#378 by GitHub stars
nano-muse/nanoMuse
nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
nanomuse/skills/builtin/amap/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/compare-options/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/feishu/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/inbox-triage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/kuaidi100/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/meeting-prep/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/phone-messages/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/skill-creator/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8b32d43c946d
No earlier version was observed for comparison.
nanomuse/skills/builtin/tencent-meeting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/train-tickets/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/trip-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
nanomuse/skills/builtin/weekly-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14fc6aeda015 → 8b32d43c946d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14fc6aeda015
No earlier version was observed for comparison.
Verified commit 8b32d43c946db2bbef6fae39c48a9fc608ebd8e9
git clone --filter=blob:none --no-checkout https://github.com/nano-muse/nanoMuse.git .hotskills/nano-muse-nanomuse && git -C .hotskills/nano-muse-nanomuse checkout --detach 8b32d43c946db2bbef6fae39c48a9fc608ebd8e9
# Copy each selected skill directory from .hotskills/nano-muse-nanomuse into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/nano-muse/nanoMuse.git .hotskills/nano-muse-nanomuse && git -C .hotskills/nano-muse-nanomuse checkout --detach 8b32d43c946db2bbef6fae39c48a9fc608ebd8e9
# Copy each selected skill directory from .hotskills/nano-muse-nanomuse into .agents/skills/<skill-name>/Heat
8.6- Star growth, last 7 daysAhead of 98% of tracked repositories
- Star growth, last 24 hoursAhead of 98% of tracked repositories
- Rank movement, last 7 daysAhead of 96% of tracked repositories
- Commits, last 30 daysAhead of 100% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- amap
nanomuse/skills/builtin/amap - compare-options
nanomuse/skills/builtin/compare-options - feishu
nanomuse/skills/builtin/feishu - inbox-triage
nanomuse/skills/builtin/inbox-triage - kuaidi100
nanomuse/skills/builtin/kuaidi100 - meeting-prep
nanomuse/skills/builtin/meeting-prep - phone-messages
nanomuse/skills/builtin/phone-messages - skill-creator
nanomuse/skills/builtin/skill-creator - tencent-meeting
nanomuse/skills/builtin/tencent-meeting - train-tickets
nanomuse/skills/builtin/train-tickets - trip-plan
nanomuse/skills/builtin/trip-plan - weekly-review
nanomuse/skills/builtin/weekly-review
How it works
amap
When your agent uses it
Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server. Use when the user asks how far, how long, how to get somewhere (car, transit, bike, foot), what is near a place, or about the weather in a Chinese city.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,033 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Is it there?
- The tools
- How to answer
- With the other hands
- Finish
Files
SKILL.mdcore3,949 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcompare-options
When your agent uses it
Compare two to five options (products, plans, places, tools, offers) on the criteria that matter to the user, in a table the user can re-weight, with a recommendation. Use when the user asks which to pick, for a comparison, or "X vs Y".
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
560 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pin down the question
- Research
- The page
- Finish
Files
SKILL.mdcore2,356 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfeishu
When your agent uses it
The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open. Use when the user mentions 飞书, Lark, a 群, a 日程 or a 飞书文档, or wants a colleague told something.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,273 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Is it there?
- Reading
- Writing
- With the other hands
- Finish
Files
SKILL.mdcore4,652 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubinbox-triage
When your agent uses it
Go through recent mail and sort it into needs-a-reply, waiting-on-others, to-do and can-ignore, with draft replies ready for review. Use when the user asks to triage, sort, catch up on or clear their inbox; never to send anything on its own.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
601 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Read
- Sort
- Draft, do not send
- Report
Files
SKILL.mdcore2,388 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubkuaidi100
When your agent uses it
Where a parcel is, when it will arrive and what a shipment would cost, through the 快递100 MCP server: any Chinese courier (顺丰, 京东, 中通, 圆通, 韵达, 邮政 and more) from a tracking number. Use when the user asks 快递到哪了, 什么时候到, 查一下单号, or how much it costs to send something.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
1,175 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Is it there?
- The tools
- How to answer
- With the other hands
- Finish
Files
SKILL.mdcore4,553 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmeeting-prep
When your agent uses it
Prepare for a meeting (who is in it, what was last said with them, what the user owes them and wants from them) as a one-page brief. Use when the user asks to prepare for or get ready for a meeting, a call or a visit; a trigger can run it before every meeting with a client.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
651 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Find the meeting
- The people
- The matter
- The brief (Markdown)
- Finish
Files
SKILL.mdcore2,634 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubphone-messages
When your agent uses it
Read and answer messages in the chat apps on the user's phone (微信 and the like) through the screen: catch up, draft a reply in the user's voice, send only text they confirmed. Use when the user asks what someone said on WeChat or wants a chat answered.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
625 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Reading
- Answering
- Do not
- Finish
Files
SKILL.mdcore2,609 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubskill-creator
When your agent uses it
Use when creating or updating a reusable skill with task-specific instructions, supporting files and checks.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
507 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Choose the scope
- Write the skill
- Check the result
Files
SKILL.mdcore2,573 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtencent-meeting
When your agent uses it
The user's 腾讯会议 via the official tmeet CLI: upcoming meetings, creating, changing or cancelling one, inviting people, then the recording, minutes, transcript and attendance. Use when the user mentions 腾讯会议, a 会议号, a 会议链接, 纪要 or 录制, or wants a meeting set up or looked up.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
1,237 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Is it there?
- Reading
- Writing
- With the other hands
- Finish
Files
SKILL.mdcore5,009 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtrain-tickets
When your agent uses it
Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment. Use when the user asks about 火车票 / 高铁 / 12306 or a train between two cities.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,582 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Is the server there?
- What you need
- Searching
- Booking
- Searching on the screen (fallback)
- With the other hands
- Finish
Files
SKILL.mdcore5,940 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtrip-plan
When your agent uses it
Plan a trip end to end (itinerary by day, a packing list to tick off, a budget, and the calendar checked for conflicts) as pages in the workspace. Use when the user is going somewhere for more than a day and wants a plan, an itinerary or a packing list.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
844 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before anything
- Research
- Itinerary (`itinerary.html`)
- Packing list (`packing.html`)
- Budget (`budget.csv`, when asked or when the user mentioned money)
- Finish
Files
SKILL.mdcore3,543 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubweekly-review
When your agent uses it
Look back at the past week and set up the next one: calendar, mail, goals and files in one page, with a short plan. Use when the user asks for a weekly review, a week in review, "how did my week go" or to plan next week.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
584 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Gather (all read-only)
- Write
- Finish
Files
SKILL.mdcore2,345 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- amap
- compare-options
- feishu
- inbox-triage
- kuaidi100
- meeting-prep
- phone-messages
- skill-creator
- tencent-meeting
- train-tickets
- trip-plan
- weekly-review
Repository facts
- License
- GPL-3.0
- Created
- Sep 23, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 388
- Open issues
- 137
- Project activity
- Active
Rank over the last 12 weeks
Now #378 · best #378 · up 605 in 30 days
- #395 on Nov 2
- #389 on Nov 3
- #385 on Nov 4
- #381 on Nov 5
- #379 on Nov 6
- #378 since Nov 7
39 earlier periods
- #922 on Sep 20
- #946 on Sep 23
- #911 on Sep 24
- #859 on Sep 25
- #882 on Sep 26
- #901 on Sep 27
- #947 on Sep 28
- #975 on Sep 29
- #939 on Sep 30
- #876 on Oct 1
- #893 on Oct 2
- #866 on Oct 3
- #908 on Oct 4
- #929 on Oct 5
- #916 on Oct 6
- #951 on Oct 7
- #983 on Oct 8
- #921 on Oct 9
- #786 on Oct 10
- #737 on Oct 11
- #707 on Oct 12
- #661 on Oct 13
- #639 on Oct 14
- #613 on Oct 15
- #597 on Oct 16
- #569 on Oct 17
- #551 on Oct 18
- #560 on Oct 19
- #505 on Oct 20
- #464 on Oct 21
- #448 on Oct 22
- #437 on Oct 23
- #419 on Oct 24
- #438 on Oct 25
- #416 on Oct 28
- #409 on Oct 29
- #407 on Oct 30
- #405 on Oct 31
- #401 on Nov 1
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
- No broad tool permissions
- No dangerous shell commands
- 8 network referencesin 4 files: amap/SKILL.md:19 kuaidi100/SKILL.md:19 tencent-meeting/SKILL.md:12 and 1 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 2 references to secretsin 2 files: amap/SKILL.md:25 kuaidi100/SKILL.md:27
- No requests to vote in Hot
Show all 10 signals by file
nanomuse/skills/builtin/amap/SKILL.md
- Network accessline 19
[[mcp.servers]] name = "amap" url = "https://mcp.amap.com/mcp?key={{vault:AMAP_KEY}}" # a free Web 服务 key from console.amap.com - Network accessline 20
name = "amap" url = "https://mcp.amap.com/mcp?key={{vault:AMAP_KEY}}" # a free Web 服务 key from console.amap.com risk = "safe" - Network accessline 21
url = "https://mcp.amap.com/mcp?key={{vault:AMAP_KEY}}" # a free Web 服务 key from console.amap.com - Access to secretsline 25
[Credential-related source omitted]
nanomuse/skills/builtin/kuaidi100/SKILL.md
- Network accessline 19
[[mcp.servers]] name = "kuaidi100" url = "https://api.kuaidi100.com/mcp/streamable?key={{vault:KUAIDI100_KEY}}" # the 授权 key from api.kuaidi100.com 企业管理后台 - Network accessline 20
name = "kuaidi100" url = "https://api.kuaidi100.com/mcp/streamable?key={{vault:KUAIDI100_KEY}}" # the 授权 key from api.kuaidi100.com 企业管理后台 risk = "safe" - Network accessline 21
url = "https://api.kuaidi100.com/mcp/streamable?key={{vault:KUAIDI100_KEY}}" # the 授权 key from api.kuaidi100.com 企业管理后台 - Access to secretsline 27
[Credential-related source omitted]
nanomuse/skills/builtin/tencent-meeting/SKILL.md
- Network accessline 12
腾讯会议 has an open platform, and [`tmeet`](https://github.com/TencentCloud/tencentmeeting-cli), Tencent's own CLI installed with `npm i -g @tencentcloud/tmeet`, wraps it. This is done with `shell`, not on the phone's screen. Every command pri
nanomuse/skills/builtin/train-tickets/SKILL.md
- Network accessline 12
Two hands, in this order. **Searching** is done with the `12306__*` tools, a community MCP server ([12306-mcp](https://github.com/Joooook/12306-mcp)) that reads 12306's public timetable and seat counts; no login, no browser, no phone, nothi
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 10 facts
- Network access in code of the SKILL.mdamap/SKILL.md:19High confidence
- Network access in code of the SKILL.mdamap/SKILL.md:20High confidence
- Network access in code of the SKILL.mdamap/SKILL.md:21High confidence
- Access to secrets in prose of the SKILL.mdamap/SKILL.md:25Low confidence
- Network access in code of the SKILL.mdkuaidi100/SKILL.md:19High confidence
- Network access in code of the SKILL.mdkuaidi100/SKILL.md:20High confidence
- Network access in code of the SKILL.mdkuaidi100/SKILL.md:21High confidence
- Access to secrets in prose of the SKILL.mdkuaidi100/SKILL.md:27Low confidence
- Network access in prose of the SKILL.mdtencent-meeting/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdtrain-tickets/SKILL.md:12Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path CLAUDE.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md nanomuse/skills/builtin/amap/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md nanomuse/skills/builtin/amap/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md nanomuse/skills/builtin/amap/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md nanomuse/skills/builtin/amap/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/nano-muse-nanomuse/)