Best for
- Use when generating changesets in the kimi-code repository, including package bump selection, internal package and CLI bundle handling, bump levels, major confirmation, and English changelog wording.
MoonshotAI/kimi-code/.agents/skills/gen-changesets/SKILL.md
Use when generating changesets in the kimi-code repository, including package bump selection, internal package and CLI bundle handling, bump levels, major confirmation, and English changelog wording.
Decision brief
kimi-code uses changesets to manage versions and changelogs. The current user-facing published package is:
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/MoonshotAI/kimi-code --skill ".agents/skills/gen-changesets"Inspect the Agent Skill "gen-changesets" from https://github.com/MoonshotAI/kimi-code/blob/013203421df03b655cc04d1095e4e41d83c2ae44/.agents/skills/gen-changesets/SKILL.md at commit 013203421df03b655cc04d1095e4e41d83c2ae44. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
1. List the changed packages and check whether each one is ignored by .changeset/config.json. 2. Decide whether the change is user-perceivable (Core Rule 6); if not, stop — no changeset. 3. Choose a bump level for each package. 4. If an ignored internal package change enters the…
1. Inspect the actual changes first. Use git status / git diff --name-only to identify which packages were actually changed. 2. List packages that changesets can release. If a changed package is ignored in .changeset/config.json, do not put that ignored package in frontmatter to…
When in doubt between patch and minor: if the change improves an existing feature and the user-facing impact is small, choose patch even when the change is technically "new". Reserve minor for a substantial new capability that introduces something users could not do before.
Never write major on your own.
Changelog entries must be written in English.
Permission review
The documentation asks the agent to create, modify, or delete local files.
Create a short kebab-case file under `.changeset/`.Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 87/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 6,096 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
kimi-code uses changesets to manage versions and changelogs. The current user-facing published package is:
@moonshot-ai/kimi-code: the CLIAll other @moonshot-ai/* packages are treated as internal packages, including @moonshot-ai/kimi-code-sdk, agent-core, kosong, kaos, kimi-code-oauth, kimi-telemetry, and migration-legacy.
@moonshot-ai/pi-tui is a special internal package: it is a private fork (private: true) that is never published, but it keeps its own changelog through changesets. It is an exception to Core Rule 4 — see the dedicated section below.
git status / git diff --name-only to identify which packages were actually changed..changeset/config.json, do not put that ignored package in frontmatter together with a non-ignored package; changesets rejects mixed ignored/non-ignored frontmatter.@moonshot-ai/kimi-code and describe the actual user-visible or release-artifact change in the changelog text.@moonshot-ai/kimi-code inline-bundles @moonshot-ai/* source, but those internal packages are devDependencies from the CLI's perspective, so changesets will not automatically propagate bumps. If a change enters the CLI output and is user-perceivable, list @moonshot-ai/kimi-code. See rule 6 for when to skip the changeset entirely.test/ changes that do not enter package output do not trigger a CLI bump.main still ship in the next release triggered by any user-facing changeset, so skipping the changeset loses nothing. Do not write changesets for:
agent-core-v2 internal architecture: new services, refactors, config-persistence or journal/wire mechanisms.kap-server WebSocket / REST protocol changes consumed only by the bundled web UI, kimi-inspect, or other dev tooling (new endpoints, subscribe protocols, stream baselines).kimi -p), unless it exposes documented user configuration such as a config.toml section or env vars that also work on a shipped surface (TUI or kimi web).@moonshot-ai/vis / vis-server / vis-web are ignored by changesets and should not be handled. @moonshot-ai/kimi-inspect (a private dev app that never ships) is likewise ignored and must never appear in a changeset frontmatter..changeset/config.json.@moonshot-ai/kimi-code in frontmatter instead of mixing the ignored package into the same changeset..changeset/.Before a release, review the accumulated .changeset/ entries against Core Rule 6 and prune non-user-facing ones; the release PR regenerates from .changeset/ on main, so deleting a changeset removes its changelog entry without affecting the shipped code.
Format:
---
"<package A>": patch
"<package B>": minor
---
<English changelog entry>
| Level | When to use |
|---|---|
patch | Bug fixes; build/package fixes; internal refactors that do not change behavior; wording tweaks; small dependency upgrades; small improvements to existing features with limited user-facing impact (e.g. a new keyboard shortcut, a flag alias, a minor UX tweak) |
minor | A substantial new user-facing feature, such as a new slash command, a new built-in tool, or a new mode |
major | Breaking changes: incompatible config changes, renamed or removed commands/arguments, behavior semantics changes, and similar |
When in doubt between patch and minor: if the change improves an existing feature and the user-facing impact is small, choose patch even when the change is technically "new". Reserve minor for a substantial new capability that introduces something users could not do before.
New configuration surface is not automatically minor. Additions to an existing feature's configuration — env var overlays, config-file fallbacks, global defaults under per-item settings — are patch. Examples: a global default MCP timeout when per-server timeouts already exist; env-based credentials for a service already configurable in config.toml.
Never write major on your own.
If you believe a change qualifies as major, stop first, explain why, and ask the user for confirmation. Only write major after the user explicitly agrees. If the user does not reply, replies ambiguously, or disagrees, fall back to minor; if minor is also unclear, fall back to patch.
Add the /foo slash command to list active sessions. Run /foo to see them.Add the kimi web subcommand to open the web UI. Run kimi web to launch it.Add a --bar flag to skip confirmation prompts. Pass --bar to skip.Add the /foo command to list active sessions. It accepts an optional --all flag to include background sessions, supports filtering by name with /foo <name>, and writes the result to the transcript...example.com, example.test, or YOUR_API_KEY.refactor, optimize, and improve. Describe the actual change, or use more specific wording.Generate the changeset from what the diff clearly shows. If part of a change is unclear and you cannot confidently describe what it does for users, do not guess or pad the entry with vague wording.
An internal package fixes a bug visible to CLI users:
---
"@moonshot-ai/kimi-code": patch
---
Fix occasional loss of tool call results in long conversations.
A new user-facing slash command (note the short usage hint):
---
"@moonshot-ai/kimi-code": minor
---
Add the /foo slash command to list active sessions. Run /foo to see them.
A new CLI subcommand:
---
"@moonshot-ai/kimi-code": minor
---
Add the kimi web subcommand to open the web UI. Run kimi web to launch it.
A new flag on an existing command:
---
"@moonshot-ai/kimi-code": patch
---
Add a --bar flag to skip confirmation prompts. Pass --bar to skip.
An internal package has an internal-only change, but it enters the CLI bundle:
---
"@moonshot-ai/kimi-code": patch
---
Unify tool execution metadata handling.
Only SDK source changed, and the CLI does not use it:
---
"@moonshot-ai/kimi-code-sdk": patch
---
Clarify session status typing for internal SDK callers.
@moonshot-ai/pi-tui changes@moonshot-ai/pi-tui is a vendored fork that lives in packages/pi-tui. It is private: true and is never published, but it is not ignored by changesets: changesets versions it and writes packages/pi-tui/CHANGELOG.md so the fork keeps its own history. Because it is bundled into the CLI like other internal packages, it is an exception to Core Rule 4 — do not list @moonshot-ai/kimi-code for a change that only touches pi-tui.
@moonshot-ai/pi-tui only. No CLI changeset.@moonshot-ai/kimi-code with CLI-focused wording, in addition to the pi-tui changeset. Do not mix both packages in one frontmatter — the two changelogs need different wording.pi-tui-only change:
---
"@moonshot-ai/pi-tui": patch
---
Export the package manifest so the bundled binary can locate its native assets.
pi-tui change that is also visible in the CLI (two separate changesets):
---
"@moonshot-ai/pi-tui": patch
---
Clamp the differential render to the visible viewport so scrolling up during streaming no longer jumps to the top.
---
"@moonshot-ai/kimi-code": patch
---
Fix the transcript jumping to the top when scrolling up through history during streaming output.
major without asking the user.agent-core-v2 internals, kap-server WS/REST protocol plumbing, experimental-engine-only behavior. Skip the changeset instead (Core Rule 6).minor — configuration additions to existing features are patch.@moonshot-ai/kimi-code is missing.packages/node-sdk was not changed, but @moonshot-ai/kimi-code-sdk was listed for "internal package sync".@moonshot-ai/pi-tui lists @moonshot-ai/kimi-code instead of @moonshot-ai/pi-tui, or mixes both packages in one frontmatter.Alternatives
alirezarezvani/claude-skills
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist
dotnet/skills
Migrates .NET test projects from VSTest to Microsoft.Testing.Platform (MTP). Use when user asks to "migrate to MTP", "switch from VSTest", "enable Microsoft.Testing.Platform", "use MTP runner", set OutputType=Exe only for test projects in Directory.Build.props, or mentions EnableMSTestRunner, EnableNUnitRunner, or UseMicrosoftTestingPlatformRunner. USE FOR: MTP behavioral differences vs VSTest (exit code 8, zero tests discovered, --ignore-exit-code, TESTINGPLATFORM_EXITCODE_IGNORE); centralizing
wyre-technology/msp-claude-plugins
Autotask ticket lifecycle: status/priority codes and transition rules, the ticket field schema, SLA calculation and clock behavior, escalation rules, ticket metrics, and the MCP tool surface (create, update, search, history, notes) for MSP service desk operations.
HKUDS/Vibe-Trading
Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.