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

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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: fully concrete dispatch logic with explicit error handling and no token waste. Its weaknesses are that the actual phase sequence lives entirely in referenced files and that all three referenced paths are missing from the bundle, leaving the skill an empty shell as evaluated.

Suggestions

Ship the referenced bundle files (commands/ per-command docs, skills/controller.md, guidelines.md) alongside SKILL.md, or inline a minimal fallback so the dispatcher doesn't point at files that don't exist in the bundle.

Add a one-line phase order (e.g., /ingest → /plan → /revise → /code → /validate → /publish → /respond) so the workflow sequence is visible without loading controller.md.

Make the failure checkpoint an explicit validation criterion, e.g. define per-phase pass conditions ("validate passes only when lint and unit tests are green in CI") instead of illustrating 'unexpected output' by example.

DimensionReasoningScore

Conciseness

The 15-line body is pure dispatch logic — "read the matching file in commands/ and follow it", "read `skills/controller.md`", the /ingest branch — with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching the lean-and-efficient anchor; there is nothing to trim for score 4.

5 / 5

Actionability

Guidance is concrete and executable throughout: exact file paths (commands/, skills/controller.md, guidelines.md), explicit decision branches for command vs. controller entry and Jira-key detection, and a specific failure protocol with named error classes ("Jira MCP errors, test failures, build errors"). Per the instruction-skill note, absence of code is not penalized when guidance is this actionable, and the decision tree covers the common entry cases.

5 / 5

Workflow Clarity

There is a clear dispatch sequence and an explicit error-recovery checkpoint — "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" — which beats the implicit-checkpoint anchor. It falls short of the top anchor because the multi-phase ordering (ingest → plan → code → validate → publish) is deferred to controller.md and failure is defined by examples rather than explicit per-phase validation criteria.

4 / 5

Progressive Disclosure

Structurally the pattern is right — a thin overview delegating to clearly signaled, one-level-deep references (commands/, skills/controller.md, guidelines.md). But none of the three referenced paths exist in the bundle (no references/, scripts/, assets/, commands/, skills/, or guidelines.md are present), so as shipped every reference dangles and navigation fails; scored against the actual bundle structure, this is a significant organization gap beyond the minor-gaps anchor at 4.

3 / 5

Total

17

/

20

Passed

Description

88%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: it chains five concrete third-person actions covering the whole implementation pipeline and closes with an explicit, well-scoped Use-when clause plus command triggers. The only weaknesses are moderate — missing natural synonyms for UI/frontend in the trigger terms and slight overlap with generic dev-workflow skills.

DimensionReasoningScore

Specificity

"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" lists five concrete, third-person actions spanning the full ingest-to-publish pipeline. This matches the anchor for multiple specific concrete actions with comprehensive coverage; score 4 would require minor gaps, but every workflow stage is named.

5 / 5

Completeness

Both questions are answered explicitly: the what is the concrete story-to-code pipeline, and the when is "Use when implementing [UI] stories produced by the design workflow with a ui-design document" plus "Activated by commands: /ingest, /plan, ...". This clearly matches the anchor requiring both what AND when with concrete trigger phrases; the when could not be much more explicit than naming the source workflow, required document, and commands.

5 / 5

Trigger Term Quality

Natural terms are present — "Jira [UI] Story", "UI/front-end stories", "ui-design document", "GitHub PRs", plus explicit command triggers (/ingest, /plan, /code, ...) — giving good keyword coverage for the niche. It falls short of the comprehensive-synonyms anchor because common variations like "user interface", "frontend", or "component" are absent, but exceeds the some-keywords anchor via the command activation list.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — "[UI] stories produced by the design workflow with a ui-design document" — with distinct triggers unlikely to fire for unrelated skills. However phrases like "writes contract-based unit tests and production code via TDD" and "manages review via GitHub PRs" create minor overlap risk with general TDD, code-implementation, or PR-review skills, matching the mostly-distinct anchor rather than the minimal-conflict one.

4 / 5

Total

18

/

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

flightctl/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.