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).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%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.

An exemplary architecture/routing skill: lean, path-precise, and immediately actionable, with a sound progressive-disclosure shape (overview here, hard constraints in AGENTS.md, dialog spec in DESIGN.md). The main gap is operational: the referenced DESIGN.md is missing from the bundle, so the normative dialog self-check cannot actually be walked.

Suggestions

Include DESIGN.md in the skill bundle (the body calls it normative and requires walking its self-check list before submitting); without it the dialog rules are unenforceable.

Add a brief fix-and-retry note to the 'Before you submit' section (what to do when lint/format/test or the CI guards flag a change) to close the workflow's feedback loop.

Mention the TUI abbreviation (or a synonym) in the frontmatter description so users who say 'TUI' rather than 'terminal UI' still trigger the skill.

Dimension	Reasoning	Score
Conciseness	Dense, decision-routing bullets with exact paths and identifiers ('components/messages/tool-renderers/registry.ts', 'buildSkillSlashCommands', 'saveTuiConfig', 'mountEditorReplacement') and no explanation of concepts Claude already knows. Every token earns its place — matches the lean/efficient 5 anchor rather than 4.	5 / 5
Actionability	For an instruction-only skill the guidance is fully concrete: a feature-type routing table with exact landing files, named functions for the theme apply/switch flow, and hard rules ('a component never writes the config file itself', 'do not stack branches inside ToolCallComponent'). No missing key details, so it fits the fully-executable 5 anchor rather than the minor-gaps 4.	5 / 5
Workflow Clarity	Clear sequence — read apps/kimi-code/AGENTS.md first, route the feature, then the 'Before you submit' checklist (lint/format/test, walk the DESIGN.md self-check, keep printableChar()/chalk.hex guards). Validation for the riskiest area (dialogs) is deferred to an external checklist and no fix-and-retry loop is described, so it matches 'most checkpoints present; minor validation gaps' (4) rather than the explicit-feedback-loop 5 anchor.	4 / 5
Progressive Disclosure	Well-sectioned overview with clearly signaled one-level-deep references (apps/kimi-code/AGENTS.md, ./DESIGN.md), fitting 'good structure; references mostly clear; minor organization gaps'. It falls short of 5 because the normative ./DESIGN.md it relies on is not present in the skill's bundle, leaving the primary detailed reference dangling.	4 / 5
	Total	18 / 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: third-person, explicit 'Use when' trigger with concrete scope, and a specific inventory of covered capabilities, all anchored to an unambiguous repo path. The only weakness is missing common synonyms such as 'TUI'.

Dimension	Reasoning	Score
Specificity	Names the domain (kimi-code terminal UI in apps/kimi-code/src/tui) and multiple concrete capabilities — components, dialogs/selectors, slash commands, themes, streaming render, KimiTUI controllers — plus what the skill covers (architecture, feature routing, test placement, theme mechanics, dialog spec). Comprehensive coverage with no notable gaps, matching the 5 anchor rather than 4.	5 / 5
Completeness	Explicitly answers both: 'Use when writing or modifying the kimi-code terminal UI in apps/kimi-code/src/tui' (when, with concrete triggers) and 'Covers the architecture, where new features go, test placement, the theme system mechanics, and the dialog interaction/visual spec' (what). Clear match to the 5 anchor; the 4 anchor's 'when could be more explicit' does not apply.	5 / 5
Trigger Term Quality	Natural terms users would say are present ('terminal UI', 'components', 'dialogs/selectors', 'slash commands', 'themes', 'streaming render'), but common synonyms like 'TUI' and looser phrasings of the domain are missing, so keyword coverage is good rather than comprehensive — fits anchor 4, not 5.	4 / 5
Distinctiveness Conflict Risk	Pinned to a specific repo path (apps/kimi-code/src/tui) and named coordinator (KimiTUI); a clear niche with distinct triggers and minimal conflict risk with any other skill. Matches the 5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: MoonshotAI/kimi-code
Path: .agents/skills/write-tui/SKILL.md
Commit: 21406fb

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.