CtrlK
BlogDocsLog inGet started
Tessl Logo

agentic

Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows.

53

Quality

60%

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/agentic/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%

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 dense, well-structured authoring guide with concrete tokens, a clear workflow, and built-in quality gates. Its main weaknesses are minor redundancy across the rules sections and the lack of a worked example showing the expected generated output.

Suggestions

Collapse the overlapping "Rules: Do/Don't", "Quality Gates", and "Example Constraint Language" sections into a single consolidated rules block to remove redundancy.

Add one short worked example of a completed component guideline (e.g. a Button rule set) so the output structure is concrete rather than only templated.

Tighten abstract rules like "preserve visual hierarchy" by anchoring them to a token, threshold, or example, as the Quality Gates section itself recommends.

DimensionReasoningScore

Conciseness

The body is mostly lean bullet lists that assume Claude's competence and avoid explaining basic concepts, but the "Mission"/"Brand" prose and the overlap between "Rules: Do/Don't", "Quality Gates", and "Example Constraint Language" could be tightened.

2 / 3

Actionability

It gives concrete, specific guidance (token values like #FF5701, a 14/16/18/24/32/40 type scale, 8pt spacing, 44px+ touch targets, required states, and a fixed output structure), but a few rules remain abstract ("preserve visual hierarchy", "ensure responsive behavior by default") and there are no worked examples of the actual output it produces.

2 / 3

Workflow Clarity

The "Guideline Authoring Workflow" is a clear six-step numbered sequence ending in a QA checklist, reinforced by an explicit "Quality Gates" validation section, giving a well-sequenced process with a concrete checkpoint.

3 / 3

Progressive Disclosure

It is a single, well-organized file with clearly headed sections and no nested or broken references; no bundle files exist, and nothing in the inline content clearly belongs in a separate file, so the sectioned overview stands on its own.

3 / 3

Total

10

/

12

Passed

Description

50%

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 identifies a recognizable niche (agentic conversational UI) but reads as a style statement rather than an action-oriented skill summary, and it lacks any explicit "Use when" trigger. It sits at the mid-level across all dimensions.

Suggestions

Rewrite the description to lead with concrete actions, e.g. "Authors implementation-ready design-system guidelines for conversational/agentic AI interfaces..."

Add an explicit trigger clause such as "Use when creating or reviewing UI guidelines for agentic workflows, conversational AI interfaces, or agent task flows."

Include natural user-facing terms ("design system", "UI guidelines", "agent interface") alongside the existing jargon to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("agentic workflows", "conversational AI-first interface") and several attributes ("minimal controls, clear outcomes, and delegated task flows"), but these are abstract nouns rather than concrete actions, so it stops short of listing specific executable actions.

2 / 3

Completeness

It conveys a what (a conversational AI-first interface style) but provides no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

It contains some relevant keywords a user might say ("agentic workflows", "conversational AI"), but the phrasing is jargon-heavy ("AI-first interface with minimal controls, clear outcomes, and delegated task flows") and misses common natural variations like "UI design", "design system", or "agent interface".

2 / 3

Distinctiveness Conflict Risk

The "agentic workflows" niche is fairly specific and lowers conflict risk, but "conversational AI-first interface" is broad enough to overlap with general UI/design-system skills, so it is not yet a clearly distinct trigger set.

2 / 3

Total

8

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
bergside/awesome-design-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.