Skill

create-plan

Create a hierarchical multi-phase project plan optimized for solo agentic development. Supports brief, roadmap, and phase-plan types. Each task is scoped for a single agent session. Saves to ./plans/YYMMDD-HHMM-slug/.

From cc-setup

Install

Run in your terminal

npx claudepluginhub krzemienski/cc-setup --plugin cc-setup

Tool Access

This skill uses the workspace's default tool permissions.

Skill Content

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

138.6k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

evaluation-methodology

1 file

Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.

plugin-eval

32.9k

Stats

Stars0

Forks0

Last CommitMar 20, 2026

Actions

View Source View Plugin View on GitHub View README

Step 3: Structure Each Phase

Phase N: <Name> Goal: <What this phase achieves> Tasks: N.1 <Task> → output: <artifact> N.2 <Task> → output: <artifact> Dependencies: Phase X must complete first Effort: S / M / L Validation gate: <What must be true before next phase>

Rules for tasks:

Each task is completable by a single agent in one session

Each task has a named output (file, endpoint, config, etc.)

Each task lists its inputs (what must exist before it runs)

Always end with a Functional Validation phase:

Phase N: Functional Validation Tasks: N.1 Build / start the real system N.2 Exercise through actual interface (CLI, UI, API) N.3 Capture evidence (screenshot, log, response) N.4 Confirm evidence matches success criteria Validation gate: Evidence captured and all success criteria met

No unit tests. No mocks. Real system only.

Output Format

## Project: <Name> **Type:** brief | roadmap | phase-plan **Goal:** <one sentence> **In scope:** ... | **Out of scope:** ... | **Constraints:** ... ## Success Criteria - [ ] ... ## Phases ### Phase 1: <Name> **Goal:** ... | **Effort:** S/M/L | **Dependencies:** none 1.1 ... → output: ... **Validation gate:** ... ### Phase N: Functional Validation ... ## Dependency Map Phase 2 → requires Phase 1 ## Effort Summary Total: ~X days

Step 3: Structure Each Phase

Rules for tasks:

Each task is completable by a single agent in one session

Each task has a named output (file, endpoint, config, etc.)

Each task lists its inputs (what must exist before it runs)

Always end with a Functional Validation phase:

No unit tests. No mocks. Real system only.

Output Format

create-plan

create-plan

Create Plan

Step 1: Detect Plan Type

Step 2: Gather Scope

Step 3: Structure Each Phase

Step 4: Save the Plan

Step 5: Present and Confirm

Output Format

Create Plan

Step 1: Detect Plan Type

Step 2: Gather Scope

Step 3: Structure Each Phase

Step 4: Save the Plan

Step 5: Present and Confirm

Output Format