本文へ移動
cccskills
無料GitHub で公開

strategic-planner

Interview-based strategic planning for complex software tasks. Conducts structured requirements gathering, gap analysis, and generates detailed work plans before implementation begins.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.9 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。

Strategic Planner

An intelligent interviewer that helps think through complex software tasks before writing code. Separates planning from execution to prevent cognitive drift and scope creep.

When to Use This Skill

  • Multi-day or multi-step implementation projects
  • Critical production changes requiring careful planning
  • Complex refactoring with behavior preservation needs
  • Any task where "just start coding" leads to rework

What This Skill Does

Phase 1: Interview — Requirements Gathering

Adapt interview style based on intent:

IntentFocusExample Questions
RefactoringSafety — behavior preservation"What tests verify current behavior?" "Rollback strategy?"
Build from ScratchDiscovery — patterns first"Found pattern X in codebase. Follow it or deviate?"
Mid-sized TaskGuardrails — exact boundaries"What must NOT be included? Hard constraints?"
ArchitectureStrategic — long-term impact"Expected lifespan? Scale requirements?"

Clearance check after each response:

  • Core objective defined?
  • Scope boundaries established?
  • No critical ambiguities?
  • Technical approach decided?
  • Test strategy confirmed?

Continue interviewing until all checks pass. Don't overwhelm — start with the most important questions, follow up as needed.

Phase 2: Gap Analysis

Before writing the plan, catch what the interview missed:

  • Hidden intentions in the user's request
  • Ambiguities that could derail implementation
  • Over-engineering or scope creep tendencies
  • Missing acceptance criteria
  • Edge cases not addressed

The plan author has "working memory ADHD" — makes connections that never make it onto the page. Gap analysis forces externalization of implicit knowledge.

Phase 3: Plan Generation

Write a structured plan with:

  1. Objective — One sentence, crystal clear
  2. Scope — What's in, what's explicitly out
  3. Tasks — Ordered, each with:
    • Description of what to do
    • Files to read/modify (specific paths)
    • Acceptance criteria (concrete, measurable)
    • Dependencies on other tasks
  4. Test Strategy — How to verify each task
  5. Risks — Known unknowns and mitigation

Phase 4: Plan Review (Optional, High-Accuracy Mode)

Validate the plan against four criteria:

  1. Clarity: Does each task specify WHERE to find implementation details?
  2. Verification: Are acceptance criteria concrete and measurable?
  3. Context: Sufficient context to proceed without >10% guesswork?
  4. Completeness: Purpose, background, and workflow clear?

Approval requires:

  • 100% of file references verified
  • =80% of tasks have clear reference sources

  • =90% of tasks have concrete acceptance criteria

  • Zero tasks requiring assumptions about business logic

If rejected, fix issues and resubmit. No maximum retry limit.

Example

User: "I want to refactor the auth system to support OAuth"

Interview output:

Q: What OAuth providers need support? → Google + GitHub
Q: Keep existing password auth? → Yes, alongside OAuth
Q: What tests exist for current auth? → Unit tests in tests/auth/
Q: Rollback strategy? → Feature flag, disable OAuth without removing code

Plan output: 6 tasks with specific file paths, acceptance criteria, dependency ordering, and test strategy.

Tips

  • Don't skip the interview — even 3 questions prevent major rework
  • Plans are living documents — update as you learn during implementation
  • The gap analysis step catches 30-40% of issues that interviews miss
  • High-accuracy review mode is worth the time for production-critical changes

Inspired by: oh-my-opencode Prometheus planning agent

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。

同じリポジトリのスキル

概要と使いどころ

Applies abstract interpretation using different abstract domains (intervals, octagons, polyhedra, sign, congruence) to statically analyze program variables and infer invariants, value ranges, and relationships. Use when analyzing program properties, inferring loop invariants, detecting potential errors, or understanding variable relationships through static analysis.

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。

ArabelaTso/Skills-4-SE2532026年8月21日 更新

Uses abstract interpretation to automatically infer loop invariants, function preconditions, and postconditions for formal verification. Generates invariants that capture program behavior and support correctness proofs in Dafny, Isabelle, Coq, and other verification systems. Use when adding formal specifications to code, generating verification conditions, inferring contracts for functions, or discovering loop invariants for proofs.

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。

ArabelaTso/Skills-4-SE2532026年8月21日 更新

Performs abstract interpretation over source code to infer possible program states, variable ranges, and data properties without executing the program. Reports potential runtime errors including out-of-bounds accesses, null dereferences, type inconsistencies, division by zero, and integer overflows. Use when analyzing code for potential runtime errors, performing static analysis, checking safety properties, or verifying program behavior without execution.

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。

ArabelaTso/Skills-4-SE2532026年8月21日 更新

Performs abstract interpretation to produce summarized execution traces and high-level program behavior representations. Highlights key control flow paths, variable relationships, loop invariants, function summaries, and potential runtime states using abstract domains (intervals, signs, nullness, etc.). Use when analyzing program behavior, understanding execution paths, computing loop invariants, tracking variable ranges, detecting potential runtime errors, or generating program summaries without concrete execution.

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。

ArabelaTso/Skills-4-SE2532026年8月21日 更新

Create ACSL (ANSI/ISO C Specification Language) formal annotations for C/C++ programs. Use this skill when working with formal verification, adding function contracts (requires/ensures), loop invariants, assertions, memory safety annotations, or any ACSL specifications. Supports Frama-C verification and generates comprehensive formal specifications for C/C++ code.

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。

ArabelaTso/Skills-4-SE2532026年8月21日 更新

CLI-based browser automation with persistent page state using ref-based element interaction. Use when users ask to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

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。

ArabelaTso/Skills-4-SE2532026年8月21日 更新

ArabelaTso のスキルをすべて見る

このスキルの問題を報告する