MCP HubMCP Hub
スキル一覧に戻る

Project Timeline

derekcrosslu
更新日 Today
56 閲覧
0
GitHubで表示
その他general

について

Project Timelineは、CLIベースのスキルで、開発者がタスク追跡と進捗管理を通じて、体系的にプロジェクトのチェックリストを管理することを支援します。このスキルは、次に推奨されるタスクを取得するコマンドと、項目を完了としてマークするコマンドを提供し、自動コミットのためのオプションのGit連携機能を備えています。作業セッションを開始する時や、次に何をすべきかわからずプロジェクトの勢いを維持したい場合に、このスキルをご利用ください。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/derekcrosslu/CLAUDE_CODE_EXPLORE
Git クローン代替
git clone https://github.com/derekcrosslu/CLAUDE_CODE_EXPLORE.git ~/.claude/skills/Project Timeline

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Project Timeline CLI

Manage project timeline with CLI: venv/bin/python SCRIPTS/timeline_cli.py (use as timeline)

When to Load This Skill

  • Starting a new work session (get next task)
  • Completing any checklist item (mark complete)
  • Unsure what to work on next
  • Checking progress

CLI Commands

Get Next Task

# What should I work on?
venv/bin/python SCRIPTS/timeline_cli.py next

# Next task in week 1
venv/bin/python SCRIPTS/timeline_cli.py next --week 1

# Next task in test section
venv/bin/python SCRIPTS/timeline_cli.py next --section test

# JSON output
venv/bin/python SCRIPTS/timeline_cli.py next --json

Mark Complete

# Mark done + automatic git commit
venv/bin/python SCRIPTS/timeline_cli.py complete w1-test-003

# Mark done without commit
venv/bin/python SCRIPTS/timeline_cli.py complete w1-test-003 --no-commit

# Custom commit message
venv/bin/python SCRIPTS/timeline_cli.py complete w1-test-003 -m "Custom message"

Check Status

# Current week progress
venv/bin/python SCRIPTS/timeline_cli.py status

# JSON output
venv/bin/python SCRIPTS/timeline_cli.py status --json

Find Tasks

# All pending tasks
venv/bin/python SCRIPTS/timeline_cli.py find --status pending

# Week 1 tasks
venv/bin/python SCRIPTS/timeline_cli.py find --week 1

# Completed tasks in test section
venv/bin/python SCRIPTS/timeline_cli.py find --status completed --section test

# First 5 tasks
venv/bin/python SCRIPTS/timeline_cli.py find --limit 5

Workflow

  1. Start Session: timeline next → Get next pending task
  2. Do Work: Implement/test/document
  3. Complete: timeline complete TASK_ID → Updates JSON + git commit
  4. Push: git push (if configured)

Core Principles

Priority 1: Complete the Framework

Establish baseline → Research dependencies → Complete framework logic

Focus on building complete system first:

  • ✅ All commands exist and work
  • ✅ All wrappers exist and work
  • ✅ All skills exist
  • ✅ State machine works
  • ✅ Integration works end-to-end

DO NOT get distracted by:

  • Testing multiple hypotheses (1-2 validates system)
  • Optimizing performance (works first, fast second)
  • Adding features not in checklist
  • Extensive documentation (minimal docs, focus on code)

Priority 2: Validate the Framework

Validate logic paths → Test robustness → Calibrate thresholds

Only after Priority 1 complete:

  • Test decision framework with diverse scenarios
  • Measure false positive/negative rates
  • Calibrate thresholds
  • Validate reliability

Robustness is meaningless without completeness.

Authoritative Documentation (Source of Truth)

When confused about workflow, phases, or decisions:

  • Read: PROJECT_DOCUMENTATION/autonomous_decision_framework.md
  • Contains: 5-phase workflow, decision thresholds, routing logic

When confused about architecture or how components fit:

  • Read: PREVIOUS_WORK/PROJECT_DOCUMENTATION/autonomous_workflow_architecture.md
  • Contains: Complete system architecture, state machine, integration patterns

Never guess. Always research first. Use authoritative docs as source of truth.

CLI Help

Use --help for command details:

venv/bin/python SCRIPTS/timeline_cli.py --help
venv/bin/python SCRIPTS/timeline_cli.py next --help
venv/bin/python SCRIPTS/timeline_cli.py complete --help

Do not read timeline_cli.py source code. Use --help for usage.


Context Savings: 60 lines (vs 631 lines in old skill) = 90% reduction

Progressive Disclosure: Load only what you need (next task, not entire timeline)

Trifecta: CLI works for humans, teams, AND agents

GitHub リポジトリ

derekcrosslu/CLAUDE_CODE_EXPLORE
パス: .claude/skills/project-timeline

関連スキル

algorithmic-art

メタ

This Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.

スキルを見る

subagent-driven-development

開発

This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.

スキルを見る

executing-plans

デザイン

Use the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.

スキルを見る

cost-optimization

その他

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

スキルを見る