knots — for Claude Code community, for Claude Code, ide skills, bash kno claim <id>, kno -C <path_to_repo>, bash kno rollback <id>, rollback, Create, description, action-oriented

v1.0.0

このスキルについて

適した場面: Ideal for AI agents that need kno new "<title " -d "<description ". ローカライズされた概要: Workflow definition language and compiler # Knots Create a knot Run: Use a short action-oriented title. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

機能

kno new "<title " -d "<description "
Use a short action-oriented title. Write the description with the expected
outcome, relevant context, and constraints for the next agent.
Follow this sequence:
If you are working inside a git worktree, run Knots commands as

# Core Topics

acartine acartine
[4]
[0]
Updated: 4/17/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
49
Canonical Locale
en
Detected Body Locale
en

適した場面: Ideal for AI agents that need kno new "<title " -d "<description ". ローカライズされた概要: Workflow definition language and compiler # Knots Create a knot Run: Use a short action-oriented title. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

このスキルを使用する理由

推奨ポイント: knots helps agents kno new "<title " -d "<description ". Workflow definition language and compiler # Knots Create a knot Run: Use a short action-oriented title. This AI agent skill supports Claude Code, Cursor

おすすめ

適した場面: Ideal for AI agents that need kno new "<title " -d "<description ".

実現可能なユースケース for knots

ユースケース: Applying kno new "<title " -d "<description "
ユースケース: Applying Use a short action-oriented title. Write the description with the expected
ユースケース: Applying outcome, relevant context, and constraints for the next agent

! セキュリティと制限

  • 制約事項: Do not invent alternate transition workflows. Prefer claim, next, and
  • 制約事項: Do not invent alternate transition workflows
  • 制約事項: Requires repository-specific context from the skill documentation

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is knots?

適した場面: Ideal for AI agents that need kno new "<title " -d "<description ". ローカライズされた概要: Workflow definition language and compiler # Knots Create a knot Run: Use a short action-oriented title. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

How do I install knots?

Run the command: npx killer-skills add acartine/loom/knots. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for knots?

Key use cases include: ユースケース: Applying kno new "<title " -d "<description ", ユースケース: Applying Use a short action-oriented title. Write the description with the expected, ユースケース: Applying outcome, relevant context, and constraints for the next agent.

Which IDEs are compatible with knots?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for knots?

制約事項: Do not invent alternate transition workflows. Prefer claim, next, and. 制約事項: Do not invent alternate transition workflows. 制約事項: Requires repository-specific context from the skill documentation.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add acartine/loom/knots. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use knots immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

knots

Workflow definition language and compiler # Knots Create a knot Run: Use a short action-oriented title. This AI agent skill supports Claude Code, Cursor, and

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Knots

Create a knot

Run:

bash
1kno new "<title>" -d "<description>"

Use a short action-oriented title. Write the description with the expected outcome, relevant context, and constraints for the next agent.

Execute a knot

Follow this sequence:

bash
1kno claim <id>
  • If you are working inside a git worktree, run Knots commands as kno -C <path_to_repo> ... because Knots is installed for the repo root, not the worktree path.
  • Record the current state from the claim output.
  • Use the claim output to determine the current state's completion goals.
  • Do the work and validate it.
  • If the goals were met, advance with a guarded state check:
bash
1kno next <id> --expected-state <current_state>
  • If you are blocked, validation fails, or the state's goals were not met, roll back safely:
bash
1kno rollback <id>

If the claimed knot lists children, handle the children first:

  • Claim each child knot and follow that child prompt to completion.
  • When the child knots are handled, evaluate the outcomes.
  • If every child advanced, advance the parent.
  • If any child rolled back, roll the parent back too.

Do not invent alternate transition workflows. Prefer claim, next, and rollback over manual state mutation unless the user explicitly asks for it.

Session close behavior

  • In an interactive session, briefly say what changed and ask what to do next.
  • In a non-interactive session, stop cleanly after the knot workflow is complete.

関連スキル

Looking for an alternative to knots or another community skill for your workflow? Explore these related open-source skills.

すべて表示

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

カスタマイズ可能なウィジェットプラグインをprompts.chatのフィードシステム用に生成する

149.6k
0
AI

flags

Logo of vercel
vercel

React フレームワーク

138.4k
0
ブラウザ

pr-review

Logo of pytorch
pytorch

Pythonにおけるテンソルと動的ニューラルネットワーク(強力なGPUアクセラレーション)

98.6k
0
開発者