CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

28

Quality

21%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/ai-engineering-toolkit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

42%

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 excels at listing specific, concrete capabilities with impressive detail (dimension counts, checklist sizes), making it clear what the skill does. However, it completely lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill. The trigger terms are somewhat technical and may not match how users naturally phrase requests.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about evaluating prompts, designing RAG systems, auditing AI agents, building evaluation harnesses, or needs AI engineering guidance.'

Include natural language trigger variations users might say, such as 'test my prompt', 'build a retrieval pipeline', 'check agent safety', 'create evals', or 'AI product review'.

Consider adding boundary language to reduce conflict risk, e.g., 'Not for general coding tasks or non-AI engineering workflows.'

DimensionReasoningScore

Specificity

Lists six specific concrete workflows: prompt evaluation with 8-dimension scoring, context budget planning, RAG pipeline design, agent security audit with 65-point checklist, eval harness building, and product sense coaching. These are detailed, concrete actions.

3 / 3

Completeness

The description answers 'what does this do' well but completely lacks any 'when should Claude use it' guidance. There is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric should cap completeness at 2, and since the 'when' is entirely absent, a score of 1 is appropriate.

1 / 3

Trigger Term Quality

Contains some good domain-specific terms like 'RAG pipeline', 'prompt evaluation', 'agent security audit', 'eval harness', but lacks natural user-facing trigger terms. Users might say 'evaluate my prompt', 'design a RAG system', or 'audit my agent' — the description uses more formal/technical naming without covering common variations or natural phrasing.

2 / 3

Distinctiveness Conflict Risk

The six workflows are fairly specific and niche (e.g., 65-point security checklist, 8-dimension prompt scoring), which helps distinctiveness. However, terms like 'prompt evaluation' and 'RAG pipeline design' could overlap with other AI/ML-related skills, and without explicit trigger boundaries, conflict risk remains moderate.

2 / 3

Total

8

/

12

Passed

Implementation

0%

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

This skill reads as a marketing README or product documentation page rather than an actionable skill file for Claude. It describes 6 workflows at a high level but provides none of the actual content needed to execute any of them — no scoring rubrics, no checklists, no decision trees, no templates, no step-by-step instructions. The file is simultaneously too verbose (explaining concepts Claude already knows, repeating safety disclaimers) and too shallow (never providing the actual methodology for any skill).

Suggestions

Replace prose descriptions of each skill with the actual executable content: the 8-dimension scoring rubric with weights, the 65-point security checklist, the RAG decision tree, etc. — either inline or in referenced bundle files.

Remove marketing-style content (overview explaining what skills are, installation instructions, repository links, license info) that wastes tokens without helping Claude execute tasks.

Add concrete step-by-step workflows with validation checkpoints for each skill, e.g., 'Step 1: Score each dimension 1-10 using [criteria]. Step 2: Calculate weighted aggregate. Step 3: Identify bottom 3 dimensions. Step 4: Generate targeted rewrite addressing those dimensions.'

Create bundle files for each of the 6 skills containing their detailed methodologies, and reference them with clear one-level-deep links from the main SKILL.md overview.

DimensionReasoningScore

Conciseness

Extremely verbose for a skill file. The overview section explains what skills are and why consistency matters (Claude already knows this). Descriptions of each skill are lengthy prose summaries rather than actionable instructions. The 'When to Use' section, 'Best Practices', and 'Security & Safety Notes' contain significant redundancy (e.g., the agent-safety-guard disclaimer appears three times in different sections). Installation instructions and repository links waste tokens on information irrelevant to Claude's task execution.

1 / 3

Actionability

Despite describing 6 workflows, the skill provides zero executable code, commands, or concrete step-by-step instructions for any of them. Each skill is described abstractly ('Scores prompts across 8 dimensions', 'Walks through a complete architecture decision tree') without providing the actual scoring rubrics, decision trees, checklists, or templates Claude would need to execute them. The examples show expected outputs but not how to produce them.

1 / 3

Workflow Clarity

No actual workflow steps are provided for any of the 6 skills. The descriptions mention concepts like '65-point red-team audit' and '8 dimensions' but never enumerate the actual steps, checkpoints, or validation criteria. The 'Best Practices' section suggests sequencing skills but doesn't provide the workflow for any individual skill. There are no validation checkpoints or feedback loops defined.

1 / 3

Progressive Disclosure

No bundle files are provided, yet the skill describes 6 complex workflows that clearly need detailed supporting files (scoring rubrics, checklists, decision trees, templates). There are no references to any supporting files within the skill bundle. All content is in a single monolithic file that simultaneously lacks depth on every topic while being verbose in its surface-level descriptions.

1 / 3

Total

4

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
sickn33/antigravity-awesome-skills
Reviewed

Table of Contents

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.