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

96%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, actionable architecture/routing reference that is concise and assumes competence, with a validated submission checklist. Its one weak point is progressive disclosure: the repeatedly-referenced DESIGN.md is missing from the skill bundle.

Suggestions

Ship DESIGN.md alongside SKILL.md (or move it under references/) so the './DESIGN.md' links resolve; a missing primary reference breaks the navigation the skill relies on.

If DESIGN.md lives elsewhere in the repo rather than the bundle, update the reference text and path so the link is correct from the skill's location.

Consider an explicit 'if lint/tests fail, fix and re-run' feedback loop in the Before-you-submit checklist to strengthen the validation feedback loop.

Dimension	Reasoning	Score
Conciseness	Dense, codebase-specific routing guidance that assumes Claude's competence — it does not explain basic concepts (what a TUI or chalk is) and defers hard constraints to AGENTS.md, so nearly every token earns its place.	3 / 3
Actionability	As an instruction/routing skill it gives concrete, specific guidance — e.g. 'CLI arguments → src/cli/commands.ts / src/cli/options.ts' and exact file destinations per feature type — which is copy-paste-ready and actionable without code samples.	3 / 3
Workflow Clarity	The 'Before you submit' section provides an explicit submission checklist with validation checkpoints (run lint/format/test, walk the DESIGN.md self-check list, keep CI-guarded printableChar()/chalk.hex usage).	3 / 3
Progressive Disclosure	References are well-signaled and one-level-deep ('see [DESIGN.md](./DESIGN.md) in this folder', AGENTS.md for hard constraints), but DESIGN.md is absent from the bundle (references/scripts/assets are empty and no DESIGN.md exists), so the primary navigation link is broken — capping this below 3.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 tight, well-scoped description that names concrete capabilities, includes an explicit 'Use when' trigger with natural terms, and is pinned to a specific codebase path. It clearly satisfies what-and-when with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability areas — 'components, dialogs/selectors, slash commands, themes, streaming render, or the KimiTUI controllers' — plus covered topics (architecture, feature routing, test placement, theme mechanics, dialog spec), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both: what ('Covers the architecture, where new features go, test placement...') and when ('Use when writing or modifying the kimi-code terminal UI in apps/kimi-code/src/tui'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Natural developer-facing terms a user would actually say — 'terminal UI', 'dialogs/selectors', 'slash commands', 'themes', 'streaming render' — giving good coverage of the vocabulary tied to this codebase.	3 / 3
Distinctiveness Conflict Risk	Scoped to a single concrete path (apps/kimi-code/src/tui) and product (kimi-code TUI) with niche-specific triggers, making conflict with other skills very unlikely.	3 / 3
	Total	12 / 12 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: 77618e3

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.