Create Implementation Plan

VerifiedSafe

Generates a detailed implementation plan from an existing issue analysis or feature concept. It detects the current branch, reads project guidelines, and produces a structured plan.md with break-down tasks, test plan, checkpoints, and commit strategy. Useful when you have an analysis document and need a concrete coding roadmap.

Sby Skills Guide Bot
DevelopmentIntermediate
3/1/2026
Claude Code
#planning#implementation-plan#workflow#git-branching#issue-tracking

Recommended for

Automated summary

Produces a detailed implementation plan (plan.md) from an issue analysis or feature concept, grounded in the project's own guidelines.

Strengths

  • Infers the correct workflow folder automatically from the current git branch name
  • Breaks work into actionable tasks with file paths, dependencies and verification checkpoints
  • Builds in a test plan, documentation updates and a commit strategy tied to project guidelines
  • Ships a structured, reusable plan.md template

Limitations

  • Requires a prior analysis.md or concept.md plus guideline files (CODING/TESTING/COMMIT_GUIDELINES.md)
  • Example templates lean Go-specific (go build, test/cmd) and need adapting for other stacks
  • Outputs only a plan: no code is written or verified
When to use it

Use it once an issue has been analyzed or a feature concept exists and you need a traceable implementation plan before coding.

When not to use it

Skip it when no analysis or context exists, or for trivial changes that don't warrant a formal plan.

Security analysis

Safe
Quality score88/100

The skill is a documentation/plan generation workflow. Allowed tools are Read, Grep, Glob, and Write; it only reads project guideline files and writes a plan.md into a workflows/ folder. There is no network access, no shell execution, no secret handling, no destructive commands, and no obfuscated content. Write is scoped to a clearly defined markdown file, so execution risk is negligible.

No concerns found

How this analysis is made

Examples

Plan from issue analysis
/create-plan — I'm on branch feature/42-add-config-loader and the analysis is already in workflows/issue-42-add-config-loader/analysis.md. Generate the implementation plan.
Plan a feature concept
Create an implementation plan from workflows/feature-export-csv/concept.md, including the test plan and doc updates per our guidelines.
Validate coverage
Write plan.md for the current branch, then check that every file listed in analysis.md is covered by a task and that the test plan matches TESTING_GUIDELINES.md.

name: create-plan description: Create an implementation plan from issue analysis or feature concept allowed-tools: Read, Grep, Glob, Write

Create Implementation Plan

Generate a detailed implementation plan based on existing analysis or concept documents.

Instructions

  1. Detect Current Context

    • Check current git branch to determine workflow folder
    • Branch feature/42-something → look for workflows/issue-42-*/
    • Branch feature/my-feature → look for workflows/feature-my-feature/
  2. Find Source Document

    • Look for analysis.md (from /analyze-issue) or concept.md (for features)
    • If not found, ask user to run /analyze-issue first or provide context
  3. Read Project Guidelines

    • Review CODING_GUIDELINES.md for implementation standards
    • Review TESTING_GUIDELINES.md for test requirements
    • Review COMMIT_GUIDELINES.md for commit structure
  4. Create Implementation Plan

    • Write plan.md in the same workflow folder
    • Break down into specific, actionable tasks
    • Include file paths and specific changes
    • Add test plan based on TESTING_GUIDELINES.md

Plan Template

Write to workflows/<folder>/plan.md:

# Implementation Plan: <branch-name>

## Source
- Issue: #<number> (<link>)
- Analysis: `workflows/<folder>/analysis.md`

## Overview
<Brief summary of what will be implemented>

## Prerequisites
- [ ] Feature branch created: `feature/<name>`
- [ ] Analysis reviewed and understood
- [ ] No blocking questions remain

## Implementation Tasks

### Task 1: <Name>
**Files**: `path/to/file.go`

**Changes**:
- [ ] <Specific change 1>
- [ ] <Specific change 2>

**Details**:
<Any additional context or code snippets>

### Task 2: <Name>
**Files**: `path/to/file1.go`, `path/to/file2.go`

**Changes**:
- [ ] <Specific change>

**Depends on**: Task 1

### Task 3: Add Tests
**Files**: `test/cmd/<file>_test.go`

**Changes**:
- [ ] Add `Test<FunctionName>` - <what it tests>
- [ ] Add `Test<FunctionName>WithError` - <error case>

**Test Requirements** (per TESTING_GUIDELINES.md):
- One test case per function
- Structured comments with Steps
- Use testutil helpers, not os.Chdir

## Test Plan

### Unit Tests
| Test Name | Purpose | File |
|-----------|---------|------|
| `TestXxx` | <purpose> | `test/...` |

### Integration Tests
| Test Name | Scenario | File |
|-----------|----------|------|
| `TestXxxCommand` | <scenario> | `test/cmd/...` |

## Documentation Updates
- [ ] `docs/<command>.1.md` - <changes needed>
- [ ] `docs/gitflow-config.5.md` - <if config changes>
- [ ] Command help text updates

## Checkpoints

After each checkpoint, verify:
1. `go build ./...` succeeds
2. `go test ./...` passes
3. Changes work as expected

| Checkpoint | After Task | Verification |
|------------|------------|--------------|
| 1 | Task 1 | <what should work> |
| 2 | Task 2 | <what should work> |
| 3 | Task 3 | All tests pass |

## Commit Strategy

Following COMMIT_GUIDELINES.md, plan these commits:
1. `<type>(<scope>): <description>` - <what's included>
2. `test(<scope>): <description>` - test additions
3. `docs(<scope>): <description>` - documentation updates

## Estimated Scope
- Files to modify: <count>
- New files: <count>
- Tests to add: <count>
  1. Validate Plan

    • Ensure all affected files from analysis are covered
    • Verify test plan aligns with TESTING_GUIDELINES.md
    • Check documentation requirements
  2. Report Completion

    • Show path to created plan
    • Suggest next step: /validate-tests to verify test approach, then start implementing

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/create-implementation-plan-mm78noin/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/create-implementation-plan-mm78noin' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/create-implementation-plan-mm78noin/download' --output '.skill-downloads/create-implementation-plan-mm78noin/SKILL.md.part' && mv '.skill-downloads/create-implementation-plan-mm78noin/SKILL.md.part' '.skill-downloads/create-implementation-plan-mm78noin/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, Write

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/create-implementation-plan-mm78noin/SKILL.md' && test -s '.skill-downloads/create-implementation-plan-mm78noin/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/create-plan' && cp -R '.skill-downloads/create-implementation-plan-mm78noin' '.claude/skills/create-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/create-implementation-plan-mm78noin'

openskills read 'create-implementation-plan-mm78noin'

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/create-implementation-plan-mm78noin/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