Automated summary
Produces a detailed implementation plan for a feature and writes it to a plan.md file that implement-feature can consume.
Strengths
- Breaks the plan into concrete sections: files to create or modify, ordered steps, test strategy, risks
- Cleans the chain directory first to avoid stale artifacts
- Fits into an explicit handoff with implement-feature through a normalized output file
Limitations
- Only produces a plan: no actual code changes are made
- Relies on the fixed path .claude/chain/plan.md and on implement-feature being available afterwards
- Plan quality depends entirely on codebase research, with no described safeguards
Use this skill as the first step when a feature needs a reviewed implementation plan before any coding starts.
Skip it for trivial fixes or exploratory tasks where a formal plan would be overkill.
Security analysis
SafeThe only executable action is a scoped `rm -f` on two fixed files inside the project's chain directory; there are no recursive deletes, downloads, pipes to shells, credential access, or obfuscated payloads. Bash is used for a legitimate cleanup purpose consistent with the skill's role in a plan/implement chain, so overall risk is low, with the sole note being that it removes prior plan/result state without prompting.
- •Declares Bash and runs `rm -f .claude/chain/plan.md .claude/chain/result.md` — deletion is narrowly scoped to two explicit, non-globbed paths with no recursion, but it does silently overwrite/delete any pre-existing chain state in those files.
Examples
/plan-feature add OAuth2 login with Google for the existing user accounts/plan-feature refactor the payment module to separate Stripe and PayPal providers/plan-feature add a rate-limiting middleware to the public REST APIname: plan-feature description: > Creates a detailed implementation plan for a feature. Outputs a plan file that can be consumed by implement-feature. Use as the first step in a feature development chain. argument-hint: "[feature description]" allowed-tools: Read, Bash
Plan feature: $ARGUMENTS
Steps
- Clean the chain directory:
rm -f .claude/chain/plan.md .claude/chain/result.md - Research the codebase to understand relevant modules and patterns
- Design the implementation approach
- Write the plan to
.claude/chain/plan.mdwith:- Feature summary
- Files to create/modify (with paths)
- Implementation steps (ordered)
- Test strategy
- Risks and mitigations
- Tell the user: "Plan saved to
.claude/chain/plan.md. Runimplement-featureto execute it."
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 filesThis 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.mdFrom the root of a test project, save the file as .skill-downloads/plan-feature-mrzxuq5i/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/plan-feature-mrzxuq5i' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/plan-feature-mrzxuq5i/download' --output '.skill-downloads/plan-feature-mrzxuq5i/SKILL.md.part' && mv '.skill-downloads/plan-feature-mrzxuq5i/SKILL.md.part' '.skill-downloads/plan-feature-mrzxuq5i/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, Bash
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/plan-feature-mrzxuq5i/SKILL.md' && test -s '.skill-downloads/plan-feature-mrzxuq5i/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/plan-feature' && cp -R '.skill-downloads/plan-feature-mrzxuq5i' '.claude/skills/plan-feature'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 installationopenskills install './.skill-downloads/plan-feature-mrzxuq5i'openskills read 'plan-feature-mrzxuq5i'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 syncManual 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/plan-feature-mrzxuq5i/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.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.