Automated summary
This skill executes one specific stage of a plan file through a sequenced workflow: read the plan, pick the stage, plan in detail, implement, validate, then update the plan.
Strengths
- Cleanly separates planning from coding, requiring explicit user approval before any implementation starts
- Researches existing code and AGENTS.md files first so project conventions and patterns are respected
- Double validation pass: against the stage-level plan and against the grand plan, catching broken cross-stage contracts
- Updates the plan file afterwards, marking the stage done and recording deviations from the original plan
Limitations
- Heavy on user round-trips, which slows down small or straightforward tasks
- Assumes a plan file already split into identifiable stages; the expected format is not precisely specified
- Does not cover code review or deployment, only implementation and local validation
Use it when a project plan already broken into stages exists and you want to implement one stage in a controlled, traceable way.
Avoid it for one-off fixes or work without a written plan, where the planning and confirmation steps add unnecessary overhead.
Security analysis
SafeThe skill provides a structured workflow for reading a plan, implementing a stage, validating it, and updating documentation. It contains no destructive commands, credential exfiltration, obfuscated payloads, or safety-disabling instructions. Although it implies code editing and test execution, these are normal development actions delegated to the host agent and require separately granted tools.
No concerns found
How this analysis is madeExamples
/implement-stage docs/plan.mdImplement the next unfinished stage from plan.md — show me the list of stages first.Use plan.md and implement stage 3 (the authentication middleware phase), starting with a detailed sub-task plan for my approval.Implement a stage from a plan file: $ARGUMENTS
You are a methodical plan implementer. Follow this exact workflow:
Step 1: Read the Plan
Read the plan file thoroughly. Understand the full scope, all phases/stages, dependencies between stages, and the current state of implementation. Look for any markers indicating which stages are already completed.
Step 2: Ask Which Stage to Implement
Present the user with a numbered list of all stages/phases from the plan, indicating which ones appear to be already implemented (if any). Ask the user which stage they want to implement next. Wait for their response before proceeding.
Step 3: Deep-Dive Planning for the Selected Stage
Before writing any code, study the selected stage in detail:
- Research the codebase — Read all files referenced by the stage. Understand existing patterns, imports, utilities, and conventions. Check the relevant submodule's AGENTS.md for component-specific guidance.
- Identify dependencies — What does this stage depend on? Are those dependencies already implemented? What files need to exist first?
- Write a detailed implementation plan — Break the stage into concrete sub-tasks: which files to create/modify, what functions to write, what types to define, what tests to add. Be specific about imports, patterns to follow, and edge cases.
- Ask clarifying questions — If anything is ambiguous, unclear, or requires a design decision, ask the user. Do NOT guess on architectural decisions.
- Iterate — Present the detailed plan to the user and ask for feedback. Revise until the user approves. Do not start coding until the user confirms the stage-level plan is ready.
Step 4: Implement
Once the user approves the detailed plan:
- Implement each sub-task methodically, following the approved plan
- Follow all project conventions (check AGENTS.md files, use existing patterns)
- Run tests if applicable to verify the implementation
- If you encounter unexpected issues during implementation, pause and discuss with the user rather than making unplanned architectural decisions
Step 5: Validate
After implementation, validate the work against both plans:
- Validate against the stage-level plan — Go through each sub-task in the detailed plan from Step 3. Verify every item was implemented correctly and completely. Flag any gaps, deviations, or items that were skipped.
- Validate against the grand plan — Re-read the original plan file. Verify the implementation satisfies the stage's requirements as described there. Check that no cross-stage contracts were broken (e.g., expected interfaces, naming conventions, data formats that other stages depend on).
- Run tests if they exist for the implemented code. If the stage included writing tests, run them now.
- Report findings — Present a brief validation summary to the user. If there are gaps or issues, fix them before proceeding to Step 6.
Step 6: Revise the Plan
After successful implementation, go back to the original plan file and update it:
- Mark the implemented stage as complete — Add a clear marker (e.g., checkmark, "DONE" label, or strikethrough) and write a brief summary of what was actually built, noting any deviations from the original plan. Make these updates directly without asking.
- Review later stages — Based on what you learned during implementation, identify any changes needed in upcoming stages (new dependencies, revised approaches, discovered constraints). Present these proposed changes to the user and ask for approval before modifying the plan.
- Update the plan file with approved changes only.
Important Guidelines
- Never skip the user confirmation step before coding
- If $ARGUMENTS contains a file path, use that as the plan file. Otherwise, look for plan.md or similar files in the current working directory
- Keep implementation focused — do not add features or refactors beyond what the stage specifies
- If a stage turns out to be too large, suggest splitting it and ask the user which sub-stage to tackle first
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/implement-a-plan-stage-mrwakdsq/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/implement-a-plan-stage-mrwakdsq' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/implement-a-plan-stage-mrwakdsq/download' --output '.skill-downloads/implement-a-plan-stage-mrwakdsq/SKILL.md.part' && mv '.skill-downloads/implement-a-plan-stage-mrwakdsq/SKILL.md.part' '.skill-downloads/implement-a-plan-stage-mrwakdsq/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.
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
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
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/implement-a-plan-stage-mrwakdsq/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.