ai-ml

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

Quality

56%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ai-ml/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

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-organized but repetitive catalog of phases, skills, and prompts; it provides some actionable guidance yet lacks concrete per-phase steps, validation checkpoints, and any external file structure for progressive disclosure.

Suggestions

Collapse the repeated per-phase scaffolding into a compact template or table to remove redundancy and tighten token use.

Add concrete, executable steps to each phase's 'Actions' list (specific commands, prompts, or API calls) rather than generic imperatives.

Insert validation/verification checkpoints between phases (e.g., 'Before advancing to Phase N, confirm the Phase N-1 checklist passes') and consider splitting detailed skill catalogs into a referenced reference file.

Dimension	Reasoning	Score
Conciseness	The 7-phase structure repeats the same Skills/Actions/Copy-Paste-Prompts scaffolding and includes redundant near-duplicate skill entries (e.g., 'autonomous-agents' and 'autonomous-agent-patterns'); it avoids explaining known concepts but is padded and repetitive where it could be tightened.	3 / 5
Actionability	Copy-paste prompts and named skills are executable, but the per-phase 'Actions' lists are high-level and generic ('Define AI use cases', 'Choose appropriate models') without the concrete steps needed to execute them.	3 / 5
Workflow Clarity	A clear 7-phase sequence with checklists and quality gates exists, but there are no validation or verification checkpoints between phases, so it sits at the level-3 anchor of 'steps listed but checkpoints missing'.	3 / 5
Progressive Disclosure	Content is well-sectioned but entirely inlined in a 258-line monolithic SKILL.md with no bundle files and no references to separate files, so it is only 'some structure' rather than the one-level-deep referenced split the level-5 anchor describes.	3 / 5
	Total	12 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 clearly conveys the AI/ML scope and lists multiple relevant sub-domains with natural trigger terms, but it omits any explicit 'Use when...' guidance and risks overlapping with the specific skills it orchestrates.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when building LLM apps, RAG systems, AI agents, or ML pipelines').

Sharpen the description with concrete verbs (e.g., 'orchestrates', 'sequences') rather than only naming domains, to distinguish it from the individual bundled skills.

Include common synonyms/extensions users say (e.g., 'chatbots', 'retrieval', '.ipynb') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete sub-areas ('LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features'), though these are domains rather than concrete verbs like 'extract' or 'merge', leaving minor gaps versus the level-5 anchor.	4 / 5
Completeness	Has a clear 'what' but no explicit 'Use when...' trigger clause; per the rubric guideline, a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users say ('LLM', 'RAG', 'agents', 'ML pipelines', 'AI-powered features') but is missing common synonyms and file extensions that would push it to level 5.	4 / 5
Distinctiveness Conflict Risk	The broad AI/ML umbrella overlaps with the very individual skills it bundles (rag-engineer, ml-engineer, etc.), so it could trigger for a more specific skill; not clearly a distinct niche.	3 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/ai-ml/SKILL.md
Commit: 1f67c44

Reviewed: about 17 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.