KS
Killer-Skills

code-with-task-local — how to use code-with-task-local how to use code-with-task-local, code-with-task-local setup guide, CSL-JSON task implementation, IPC status reporting tools, code-with-task-local alternative, code-with-task-local vs other reference management tools, code-with-task-local install, local reference management best practices

v1.0.0
GitHub

About this Skill

Perfect for Developer Agents needing streamlined task implementation and local reference management via CSL-JSON. code-with-task-local is a local reference management tool using CSL-JSON for task implementation and IPC status reporting

Features

Utilizes CSL-JSON as the single source of truth for task implementation
Implements tasks based on spec/_index.md and spec/tasks/ directory
Reports IPC status to .worker-status.json file
Manages tasks using Git branches
Supports dynamic task file path and status updates

# Core Topics

ncukondo ncukondo
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
30
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add ncukondo/reference-manager/code-with-task-local

Agent Capability Analysis

The code-with-task-local MCP Server by ncukondo is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use code-with-task-local, code-with-task-local setup guide, CSL-JSON task implementation.

Ideal Agent Persona

Perfect for Developer Agents needing streamlined task implementation and local reference management via CSL-JSON.

Core Value

Empowers agents to manage tasks and report IPC status efficiently, utilizing CSL-JSON as the single source of truth and facilitating workflow through automated reporting to `.worker-status.json` files.

Capabilities Granted for code-with-task-local MCP Server

Implementing tasks locally with automated status reporting
Managing workflows through CSL-JSON reference management
Debugging IPC status through `.worker-status.json` files

! Prerequisites & Limits

  • Requires local development environment setup
  • Limited to tasks defined in `spec/tasks/` directory
  • Dependent on Git for branch management and workflow
Project
SKILL.md
1.6 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Task Implementation (Local): $ARGUMENTS

spec/_index.mdを起点として必要事項を確認後、spec/tasks/内のタスク [prefix]-*$ARGUMENTS*.md に取り組みます。

作業は $ARGUMENTS に結びつけられたブランチ(無ければ妥当な名前を考えて作成)で行います。

IPC Status Reporting

worktreeルートの .worker-status.json にステータスを書き込む:

bash
1WORKTREE_ROOT="$(git rev-parse --show-toplevel)" 2cat > "$WORKTREE_ROOT/.worker-status.json" <<IPCEOF 3{ 4 "branch": "$(git branch --show-current)", 5 "task_file": "<task file path>", 6 "status": "<status>", 7 "current_step": "<step description>", 8 "pr_number": null, 9 "error": null, 10 "updated_at": "$(date -u +%Y-%m-%dT%H:%M:%SZ)" 11} 12IPCEOF

ステータス値: startingin_progresstestingcreating_prcompleted / failed

書き込みタイミング:

  • 作業開始時: starting
  • 各ステップ着手時: in_progress + current_step 更新
  • テスト実行時: testing
  • PR作成時: creating_pr
  • 完了時: completed + pr_number 設定
  • エラー時: failed + error 設定

Workflow

ステップ一つが完了する毎にタスクファイルを更新し、commit。次の作業に移る前に残りのcontextを確認し、次の作業の完了までにcompactが必要になってしまいそうならその時点で作業を中断して下さい。

Work Boundaries

並列作業時のconflictを避けるため:

  • ブランチ内での作業: 実装 → テスト → PR作成まで
  • マージ後にmainブランチで: ROADMAP.md更新とタスクファイルのcompleted/への移動

Related Skills

Looking for an alternative to code-with-task-local or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication