Project Planning

VerifiedSafe

Creates detailed step-by-step implementation plans with acceptance criteria, exclusive to the planner agent. Leverages MCP helpers like Gemini-Bridge and Context7 for architecture analysis and documentation lookup. Supports PHP/Laravel and Python stacks with independently testable phases and risk matrices.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#project-planning#implementation-plans#acceptance-criteria#mcp#architecture

Recommended for

Automated summary

This skill creates detailed implementation plans with testable phases, estimates, and acceptance criteria, using MCP helpers for architecture and documentation research.

Strengths

  • Clear structure with independent, testable phases
  • Integrates architecture research via MCP helpers (Gemini, Context7)
  • Provides estimation techniques (T-shirt sizing) and risk matrix

Limitations

  • Exclusive to the planner agent, not directly usable in other contexts
  • Requires MCP tools to be configured and accessible
  • Estimates remain approximate and depend on actual complexity
When to use it

Use this skill to break down a complex feature into manageable tasks with clear milestones and acceptance criteria.

When not to use it

Avoid this skill for simple fixes or trivial changes that do not require structured planning.

Security analysis

Safe
Quality score90/100

The skill instructs the planner agent to create implementation plans using MCP tools for research and documentation lookup. It does not execute destructive or exfiltrating commands; the use of Bash is only for suggested verification commands within the plan template, with no actual execution risk.

No concerns found

How this analysis is made

Examples

New settings page
Plan a new settings page for the Laravel app with Inertia.js, including fields for user profile, notifications, and privacy. Use MCP helpers to research existing patterns.
Safe column migration
Create a migration plan for adding a column safely to the users table, with rollback steps and risk mitigation.
Feature implementation plan
Plan the implementation of a two-factor authentication feature, breaking it down into phases with estimates and acceptance criteria.

name: project-planning description: Create clear, step-by-step implementation plans with acceptance criteria using MCP helpers. EXCLUSIVE to planner agent. allowed-tools: Read, Grep, Glob, Bash, mcp_gemini-bridge, mcp_open-bridge, mcp_codex-bridge, mcp_context7

Project Planning

Exclusive to: planner agent

MCP Helpers (Brain + Memory)

🧠 Gemini-Bridge (Brain) β€” Architecture Analysis

mcp_gemini-bridge_consult_gemini(
  query="Design architecture for [feature]: phases, risks, dependencies...",
  directory="."
)

πŸŒ‰ Open-Bridge β€” Alternative Architecture Analysis

mcp_open-bridge_consult_gemini(
  query="Design architecture for [feature]: phases, risks, dependencies...",
  directory="."
)

πŸ“š Context7 (Memory) β€” Documentation Lookup

mcp_context7_resolve-library-id(libraryName="laravel", query="[feature]")
mcp_context7_query-docs(libraryId="/laravel/docs", query="[specific pattern]")

Supported Stacks

PHP/Laravel: Laravel 12, Inertia.js, React 19, TypeScript, Tailwind Python: FastAPI, LangChain, LangGraph, Pydantic, pytest

Instructions

1. Restate Goal

One sentence summary of what we're building.

2. Research

  • Search codebase for similar patterns
  • Identify affected files
  • Note dependencies

3. Break Down

Create 3-5 phases, each independently testable.

Estimation Techniques

T-Shirt Sizing

| Size | Hours | Complexity | |------|-------|------------| | XS | 1-2 | Single file | | S | 2-4 | Few files | | M | 4-8 | Multiple files | | L | 1-2 days | Multiple components | | XL | 3-5 days | Full feature |

Risk Multipliers

  • Database migration: 1.5x
  • Auth/security: 1.5x
  • Third-party: 2x

Risk Matrix

| Level | Criteria | Mitigation | |-------|----------|------------| | πŸ”΄ High | Data loss, security, breaking | Rollback plan, staging | | 🟑 Medium | Performance, UX regression | Feature flag | | 🟒 Low | Cosmetic, refactor | Standard testing |

Phase Template

# Phase N: [Name]

## Objective
[What this accomplishes]

## Tasks
- [ ] Task with file path

## Files
| File | Action |
|------|--------|
| `path/file` | Create/Modify |

## Verification
```bash
[commands]

Estimate

[X hours]


## plan.md Output (REQUIRED)

Always create a consolidated `plan.md` file that contains ALL phases and context:

```markdown
# Plan: [Feature Name]

## Context
[What we're building and why]

## Code Patterns to Follow
[Key patterns from codebase research]

## Phases
| # | Name | Objective | Est. |
|---|------|-----------|------|

---

## Phase 1: [Name]
### Objective
[Goal]

### Tasks
- [ ] Task with `path/to/file`

### Files
| File | Action |
|------|--------|

---

[... repeat for each phase ...]

---

## Summary
- **Total Phases**: N
- **Estimated Effort**: X hours
- **Key Risks**: [list]

Examples

  • "Plan a new settings page"
  • "Create a migration plan for adding a column safely"

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/project-planning-mmbizkj5/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/project-planning-mmbizkj5' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/project-planning-mmbizkj5/download' --output '.skill-downloads/project-planning-mmbizkj5/SKILL.md.part' && mv '.skill-downloads/project-planning-mmbizkj5/SKILL.md.part' '.skill-downloads/project-planning-mmbizkj5/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Grep, Glob, Bash, mcp_gemini-bridge, mcp_open-bridge, mcp_codex-bridge, mcp_context7

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/project-planning-mmbizkj5/SKILL.md' && test -s '.skill-downloads/project-planning-mmbizkj5/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/project-planning' && cp -R '.skill-downloads/project-planning-mmbizkj5' '.claude/skills/project-planning'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js β‰₯ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/project-planning-mmbizkj5'

openskills read 'project-planning-mmbizkj5'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/project-planning-mmbizkj5/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills