feat: add skill discovery commands

[Coiggahou2002]

Related Issue

Resolve #60

Problem

Skills can currently be invoked through generated slash commands, but users have no supported way to inspect which Skill files were loaded, where they came from, what command name is effective, or why a Skill was skipped. This makes discovery and troubleshooting difficult in both the TUI and automation.

What changed

• add a searchable, read-only /skills picker that displays the effective command, name, source, type, description, and path; selection inserts the command without executing it;
• add kimi skills list and kimi skills list --json for session-less workspace inspection, including support for the global --skills-dir override;
• add backward-compatible SDK/core inspection methods while preserving the existing listSkills and listWorkspaceSkills APIs;
• expose structured diagnostics for invalid, unsupported, unreadable, and unexpectedly failing Skill files in both v1 and v2 discovery;
• document the TUI and shell commands in English and Chinese;
• add a patch changeset for the CLI and SDK packages.

Verification:

• 95 focused Vitest tests across agent-core, agent-core-v2, node-sdk, CLI, and TUI;
• typecheck for all four affected packages;
• full repository lint: 0 errors (existing warnings remain);
• Kimi Code production build;
• agent-core-v2 import-boundary check;
• bilingual VitePress documentation build;
• real CLI JSON invocation with an explicit --skills-dir.

Checklist

• I have read the CONTRIBUTING document.
• I have linked a related issue, or explained the problem above.
• I have added tests that prove my feature works.
• Ran gen-changesets skill, or this PR needs no changeset.
• Ran gen-docs skill, or this PR needs no doc update.

[changeset-bot]

🦋 Changeset detected

Latest commit: 1dd712f

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 2 packages

Name	Type
@moonshot-ai/kimi-code	Patch
@moonshot-ai/kimi-code-sdk	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 1dd712f670

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Refresh skill commands before inserting from /skills

When the skill catalog changes after the last startup/session switch/reload (for example a new .kimi-code/skills/*/SKILL.md is added while the TUI is open), this picker reads the fresh inspectSkills() report but never updates host.skillCommandMap. Selecting that newly discovered skill inserts /skill:name, yet dispatchInput resolves skills only through the stale map, so pressing Enter sends the slash command as a normal model message instead of activating the skill. Refresh the host skill commands from this report/session before inserting, or activate through a path that does not depend on the cached map.

Useful? React with 👍 / 👎.

[liruifengv]

Thank you for your interest in contributing to Kimi Code.

For new features, please discuss first. We are not currently accepting pull requests for new features.