CtrlK
BlogDocsLog inGet started
Tessl Logo

write-tui

Use when writing or modifying the kimi-code terminal UI in apps/kimi-code/src/tui — components, dialogs/selectors, slash commands, themes, streaming render, or the KimiTUI controllers. Covers the architecture, where new features go, test placement, the theme system mechanics, and the dialog interaction/visual spec (DESIGN.md).

68

Quality

83%

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

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.

A lean, highly actionable architecture-and-routing reference with a clear submission checklist, weakened only by a missing central referenced file (DESIGN.md) that the body repeatedly defers to for normative detail.

Suggestions

Add the missing ./DESIGN.md to the bundle (or replace the ./DESIGN.md references with the correct existing path), since the body cites it three times as the authoritative dialog/self-check spec.

For the few architectural entries that read as principles ('decide whether it truly belongs here vs. local component state', 'no TUI-state dependency → src/utils; depends on TUI state → src/tui/utils'), add a one-line concrete example or decision rule so they are directly applicable.

Tighten the 'Before you submit' section into an explicit validate→fix→retry loop (e.g. re-run lint/test until clean) to lift workflow clarity above a single end-of-task checkpoint.

DimensionReasoningScore

Conciseness

The body is a dense, information-packed routing guide that assumes Claude's competence — it never explains what a TUI, chalk, or a controller is, and nearly every line is a routing decision, file-path assignment, or hard constraint, so every token earns its place.

5 / 5

Actionability

It gives concrete, copy-usable guidance — exact file paths per feature type ('CLI arguments → src/cli/commands.ts / src/cli/options.ts') and per-controller responsibilities — but a few entries are architectural decision rules rather than executable steps and there is no runnable code/command, keeping it just below the fully copy-paste-ready bar.

4 / 5

Workflow Clarity

A clear orient-then-route-then-validate flow is present ('Before writing TUI code, read apps/kimi-code/AGENTS.md' up front, a 'Before you submit' checklist with lint/format/test and the DESIGN.md self-check at the end), providing a real validation checkpoint, but there is no explicit validate→fix→retry feedback loop for the operations involved.

4 / 5

Progressive Disclosure

Structure and signaling are good — section headers, one-level-deep references to AGENTS.md and DESIGN.md with markdown links — but the centrally-referenced ./DESIGN.md (cited 3× as the normative dialog spec and self-check list) is absent from the skill folder, so the promised disclosure path (overview → DESIGN.md for details) is broken for the reader.

3 / 5

Total

16

/

20

Passed

Description

87%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, well-scoped description with an explicit 'Use when' trigger, concrete capability enumeration, and low conflict risk. The only soft spot is that the action vocabulary is essentially 'writing or modifying' while the rest is topic enumeration rather than distinct verbs.

DimensionReasoningScore

Specificity

The description names the domain ('kimi-code terminal UI') and enumerates many concrete capability areas ('components, dialogs/selectors, slash commands, themes, streaming render, or the KimiTUI controllers', 'architecture, where new features go, test placement, the theme system mechanics, and the dialog interaction/visual spec'), but the action verbs themselves are limited to 'writing or modifying', keeping it just below the comprehensive-multi-action bar of a 5.

4 / 5

Completeness

It explicitly answers both what (writing/modifying the TUI plus the enumerated coverage areas) and when via a concrete 'Use when writing or modifying the kimi-code terminal UI ...' trigger clause with specific triggers, matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.

5 / 5

Trigger Term Quality

It surfaces natural developer-facing terms ('terminal UI', 'slash commands', 'themes', 'dialogs/selectors', 'streaming render', 'KimiTUI controllers') that a user would plausibly say, with good coverage but a few common paraphrases (e.g. 'add a dialog', 'render output') not surfaced as keywords, fitting the 'good coverage, a few missing' anchor.

4 / 5

Distinctiveness Conflict Risk

It is tightly scoped to a single app's TUI directory ('apps/kimi-code/src/tui', 'KimiTUI controllers', 'DESIGN.md'), giving it a clear niche with distinct triggers and minimal realistic conflict with other skills.

5 / 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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
MoonshotAI/kimi-code
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.