, and its referenced files are not present in the bundle to verify.

Suggestions

Tighten the Philosophy and Quality Standards/anti-patterns sections and collapse the repeated full output templates into one compact canonical template to improve conciseness.

Move the per-dimension position tables, edge-case scripts, and large output-format blocks into reference files so SKILL.md stays a lean overview with clearly signaled one-level-deep links.

Verify or include the six referenced reference files (tradition-presets.md, methodology.md, components.md, dimension-claim-map.md, interaction-constraints.md, claim-map.md) in the bundle so progressive-disclosure navigation is confirmed rather than assumed.

Dimension	Reasoning	Score
Conciseness	It does not pad with concepts Claude already knows, but the ~550-line body carries substantial verbosity — the Philosophy section, repeated full output templates, scripted edge-case dialogues, and Quality Standards/anti-patterns that could be tightened or externalized. It fits the 'mostly efficient but could be tightened' anchor rather than the lean score-3 anchor.	2 / 3
Actionability	Concrete, executable guidance: named qmd MCP tool calls (mcp__qmd__deep_search query="..."), explicit per-dimension positions with key signals, confidence tables, and a precise output-format template. As an instruction-only skill, absence of code is not penalized and the guidance is specific and actionable.	3 / 3
Workflow Clarity	A clear six-phase sequence (1a/1b/1c through 6) with explicit validation checkpoints in Phase 5 — hard blocks, soft warns, and cascades — plus feedback loops (adjust the lower-confidence dimension, re-validate) and confidence assignment, matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	It points to six one-level-deep reference files clearly signaled in Step 0 and per-phase, but no bundle/reference files are present to verify, and the body itself remains a long monolith with large inline output templates, dimension tables, and edge-case scripts that could be split out — fitting the 'content that should be separate is inline' anchor.	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 specific, uses natural trigger terms, explicitly covers both what the skill does and when to use it, and carves out a clear niche. It is concise without padding and avoids first/second person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "research-backed architecture advice", "get specific recommendations ... with rationale for each decision", and instructs the user to "Describe your use case, constraints, and goals" — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what the skill does (research-backed recommendations with rationale) and when to use it via an explicit "Triggers on ..." clause, satisfying the both what-and-when anchor.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say — "/recommend", "what would you recommend", "architecture advice", "knowledge system for" — giving good coverage of natural terms rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The knowledge-system architecture niche with distinctive triggers ("architecture advice", "knowledge system for") is unlikely to fire for unrelated skills, though it sits adjacent to sibling skills like /architect.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (558 lines); consider splitting into references/ and linking	Warning
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	13 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skills/recommend/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.