aiq-research

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

Quality

87%

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

85%

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

The body is highly actionable with a clear, validated workflow and well-structured references to the bundled helper script. Its only notable weakness is verbosity from the semver explanation and command repetition across multiple sections.

Suggestions

Replace the 'Semantic Versioning Compatibility Rules' explanation with a compact compatibility table or a one-line rule, since Claude already understands semver.

De-duplicate the aiq.py command listings: keep the canonical argument reference in the Available Scripts table and have the Steps/Examples/Common Issues sections reference it rather than re-printing each invocation.

Consider trimming the overlap between the Instructions summary and the Step 1–5 detail so the workflow is stated once.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the Semantic Versioning Compatibility Rules section explains major/minor/patch matching that Claude already knows, and the same aiq.py invocations are repeated across Instructions, Steps, Available Scripts, Examples, and Common Issues.	2 / 3
Actionability	It provides fully executable commands (e.g. `python3 $SKILL_DIR/scripts/aiq.py health`), an argument table per subcommand, and copy-paste-ready examples; the referenced scripts/aiq.py exists in the bundle.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced with an explicit validation checkpoint ("Run health before sending research requests") and feedback loops for failure cases (401/403 handling and offering retry with a narrower query).	3 / 3
Progressive Disclosure	Content is organized into clearly labeled sections with the implementation detail delegated one level deep to scripts/aiq.py, which is referenced and signaled in both the Available Scripts and References tables and verified present in the bundle.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 concise, uses an explicit "Use when..." trigger, and clearly scopes the skill to a reachable NVIDIA AI-Q Blueprint backend. Its main weakness is that it names only one action, so the capability specificity is solid but not comprehensive.

Dimension	Reasoning	Score
Specificity	The description names a concrete action ("run deep research or AI-Q research") and a concrete target ("reachable NVIDIA AI-Q Blueprint backend"), but it lists only a single action rather than multiple specific concrete actions, so it stops at the 'names domain and some actions' anchor.	2 / 3
Completeness	It explicitly answers both what it does ("run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend") and when to use it via the "Use when asked to run..." clause, matching the explicit-trigger anchor.	3 / 3
Trigger Term Quality	The phrases "deep research" and "AI-Q research" are natural terms a user would actually say when requesting this skill, giving good coverage of relevant trigger keywords.	3 / 3
Distinctiveness Conflict Risk	The "NVIDIA AI-Q Blueprint backend" qualifier carves out a clear niche with distinct AI-Q triggers, making it unlikely to fire for unrelated research skills.	3 / 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
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: openai/plugins
Path: plugins/nvidia/skills/aiq-research/SKILL.md
Commit: 11c74d6

Reviewed: about 10 hours 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.