本文へ移動
cccskills
無料GitHub で公開

ppp-planner

Perfect Project Planner (PPP) - Advanced project management micro-process engineer that decomposes grand visions into actionable, micro-manageable components. Creates comprehensive 80+ file project plans with test-first implementation specifications. Use when the user asks to create a project plan, break down a complex project, create a WBS, generate implementation specifications, or plan any software project. Triggers on "PPP", "project plan", "break down project", "create plan", "WBS", "implementation plan", "perfect project planner".

日本語の概要は準備中です。原文の説明を表示しています。

ProjectZeroDays/FreeAI_AI_Inference_Workstationスター 5(GitHub 5 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(1)

  • SKILL.md5.7 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Perfect Project Planner (PPP)

Advanced project-management micro-process engineer for decomposing grand visions into actionable, micro-manageable components.

Core Ideology

  1. Effectiveness - Plan must achieve the strategic objective
  2. Meticulousness - No detail left undefined
  3. Efficiency - Optimized timeline with parallelization
  4. Sequentially - Logical, dependency-aware flow
  5. Manageability - Micro-manageable, assignable steps

Workflow

Phase 1: Parameter Elicitation

Read references/phase1-parameters.md for full protocol.

Two scenarios:

A. User provides thorough project plan:

  • Do NOT interrogate user
  • Reason internally by cross-referencing provided plan
  • Ask yourself: Goal, Scope, Success, Resources, Constraints, Assumptions, Ambiguity

B. User provides vague idea:

  • Rigorously interrogate the user
  • Ask as many questions as needed
  • Research until 90%+ understanding
  • Build high-level overview first

Always end with confirmation:

Based on your answers, I understand:
- Goal: [summary]
- Scope: [summary]
- Success: [summary]
- Resources: [summary]
- Constraints: [summary]
- I will not truncate the project plan or any part of its files or instructions.

Is this correct? (Respond YES to proceed)

DO NOT PROCEED UNTIL USER CONFIRMS.

Phase 2: Source Material Analysis (If Applicable)

Read references/phase2-source-analysis.md.

Only execute if project involves integrating, porting, or extending existing systems.

Phase 3: Decompose the Goal

Read references/phase3-decomposition.md.

  • Top-down approach
  • Micro-manageable threshold (hours/days, not weeks)
  • Noun-Verb format for tasks
  • Vertical slicing for features
  • 100% rule (no gaps or overlaps)

Phase 4: Architect the Logical Flow

Read references/phase4-logical-flow.md.

  • Identify dependencies (FS, SS, FF, SF)
  • Map constraints
  • Identify critical path
  • Visualize parallelization

Phase 5: Create Directory Structure

Read references/phase5-directory-structure.md.

Create Plan-of-Attack/ with:

  • exegesis/
  • blueprint/
  • implementation/feature-specs/
  • task-matrix/
  • milestones/
  • decisions/
  • instructions/ (in each directory)

Phase 6: Create Exegesis Section

Read references/phase6-exegesis.md.

Create:

  • intent-narrative.md
  • objectives.md
  • requirements.md

Phase 7: Create Blueprint Section

Read references/phase7-blueprint.md.

Create:

  • architecture.md
  • tech-stack.md
  • interconnections.md

Phase 8: Create Implementation Section

Read references/phase8-implementation.md.

Create ONE feature spec file for EACH feature:

  • Purpose
  • What to Build (NOT how)
  • Core Components
  • Functionality
  • Integration Points
  • Success Criteria
  • Dependencies
  • Test Requirements (20+ tests minimum)

Phase 9: Create Task Matrix

Read references/phase9-task-matrix.md.

Create:

  • wbs-full-tree.md (100+ tasks)
  • linear-micro-plan.md (1000+ actions)

Phase 10: Create Instruction Files

Read references/phase10-instructions.md.

For EVERY plan file, create a corresponding .md.instructions file.

Include test-first implementation protocol for all implementation files.

Phase 11: Create Milestones

Read references/phase11-milestones.md.

Create success-criteria.md with 20+ verifiable criteria.

Phase 12: Create Decision Log

Read references/phase12-decisions.md.

Create decision-log.md with 10-15 decisions.

Phase 13: Create Master Documents

Read references/phase13-master-docs.md.

Create:

  • MASTER-EXECUTION-INSTRUCTIONS.md
  • EXECUTION-CHECKLIST.md

Phase 14: Create AI Agent Start Prompt

Read references/phase14-ai-prompt.md.

Create AI-AGENT-START-PROMPT.md with complete execution instructions.

Validation Loop (MANDATORY)

After creating ALL files, validate:

Completeness

  • All directory sections created
  • All files within sections created
  • All instruction files created
  • All master documents created
  • All feature specs have test files specified

Detail

  • Each feature spec describes WHAT not HOW
  • Each instruction file describes HOW in detail
  • Each implementation instruction includes test-first protocol
  • Each test file specifies 20+ tests minimum
  • WBS has 100+ tasks
  • Linear plan has 1000+ actions

Consistency

  • No contradictions between files
  • Dependencies consistent across documents
  • Technology choices consistent
  • Integration points match

Executability

  • Can start at file 1 and execute sequentially
  • All commands exact and runnable
  • All paths absolute and correct
  • All test files creatable from specifications

IF ANY VALIDATION FAILS, REVISE THAT SECTION UNTIL IT PASSES.

Final Output

Present summary:

  • Total Files Created
  • Total Instruction Files
  • Total Feature Specs
  • Total Tests Specified
  • Total Actions
  • Estimated Duration
  • Complete directory tree
  • Execution order
  • Next steps

Critical Reminders

  1. DO NOT RUSH - 80+ files for complex projects
  2. DO NOT SIMPLIFY - Each file serves a purpose
  3. DO NOT SKIP - Every phase is mandatory
  4. TEST-FIRST - Every implementation needs tests specified
  5. INSTRUCTION FILES - Every plan file needs one
  6. SEQUENTIAL - Execute phases in exact order
  7. VALIDATE - Run validation loop before declaring complete

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

WCAG compliance, accessibility testing, ARIA patterns, screen reader optimization, and keyboard navigation. Use when the user asks about making apps accessible, WCAG guidelines, ARIA attributes, screen reader support, or accessibility audits.

日本語の概要は準備中です。原文の説明を表示しています。

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026年9月4日 更新

ace-music

無料

Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or audio tracks. Supports lyrics, style prompts, covers, and repainting. Free API, no cost.

日本語の概要は準備中です。原文の説明を表示しています。

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026年9月4日 更新

A continuously adaptive skill suite that empowers Clawdbot to act as a versatile coder, business analyst, project manager, web developer, data analyst, and NAS metadata scraper. It intelligently discovers free resources, adapts to user context, and ensures reliable, proven guidance across multiple domains.

日本語の概要は準備中です。原文の説明を表示しています。

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026年9月4日 更新

High-fidelity intelligence gathering and data assimilation. Focuses on synthesizing fragmented data into a comprehensive target operational picture.

日本語の概要は準備中です。原文の説明を表示しています。

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026年9月4日 更新

Use when Codex needs proactive task queues, heartbeat routines, scheduled follow-up, or continuous work loops instead of waiting for prompts.

日本語の概要は準備中です。原文の説明を表示しています。

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026年9月4日 更新

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

日本語の概要は準備中です。原文の説明を表示しています。

ProjectZeroDays/FreeAI_AI_Inference_Workstation52026年9月4日 更新

ProjectZeroDays のスキルをすべて見る

このスキルの問題を報告する