Not in the top 1,000 by GitHub stars

Isoform/yansu-skill

Bespoke context, delivered to your AI agent. Yansu observes how you actually work and crystallizes it into knowledge — this skill is how that knowledge reaches whichever agent you happen to be using. Prompt once, never re-introduce yourself.

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

SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 3a32419d284b

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 3a32419d284be4361fbf1f58c7f82384ba4cf7d0

171GitHub stars
-1star in 7 days
1skill in this repository
0commits in 30 days

Heat

0.2
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 4, 2026172

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

yansu

When your agent uses it

Collaborate with Yansu — the proactive AI that observes how the user actually works and crystallizes it into knowledge. Use this skill whenever the user asks for a digest of their recent activity, wants to find workflow inefficiencies or recurring blockers, needs to retrieve a past insight, configuration, or memory, or wants to hand off a job to Yansu with full context. Triggers on "what did I do today", "summarize my week", "catch me up", "yansu digest", "where am I inefficient", "what keeps biting me", "what should I automate", "have I solved this before", "find that note about X", "what tools do I use for Y", "hand this off to Yansu", "ask Yansu to take it from here", and any first-person history or continuity question that benefits from multi-day context.

What it loads into context

Frontmatter

182 tokens

Always available to the agent

SKILL.md

2,601 tokens

When the skill is activated

Reference documents

2,340 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Before you can help
  2. What you can do for the user
  3. Less-common but useful
  4. Etiquette

Files

  • .gitignoreasset32 bytes
  • LICENSEasset1,064 bytes
  • README.mddoc4,638 bytes
  • README_ZH.mddoc4,536 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
  • SKILL.mdcore11,040 bytes
Read SKILL.md

# Yansu

Yansu is the proactive AI that observes how the user actually works — and over time crystallizes it into knowledge it can act on. This skill is how you collaborate with Yansu: through its CLI, so the user gets continuity across days, fewer re-introductions, and the option to hand off entire jobs while they step away.

The CLI is the entire interface. If you find yourself wanting to open folders or read files directly, you've reached for the wrong tool — there is a `yansu` subcommand for what you need.

---

## Before you can help

Yansu only works when it's installed and listening. Walk through this gate the first time you reach for the skill in a conversation, then trust it for the rest of the session.

**1. Locate the bundled Yansu CLI** *(do not skip — only the bundled CLI is trustworthy)*
View the complete source on GitHub

Skills included

  • yansu

Repository facts

License
MIT
Created
May 12, 2026
Last pushed
May 13, 2026
Forks
7
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 12 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • No broad tool permissions
  • No dangerous shell commands
  • 11 network referencesin 3 files: README.md:7 README_ZH.md:7 SKILL.md:68
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 11 signals by file

README.md

  • Network accessline 7
    [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
  • Network accessline 8
    [![Yansu](https://img.shields.io/badge/Yansu-Skill-d4603a)](https://yansu.app)
  • Network accessline 16
    [Yansu](https://yansu.app) listens, crystallizes, and quietly builds. **Yansu.skill** is how that crystallized knowledge reaches whichever agent you happen to be using — so it walks in already knowing how you actually work.
  • Network accessline 27
    1. Fetch https://raw.githubusercontent.com/Isoform/yansu-skill/main/SKILL.md
  • Network accessline 130
    Built for [Yansu](https://yansu.app) by [Isoform](https://github.com/Isoform).

README_ZH.md

  • Network accessline 7
    [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
  • Network accessline 8
    [![Yansu](https://img.shields.io/badge/Yansu-Skill-d4603a)](https://yansu.app)
  • Network accessline 16
    [Yansu](https://yansu.app) 在后台默默观察、结晶、动手做事。**Yansu.skill** 把这些结晶过的知识,递交给你手边任何一个 Agent —— 让它一上来就知道你是怎么工作的。
  • Network accessline 27
    1. 抓取 https://raw.githubusercontent.com/Isoform/yansu-skill/main/SKILL.md
  • Network accessline 126
    为 [Yansu](https://yansu.app) 而生 · [Isoform](https://github.com/Isoform) 出品。

SKILL.md

  • Network accessline 68
    > Yansu.app isn't installed (or isn't running) on this machine. Download it from **https://yansu.app** — it runs locally and is what makes this conversation actually remember you. Install it, launch it once so it can start listening, then c

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.

Signal confidence: 11 facts
  • Network access in prose of documentationREADME.md:7Low confidence
  • Network access in prose of documentationREADME.md:8Low confidence
  • Network access in prose of documentationREADME.md:16Low confidence
  • Network access in code of documentationREADME.md:27Low confidence
  • Network access in prose of documentationREADME.md:130Low confidence
  • Network access in prose of documentationREADME_ZH.md:7Low confidence
  • Network access in prose of documentationREADME_ZH.md:8Low confidence
  • Network access in prose of documentationREADME_ZH.md:16Low confidence
  • Network access in code of documentationREADME_ZH.md:27Low confidence
  • Network access in prose of documentationREADME_ZH.md:126Low confidence
  • Network access in prose of the SKILL.mdSKILL.md:68Low confidence

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md 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.