CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ui-implement

Story-to-code workflow for UI/front-end stories. Takes a Jira [UI] Story, plans the implementation using discovered design-system and testing conventions, writes contract-based unit tests and production code via TDD, validates against the project's CI expectations, and manages review via GitHub PRs. Use when implementing [UI] stories produced by the design workflow with a ui-design document. Activated by commands: /ingest, /plan, /revise, /code, /validate, /publish, /respond.

Quality

87%

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

The canonical home for this skill is ui-implement 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 hub with explicit routing logic and a strong failure-handling checkpoint, but its quality rests entirely on referenced files (commands/, skills/controller.md, guidelines.md) that are absent from the provided bundle, leaving the skill unverifiable and non-navigable as shipped here.

Suggestions

Ship (or include for review) the referenced bundle files — commands/, skills/controller.md, and guidelines.md — so the hub's references actually resolve; a pointer-only SKILL.md with dangling targets cannot be navigated or verified.

Define the fallback behavior when the user provides no command, Jira key, or phase (e.g., prompt for an issue key or list available phases) instead of the undefined "execute the first phase the user requests".

Briefly enumerate the workflow phases (ingest → plan → code → validate → publish → respond) in the body or confirm controller.md sequences them with per-phase checkpoints, so the 'do not advance on failure' rule has explicit checkpoints to anchor to.

DimensionReasoningScore

Conciseness

The body is ~15 lines of pure routing instruction with zero concept explanation — every line directs an action ("read the matching file in commands/", "read skills/controller.md", "stop and report the error to the user. Do not advance"). Matches the 'lean and efficient; every token earns its place' anchor; nothing could be trimmed without losing information.

5 / 5

Actionability

Routing is concrete and unambiguous — specific paths (commands/, skills/controller.md, guidelines.md), explicit conditions ("If the user provided a Jira issue key or URL, execute the /ingest phase"), and a fully specified failure path. Falls short of 'fully executable' because the instructions depend on files not present in the provided bundle, and "execute the first phase the user requests" leaves the no-input case undefined — minor gaps, matching anchor 4.

4 / 5

Workflow Clarity

The orchestrator's own sequence is clear with an explicit error checkpoint and feedback loop ("If a step fails or produces unexpected output... stop and report the error to the user. Do not advance to the next phase. Offer to retry the failed step or escalate"). Not 5 because the multi-phase workflow it orchestrates is never sequenced in the body — it is delegated wholesale to skills/controller.md — leaving the happy-path checkpoints implicit here.

4 / 5

Progressive Disclosure

On paper the structure is ideal — a lean hub with clearly signaled one-level-deep references (commands/, skills/controller.md, guidelines.md) — but none of these referenced files exist in the bundle as provided (no references/, scripts/, assets/, or any other files alongside SKILL.md), so every reference dangles and navigation cannot be completed. The organization of what is written exceeds anchor 3, but unverifiable/missing targets mean it cannot be credited as well-organized end-to-end (anchor 4).

3 / 5

Total

16

/

20

Passed

Description

92%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 strong description in third-person voice: it enumerates the complete story-to-code pipeline as concrete actions, gives an explicit 'Use when' trigger clause tied to a specific story type, and lists activation commands. The only weakness is modest synonym coverage in trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full pipeline — "Takes a Jira [UI] Story, plans the implementation..., writes contract-based unit tests and production code via TDD, validates against the project's CI expectations, and manages review via GitHub PRs" — matching the anchor for comprehensive coverage of specific concrete actions. Not 4 because no phase of the workflow is left uncovered; ingest through publish are all named.

5 / 5

Completeness

Both questions are answered explicitly: the what is the full action pipeline quoted above, and the when is a concrete trigger clause — "Use when implementing [UI] stories produced by the design workflow with a ui-design document". Not 4 because the when-clause is already explicit and specific, not merely present.

5 / 5

Trigger Term Quality

Good natural-term coverage: "implementing [UI] stories", "UI/front-end", "unit tests", "TDD", "GitHub PRs", "ui-design document", plus the explicit slash-command list. A few natural synonyms are missing (e.g., "frontend" unhyphenated, "ticket", "issue", "component"), which fits anchor 4 rather than 5's comprehensive-synonym coverage; it clearly exceeds anchor 3's 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — Jira [UI] stories "produced by the design workflow with a ui-design document" — with distinct triggers, so overlap risk with general coding or non-UI skills is minimal. Not 4 because the trigger conditions are narrow and unambiguous rather than leaving minor overlap risk.

5 / 5

Total

19

/

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

amir-yogev-gh/ai-workflows

Path

ui-implement/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.