ct — for Claude Code community, for Claude Code, ide skills, binary, CommonTools, current, commands, operations, checking, Environment

v1.0.0

Über diesen Skill

Perfekt für Deno-Aufgabenverwaltungsagenten, die eine erweiterte CommonTools-Integration und Typprüfungsfunktionen benötigen. Lokalisierte Zusammenfassung: Guide for using the ct (CommonTools) binary to interact with pieces, # CT CLI The ct binary is the CLI for CommonTools. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Funktionen

The ct binary is the CLI for CommonTools. Use --help for current commands:
deno task ct --help # Top-level commands
deno task ct piece --help # Piece operations
deno task ct check --help # Type checking
Identity key (required for most operations):

# Core Topics

commontoolsinc commontoolsinc
[0]
[0]
Updated: 3/9/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

This page remains useful for teams, 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 Quality floor passed for review
Review Score
10/11
Quality Score
60
Canonical Locale
en
Detected Body Locale
en

Perfekt für Deno-Aufgabenverwaltungsagenten, die eine erweiterte CommonTools-Integration und Typprüfungsfunktionen benötigen. Lokalisierte Zusammenfassung: Guide for using the ct (CommonTools) binary to interact with pieces, # CT CLI The ct binary is the CLI for CommonTools. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Warum diese Fähigkeit verwenden

Ermöglicht es Agenten, mit Teilen über das ct-Binär zu interagieren, indem Typprüfung und Teileoperationen durch Befehle wie `deno task ct piece` und `deno task ct check` bereitgestellt werden, wodurch die Deno-Aufgabenverwaltung und CommonTools genutzt werden.

Am besten geeignet für

Perfekt für Deno-Aufgabenverwaltungsagenten, die eine erweiterte CommonTools-Integration und Typprüfungsfunktionen benötigen.

Handlungsfähige Anwendungsfälle for ct

Ableiten von Identitätsschlüsseln für lokale Entwicklung
Durchführen von Typprüfungen auf Teilen mit `deno task ct check`
Verwalten von Teilen mit `deno task ct piece`-Operationen

! Sicherheit & Einschränkungen

  • Benötigt einen Identitätsschlüssel für die meisten Operationen
  • Spezifisch für CommonTools und Deno-Aufgabenverwaltung
  • Benötigt `claude.key` für die implizite Vertrauensidentität

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

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 ct?

Perfekt für Deno-Aufgabenverwaltungsagenten, die eine erweiterte CommonTools-Integration und Typprüfungsfunktionen benötigen. Lokalisierte Zusammenfassung: Guide for using the ct (CommonTools) binary to interact with pieces, # CT CLI The ct binary is the CLI for CommonTools. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

How do I install ct?

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

What are the use cases for ct?

Key use cases include: Ableiten von Identitätsschlüsseln für lokale Entwicklung, Durchführen von Typprüfungen auf Teilen mit `deno task ct check`, Verwalten von Teilen mit `deno task ct piece`-Operationen.

Which IDEs are compatible with ct?

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 ct?

Benötigt einen Identitätsschlüssel für die meisten Operationen. Spezifisch für CommonTools und Deno-Aufgabenverwaltung. Benötigt `claude.key` für die implizite Vertrauensidentität.

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 commontoolsinc/labs. 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 ct 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

ct

Install ct, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

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

CT CLI

The ct binary is the CLI for CommonTools. Use --help for current commands:

bash
1deno task ct --help # Top-level commands 2deno task ct piece --help # Piece operations 3deno task ct check --help # Type checking

Environment Setup

Identity key (required for most operations):

bash
1ls -la claude.key # Check for existing 2 3# For local dev: derive key matching toolshed's "implicit trust" identity 4deno run -A packages/cli/mod.ts id derive "implicit trust" > claude.key 5 6# For a fresh random key (e.g., against production): 7deno run -A packages/cli/mod.ts id new > claude.key

IMPORTANT: Do NOT use deno task ct id new > file — the deno task wrapper prints ANSI-colored preamble to stdout, which pollutes the key file. Always use deno run -A packages/cli/mod.ts when redirecting output.

Environment variables (avoid repeating flags):

bash
1export CT_API_URL=http://localhost:8000 # or https://toolshed.saga-castor.ts.net/ 2export CT_IDENTITY=./claude.key

Experimental flags (must be set on both servers AND CLI commands):

bash
1# Pass experiment env vars to CLI commands: 2EXPERIMENTAL_CANONICAL_HASHING=true \ 3EXPERIMENTAL_RICH_STORABLE_VALUES=true \ 4deno task ct piece new pattern.tsx ...

See docs/development/EXPERIMENTAL_OPTIONS.md for all available flags.

Local servers: See docs/development/LOCAL_DEV_SERVERS.md

Quick Command Reference

OperationCommand
Type checkdeno task ct check pattern.tsx --no-run
Deploy newdeno task ct piece new pattern.tsx -i key -a url -s space
Update existingdeno task ct piece setsrc pattern.tsx --piece ID -i key -a url -s space
Inspect statedeno task ct piece inspect --piece ID ...
Get fielddeno task ct piece get --piece ID fieldPath ...
Set fieldecho '{"data":...}' | deno task ct piece set --piece ID path ...
Call handlerdeno task ct piece call --piece ID handlerName ...
Trigger recomputedeno task ct piece step --piece ID ...
List piecesdeno task ct piece ls -i key -a url -s space
Visualizedeno task ct piece map ...

Check Command Flags

deno task ct check compiles and evaluates patterns. Key flags:

FlagPurpose
--no-runType check only, don't execute
--no-checkExecute without type checking
--show-transformedShow the transformed TypeScript after compilation
--verbose-errorsShow original TS errors alongside simplified hints
--pattern-jsonPrint the evaluated pattern export as JSON
--output <path>Store compiled JS to a file
--main-export <name>Select non-default export (default: "default")
--filename <name>Override filename for source maps

Common usage:

bash
1deno task ct check pattern.tsx # Compile + execute (quiet on success) 2deno task ct check pattern.tsx --no-run # Type check only (fast) 3deno task ct check pattern.tsx --no-check # Skip types, just execute 4deno task ct check pattern.tsx --show-transformed # Debug compiler transforms 5deno task ct check pattern.tsx --verbose-errors # Detailed error context

Core Workflow: setsrc vs new

Critical pattern: After initial deployment, use setsrc to iterate:

bash
1# First time only 2deno task ct piece new pattern.tsx ... 3# Output: Created piece bafyreia... <- Save this ID! 4 5# ALL subsequent iterations 6deno task ct piece setsrc pattern.tsx --piece bafyreia... ...

Why: new creates duplicate pieces. setsrc updates in-place.

JSON Input Format

All values to set and call must be valid JSON:

bash
1# Strings need nested quotes 2echo '"hello world"' | deno task ct piece set ... title 3 4# Numbers are bare 5echo '42' | deno task ct piece set ... count 6 7# Objects 8echo '{"name": "John"}' | deno task ct piece set ... user

Gotcha: Always step After set or call

Neither piece set nor piece call triggers recomputation automatically. You must run piece step after either one to get fresh computed values.

bash
1# After setting data: 2echo '[...]' | deno task ct piece set --piece ID expenses ... 3deno task ct piece step --piece ID ... # Required! 4deno task ct piece get --piece ID totalSpent ... 5 6# After calling a handler: 7deno task ct piece call --piece ID addItem '{"title": "Test"}' 8deno task ct piece step --piece ID ... # Required! 9deno task ct piece inspect --piece ID ...

Handler testing workflow (deploy → call → step → inspect):

bash
1# 1. Deploy 2deno task ct piece new pattern.tsx -i key -a url -s space 3# 2. Call a handler 4deno task ct piece call --piece ID handlerName '{"arg": "value"}' ... 5# 3. Step to process 6deno task ct piece step --piece ID ... 7# 4. Inspect result 8deno task ct piece inspect --piece ID ... 9# 5. Repeat 2-4 for each handler

See docs/common/workflows/handlers-cli-testing.md for the full workflow and docs/development/debugging/cli-debugging.md for debugging.

Troubleshooting

IssueFix
Commands hangCheck Tailnet connection for *.ts.net URLs
Permission deniedchmod 600 claude.key
JSON parse errorCheck nested quotes, no trailing commas
Local servers not responding./scripts/check-local-dev.sh then ./scripts/restart-local-dev.sh --force

References

  • packages/patterns/system/default-app.tsx - System pieces (allCharms list lives here)
  • docs/common/workflows/handlers-cli-testing.md - Handler testing
  • docs/development/debugging/cli-debugging.md - CLI debugging

Verwandte Fähigkeiten

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

Alle anzeigen

openclaw-release-maintainer

Logo of openclaw
openclaw

Lokalisierte Zusammenfassung: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

333.8k
0
Künstliche Intelligenz

widget-generator

Logo of f
f

Lokalisierte Zusammenfassung: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code

149.6k
0
Künstliche Intelligenz

flags

Logo of vercel
vercel

Lokalisierte Zusammenfassung: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
Browser

pr-review

Logo of pytorch
pytorch

Lokalisierte Zusammenfassung: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
Entwickler