CtrlK
BlogDocsLog inGet started
Tessl Logo

oracle

System architect and design expert - provides strategic technical guidance

41

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/oracle/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 cleanly organized but largely generic persona brief: the Output Format template is genuinely actionable, while the Approach, Scenarios, and Principles sections mostly restate process steps Claude already knows. Workflow sequencing is clear but lacks checkpoints.

Suggestions

Trim the generic Approach, Example Scenarios, and Principles sections that restate process steps Claude already knows, and remove the decorative closing quote.

Replace high-level hints ('Consider pros/cons', 'Identify bottlenecks') with concrete methodology, e.g. specific trade-off frameworks, decision criteria, or a worked architectural decision record example.

Keep and foreground the 5-part Output Format template, which is the most actionable part of the skill.

DimensionReasoningScore

Conciseness

Several sections restate process knowledge Claude already has ('Ask clarifying questions', 'Consider pros/cons', 'Avoid over-engineering', 'Balance ideal vs practical') and a decorative closing quote adds no value, matching the score-2 anchor 'Noticeably verbose; several unnecessary explanations or padded sections'. It is not a 3 because the padding is widespread rather than a single tightenable spot.

2 / 5

Actionability

The Output Format section provides a concrete, copy-ready 5-part template (Analysis, Options, Recommendation, Rationale, Next Steps), but the Approach and Example Scenarios sections give only high-level hints ('Identify bottlenecks', 'Consider team expertise') without specific methods, fitting the score-3 anchor 'Some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

The Approach section lists a clear 4-step sequence (Understand Context, Analyze Trade-offs, Recommend, Plan) and the Output Format adds another, but there are no validation/checkpoint steps anywhere, matching the score-3 anchor 'Steps listed but validation gaps; checkpoints missing or implicit'. The destructive/batch cap does not apply since this is advisory work.

3 / 5

Progressive Disclosure

The body is organized into clear, well-labeled sections (Core Expertise, When to Use, Approach, Scenarios, Principles, Output Format) with no nested or buried references and no need for external files, fitting the score-4 anchor 'Good structure; most content is appropriately placed'. It is not a 5 because the body is slightly over the ~50-line simple-skill threshold and contains padding that could be split or trimmed.

4 / 5

Total

12

/

20

Passed

Description

36%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 reads as a persona label rather than a trigger-oriented capability statement: it names a domain but gives only a vague action and no usage triggers. This limits both completeness and specificity.

Suggestions

Add an explicit 'Use when...' clause with concrete triggers, e.g. 'Use when starting new projects, planning system architecture, making major refactoring decisions, or choosing between technical approaches'.

Replace 'provides strategic technical guidance' with specific actions such as 'analyzes architectural trade-offs, recommends technology stacks, and reviews code for structural issues'.

Add natural trigger phrases users actually say (e.g. 'architecture review', 'should I use X or Y', 'is this design scalable') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('System architect and design expert') but the only action ('provides strategic technical guidance') is generic and abstract, matching the score-2 anchor 'Names the domain but actions are minimal or generic'. It does not list the concrete actions (e.g. trade-off analysis, stack selection, architectural review) needed for a 3.

2 / 5

Completeness

It offers only a vague 'what' ('provides strategic technical guidance') and entirely omits any 'Use when...' trigger clause, matching the score-2 anchor 'Has a vague what and no when'. The missing-Use-when cap at 3 is a ceiling, not a floor, and the vague 'what' pulls it to 2.

2 / 5

Trigger Term Quality

It includes a couple of relevant keywords a user might say ('architect', 'design', 'system'), but the dominant phrase 'strategic technical guidance' is jargon and common variations/synonyms ('architecture review', 'help me choose between X and Y', 'is this design good') are missing, fitting the score-3 anchor 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

'System architect and design expert' carves out a recognizable niche, but 'strategic technical guidance' is broad and would overlap with general code-review or technical-advice skills, fitting the score-3 anchor 'Somewhat specific but could still overlap with similar skills'.

3 / 5

Total

10

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
TurnaboutHero/oh-my-antigravity
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.