allium

Give your AI agents something more useful than a prompt. Velocity through clarity.

Quality

32%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/allium/SKILL.md

Quality

Discovery

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

This description is a marketing slogan rather than a functional skill description. It provides zero information about what the skill does, when it should be used, or what triggers should activate it. It fails on every dimension of the rubric.

Suggestions

Replace the marketing tagline with concrete actions describing what the skill actually does (e.g., 'Generates structured prompts for AI agents' or whatever the actual capability is).

Add an explicit 'Use when...' clause with natural trigger terms that users would actually say when they need this skill.

Use third-person voice to describe specific capabilities (e.g., 'Creates agent configurations, defines tool schemas, and structures system prompts') so Claude can distinguish this skill from others.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Velocity through clarity' is a marketing tagline, not a capability description. There is no indication of what this skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of functionality.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say when needing this skill. 'AI agents', 'prompt', 'velocity', and 'clarity' are vague buzzwords that don't map to any specific user request.	1 / 3
Distinctiveness Conflict Risk	The description is so generic and abstract that it could apply to virtually any skill. There are no distinct triggers or domain-specific terms to differentiate it from other skills.	1 / 3
	Total	4 / 12 Passed

Implementation

64%

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

This is a comprehensive language specification skill with excellent actionability — every construct has concrete, realistic syntax examples. However, the body is too long for a SKILL.md overview; the bulk of the syntax reference should live in the referenced language-reference.md file with only a quick-start subset inline. The workflow for authoring specs could be more explicit with sequenced steps and validation checkpoints.

Suggestions

Move the detailed syntax reference (everything after 'Quick syntax summary') into the language-reference.md file, keeping only 2-3 essential constructs (entity, rule, surface) as a quick-start in SKILL.md.

Add an explicit authoring workflow section with numbered steps (e.g., 1. Define entities → 2. Write rules → 3. Add surfaces → 4. Validate with CLI → 5. Fix errors and re-validate).

Remove the explanatory preamble about the name origin and the 'Allium does NOT' paragraph — Claude doesn't need this context to use the language correctly.

Dimension	Reasoning	Score
Conciseness	The skill is fairly dense and information-rich, but includes some unnecessary preamble (explaining the name's botanical origin, listing what Allium does NOT do). The syntax reference section is efficient with good examples, though the sheer volume of content could benefit from more aggressive splitting into reference files.	2 / 3
Actionability	The skill provides concrete, copy-paste-ready syntax examples for every construct (entities, rules, surfaces, contracts, etc.) with realistic domain examples. The routing table clearly directs Claude to the right tool for each task. Code blocks are complete and illustrative.	3 / 3
Workflow Clarity	The verification section mentions a CLI hook and fallback to the language reference, but lacks explicit step-by-step workflow for writing a spec (e.g., define entities → write rules → add surfaces → validate). The routing table helps with task selection but the actual authoring workflow is implicit rather than sequenced with validation checkpoints.	2 / 3
Progressive Disclosure	References to language-reference.md, test-generation.md, and patterns.md are well-signaled at the bottom, and the routing table points to other skills/agents. However, the body itself is a very long inline syntax reference (~200+ lines) that could largely live in the language reference file, with only a quick-start subset kept in SKILL.md. Bundle files were not provided, so referenced paths cannot be verified.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: DataDog/datadog-agent
Commit: 0f36ad4

Reviewed: about 16 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.