ai-ml

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

1.08x

Quality

53%

Does it follow best practices?

Impact

94%

1.08x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/ai-ml/SKILL.md

The canonical home for this skill is ai-ml in sickn33/agentic-awesome-skills

Quality

Content

53%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-structured seven-phase orchestrator with concrete skill-invocation pointers, copy-paste prompts, and checklists, but it leans on abstract task lists and thin redundant copy-paste blocks rather than executable steps or per-phase validation checkpoints. Progressive disclosure is fine for a single-file meta-workflow.

Suggestions

Add per-phase validation checkpoints (e.g., after RAG setup: 'Verify retrieval recall on a held-out sample before proceeding to agent integration') to lift workflow clarity above 3.

Trim the repetitive 'Use @skill to…' copy-paste blocks that restate the skill list, or merge each phase's prompts into a single richer example, to improve conciseness.

Tighten the per-phase 'Actions' into more concrete, executable steps (e.g., name the specific artifact to produce per phase) to move actionability from abstract task-naming toward executable guidance.

Dimension	Reasoning	Score
Conciseness	The body is list-structured with no concept-padding Claude already knows, but each phase carries two-to-three near-identical thin 'Use @skill to…' copy-paste one-liners that restate the skill list — trimmable padding that fits anchor 3 ('mostly efficient but includes some unnecessary… could be tightened'), not 2 (no prose concept explanations) and not 4 (the copy-paste blocks are genuine redundancy).	3 / 5
Actionability	Concrete skill-invocation targets, copy-paste prompts, and checklist items provide some executable guidance, but the per-phase 'Actions' ('Define AI use cases', 'Choose appropriate models') are abstract task-naming rather than executable steps and the prompts are minimal — anchor 3 ('some concrete guidance but incomplete'), not 4 because the vague action lists are a substantial, not minor, gap.	3 / 5
Workflow Clarity	Seven phases are clearly sequenced with numbered actions and end-placed checklists and Quality Gates give some verification, but there are no per-phase validate→fix→proceed feedback loops, so checkpoints are implicit rather than gated — anchor 3 ('steps listed but validation gaps… checkpoints missing or implicit'), not 4 which requires most checkpoints present.	3 / 5
Progressive Disclosure	No bundle files exist and the single file is well-organized into clear phase/checklist/quality-gate headers with easy navigation; as a meta-orchestrator pointing to external skills it legitimately needs no separate files — anchor 4 ('good structure; most content appropriately placed; minor organization gaps'), not 5 (everything is inline with no reference split) and not 3 (no large block is mis-placed inline).	4 / 5
	Total	13 / 20 Passed

Description

52%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 names the AI/ML subdomains the bundle covers but lacks concrete action verbs and any 'Use when…' trigger guidance, capping completeness at 3. Trigger-term coverage is good across the subdomains, though synonyms and file-format cues are missing.

Suggestions

Add an explicit 'Use when…' clause naming concrete user phrasings (e.g., 'Use when building LLM applications, implementing RAG, designing AI agents, or setting up ML pipelines') to lift completeness above 3.

Replace domain noun phrases with concrete verbs the skill performs (e.g., 'orchestrates…', 'guides…', 'sequences…') to improve specificity.

Add natural synonyms and format cues users say (chatbot, embeddings, vector search, retrieval-augmented generation, fine-tuning) to strengthen trigger-term quality.

Dimension	Reasoning	Score
Specificity	The description lists subdomains as noun phrases ('LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features') but names no concrete actions performed on inputs, matching anchor 2 ('Names the domain but actions are minimal or generic').	2 / 5
Completeness	It clearly states the 'what' (a workflow covering those areas) but includes no 'Use when…' clause or equivalent trigger guidance; the rubric caps completeness at 3 for missing explicit 'when' guidance, matching anchor 3 exactly.	3 / 5
Trigger Term Quality	Terms like 'LLM application development', 'RAG implementation', 'agent architecture', and 'ML pipelines' are natural phrasings a user would say across five subdomains, giving good keyword coverage with a few synonyms (chatbot, embeddings, vector search) missing — anchor 4, not 3 (coverage is genuinely broad) and not 5 (synonyms/extensions absent).	4 / 5
Distinctiveness Conflict Risk	It carves a recognizable meta-workflow niche (AI/ML orchestration) but spans five subdomains each backed by its own skills, creating real overlap with those component skills — anchor 3 ('somewhat specific but could still overlap'), not 2 (it is not as broad as generic 'helps with documents').	3 / 5
	Total	12 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/ai-ml/SKILL.md
Commit: 900c504

Reviewed: 1 hour 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.