CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ux-design

UX design workflow that supports early research and exploratory prototyping from a Jira Feature or published PRD, then enriches the same context from its design document and linked [UX] story before implementation handoff. Contexts missing any of those upstream inputs remain exploratory and cannot be handed off to ui-design. Activated by commands: /ingest, /research, /prototype, /evaluate, /handoff, /revise, /publish, /respond.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./ux-design/SKILL.md

The canonical home for this skill is ux-design in flightctl/ai-workflows

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 an exemplary lean orchestrator overview with clear entry logic and an explicit failure checkpoint, but it is entirely navigation: all operational content lives in referenced files, and none of those files are present in the bundle, leaving 11 dangling references. Bundled correctly it would score notably higher on progressive disclosure and actionability.

Suggestions

Ship the referenced files (commands/*.md, skills/controller.md, guidelines.md) in the bundle so the one-level-deep references resolve.

Inline a one-line phase order (ingest > research > prototype > evaluate > handoff) so the workflow shape is visible even before opening controller.md.

Define 'escalate' concretely in the body (e.g. what to do or who/what to hand the failure to) since it is the sole recovery path offered.

DimensionReasoningScore

Conciseness

The ~20-line body is pure instruction with zero padding and no explanation of concepts Claude already knows; every line directs behavior ('read its wrapper', 'read skills/controller.md', 'stop and report the error'). This matches anchor 5: lean, assumes competence, every token earns its place.

5 / 5

Actionability

Guidance is directly executable for an orchestrator skill: named files to read per condition, the phase to execute per input type, and an explicit failure policy. Minor gaps keep it at 4 rather than 5: 'escalate' is undefined in the body and 'execute the first phase the user requests' leaves the phase set implicit, deferring all execution detail to referenced files.

4 / 5

Workflow Clarity

The entry decision tree is clearly sequenced (command invoked vs. controller load, Jira key vs. requested phase) and includes an explicit checkpoint with feedback loop ('If a step fails or produces unexpected output, stop and report... Do not advance... Offer to retry or escalate'). Not 5 because the actual phase progression and per-phase validation are externalized to controller.md and 'escalate' is not defined here.

4 / 5

Progressive Disclosure

On paper the structure is ideal — a concise overview with well-signaled, one-level-deep references (eight command wrappers, controller, guidelines). However, per the rubric guideline to score against the actual bundle structure, the bundle contains no files at all: commands/*.md, skills/controller.md, and guidelines.md are all missing, so every reference is a dead link and the skill is unusable as bundled. This drops it to anchor 3 rather than 4-5.

3 / 5

Total

16

/

20

Passed

Description

70%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.

A solid, domain-specific description in third person with a clear what and explicit command-based activation triggers. Its main weaknesses are abstract action verbs that never state concrete deliverables, and trigger guidance limited to slash commands with no natural-language 'use when' phrasing.

Suggestions

Replace abstract verbs with concrete deliverables, e.g. 'Produces research summaries, exploratory prototypes, and evaluation reports from a Jira Feature or published PRD'.

Add a natural-language trigger clause alongside the command list, e.g. 'Use when the user asks for UX research, prototyping, or design-handoff for a Jira feature or PRD'.

Include a few common synonyms users say (wireframe, mockup, usability) to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain and several workflow-level actions ("supports early research and exploratory prototyping", "enriches the same context from its design document and linked [UX] story", "implementation handoff"), but the verbs are abstract ('supports', 'enriches') and no concrete deliverables or operations are stated. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than 4, which requires specifically enumerated actions.

3 / 5

Completeness

Both parts are present: a clear 'what' (UX design workflow from Jira Feature/PRD through handoff) and explicit trigger guidance ('Activated by commands: /ingest, /research, /prototype, ...'), which is equivalent to a 'Use when' clause so the cap-at-3 rule does not apply. Not 5 because the 'when' covers only command invocation and gives no natural-language usage triggers.

4 / 5

Trigger Term Quality

Good coverage of natural domain terms a user would say: 'UX design', 'research', 'prototyp', 'Jira Feature', 'PRD', 'design document', 'handoff'. A few common variations and synonyms (wireframe, mockup, usability) are missing, so it fits anchor 4 rather than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The skill has a distinct niche (Jira/PRD-driven UX workflow with named phases) and explicitly draws a boundary against the related 'ui-design' skill ('cannot be handed off to ui-design'). Mostly distinct with minor overlap risk against generic design/research skills, matching anchor 4 rather than 5's minimal-conflict profile.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 8 missing

Warning

Total

14

/

16

Passed

Repository

amir-yogev-gh/ai-workflows

Path

ux-design/SKILL.md

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.