Implementation Planning

VerifiedSafe

Create a detailed implementation plan based on research findings. Use after research is complete and before writing code to define success criteria, scope boundaries, and step-by-step tasks with verification. Helps structure work and prevent scope creep.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#planning#implementation-plan#development-workflow

Recommended for

Automated summary

Creates a detailed implementation plan based on research findings, before writing any code.

Strengths

  • Provides a clear, repeatable structure for planning
  • Integrates success criteria and scope boundaries
  • Facilitates human review before implementation begins

Limitations

  • Requires that research is already completed
  • May be overly formal for very simple tasks
When to use it

Use this skill after completing research and before starting implementation, to structure the coding work.

When not to use it

Avoid using it when the task is trivial or the plan would take longer than the implementation itself.

Security analysis

Safe
Quality score80/100

The skill only uses Read, Write, Glob, and Grep tools, with no network or shell execution. It instructs planning tasks without any destructive or exfiltrating actions.

No concerns found

How this analysis is made

Examples

Plan feature implementation
Create an implementation plan for adding user authentication with JWT, following the planning phase instructions.
Plan refactoring
I need to refactor the payment module. Please generate a step-by-step plan with verification commands.

name: plan version: 1.0.0 changelog: Initial planning skill with handoff format description: Create specific implementation steps for review. Use after research is complete and before writing code. allowed-tools: Read, Write, Glob, Grep temperature: 0.2 # Mostly deterministic, slight flexibility

Planning Phase

Create a specific implementation plan for review.

Task

$ARGUMENTS

Instructions

Output: ## Planning Phase

State: At phase start, update STATE.md:

  • Set task: from $ARGUMENTS (if STATE.md is idle/complete or task is "None")
  • Set phase: plan
  • Set status: in_progress

1. Consume Research Handoff

Read ## Research Findings from STATE.md:

  • Use Key Files as starting points
  • Honor Constraints in plan design
  • Address Remaining items from research

2. Gather Context

  • Read files identified in research handoff
  • Verify understanding is current
  • Spawn parallel research tasks if gaps exist

3. Define Success Criteria

Automated verification:

  • Build commands that must pass
  • Test commands that must pass
  • Type check commands

Manual verification:

  • UI/UX checks requiring human review
  • Performance validation
  • Edge case review

4. Scope Boundaries

What we're doing:

  • Specific deliverables

What we're NOT doing:

  • Explicit exclusions (prevents scope creep)

5. Create Step-by-Step Plan

Use the plan format template:

## Phase 1: [Name]

- [ ] Step 1: Description
      File: `path/to/file.ts`
      Verification: how to verify this step

- [ ] Step 2: Description
      File: `path/to/other.ts`
      Verification: run `npm test`

## Phase 2: [Name]

- [ ] Step 3: ...

Task schema (from style.md): Each task should have:

  • Action: What to do and why
  • Files: Specific paths (src/auth.ts:42)
  • Verify: Testable command
  • Done: Measurable acceptance criteria

6. Identify Decision Points

  • Where are there meaningful alternatives?
  • What tradeoffs exist?
  • What needs human input before proceeding?

7. Checkpoint

Update STATE.md incrementally:

  • Set phase: plan
  • Add plan decisions to ## Decisions
  • Update ## Next Steps with plan summary and approval status

Run /checkpoint if context is heavy or taking a break.

8. Produce Handoff

Before exit gate, append handoff to STATE.md under ## Plan:

## Plan

### Completed
- [x] Implementation plan created
- [x] Success criteria defined

### Context
**Plan Summary**:
1. [Step 1 brief]
2. [Step 2 brief]
...

**Verification Commands**:
- `[test command]`
- `[build command]`

**Risks Identified**:
- [Risk]: [mitigation]

### Remaining
- [ ] Execute plan steps
- [ ] Verify each step before proceeding

See handoff template for full format.

Constraints

  • Do not implement yet
  • Plan should be specific enough that implementation is mechanical
  • Each phase should be independently verifiable
  • Keep total steps reasonable (3-10 per phase, 20 max overall)

Exit Criteria

Plan is approved by human before proceeding to implementation.

Gate: "Here's the plan. Approve to proceed?"

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/implementation-planning-mmlj2oqi/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/implementation-planning-mmlj2oqi' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/implementation-planning-mmlj2oqi/download' --output '.skill-downloads/implementation-planning-mmlj2oqi/SKILL.md.part' && mv '.skill-downloads/implementation-planning-mmlj2oqi/SKILL.md.part' '.skill-downloads/implementation-planning-mmlj2oqi/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, Write, Glob, Grep

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/implementation-planning-mmlj2oqi/SKILL.md' && test -s '.skill-downloads/implementation-planning-mmlj2oqi/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/plan' && cp -R '.skill-downloads/implementation-planning-mmlj2oqi' '.claude/skills/plan'

OpenSkills

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

Official OpenSkills installation
openskills install './.skill-downloads/implementation-planning-mmlj2oqi'

openskills read 'implementation-planning-mmlj2oqi'

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/implementation-planning-mmlj2oqi/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