mcpbeat Sign in

Writing Plans Agent Skill

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

906 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
4940
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/microsoft/FluidFramework --skill writing-plans

The instruction itself

5 sections, as written by the author

<required>

CRITICAL. Add the following steps to your Todo list using TodoWrite:

  • Read the 'Guidelines'.
  • Create a comprehensive plan that a senior engineer can follow.

<system-reminder>Any absolute paths in your plan MUST take into account any worktrees that may have been created</system-reminder>

  • Think about backwards compability. Add any notes to the plan.
  • Think about edge cases. Add them to the plan.
  • Think about questions or areas that require clarity. Add them to the plan.
  • Emphasize how you will test your plan.
  • Present plan to user.

</required>

Guidelines

Overview

Create a comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD.

Assume they are a talented developer. However, assume that they know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.

Do not add code, but include enough detail that the necessary code is obvious.

Do not write a file to disk unless explicitly asked.

Plan Document Header

Every plan MUST start with this header:

# [Feature Name] Implementation Plan

**Goal:** [One sentence describing what this builds]

**Architecture:** [2-3 sentences about approach]

**Tech Stack:** [Key technologies/libraries]

---

Test Section

Every plan MUST have a test section. This should be written first, and should

document how you plan to test the *behavior*.


**Testing Plan**

I will add an integration test that ensures foo behaves like blah. The
integration test will mock A/B/C. The test will then call function/cli/etc.

I will add a unit test that ensures baz behaves like qux...

You should end EVERY testing plan section by writing:

NOTE: I will write *all* tests before I add any implementation behavior.

<system-reminder>Your tests should NOT contain tests for datastructures or

types. Your tests should NOT simply test mocks. Always test actual behavior.</system-reminder>

<required>

For each test, follow this checklist:

  • Ensure that the test does not just test mocks. If it does, remove the test and try again.
  • Ensure the test does not test implementation detail. If it does, rewrite the test so that it tests boundary behavior.
  • Ensure the test does not test data structure format or types. If it does, remove the test and try again.
  • Ensure the test does not test for removed behavior. For example, if some behavior has been deprecated, do not write a test that simply confirms the behavior no longer works.
  • Evaluate if the test treats the interior of the test boundary as a blackbox. You should not know anything about interior variables, function calls, or control flow.

</required>

Every plan MUST end with this footer:

**Testing Details** [Brief description of what tests are being added and how they specifically test BEHAVIOR and NOT just implementation]

**Implementation Details** [maximum 10 bullets about key details]

**Question** [any questions or concerns that may be relevant that need answers]

---

Other skills for the same job

different authors, same section of the catalogue
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Codex
by softaworks
×2

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

2k tokens
Memory Safety Patterns
by ComeOnOliver
×2

Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.

6k tokens
Pysam
by K-Dense-AI
×1

Python/HTSlib workflows for genomic files. Use when reading, querying, filtering, or writing SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ, or tabix data with pysam, including pileup, coverage, indexing, and CRAM references.

34k tokens scripts
Scientific Critical Thinking
by K-Dense-AI
×1

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.

26k tokens
Gh Fix CI
by openai
vendor ×1

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

8k tokens scripts
Documentation
by lingxling
×1

Documentation generation workflow covering API docs, architecture docs, README files, code comments, and technical writing.

1k tokens
Readme I18n
by ComeOnOliver
×1

Use when the user wants to translate a repository README, make a repo multilingual, localize docs, add a language switcher, internationalize the README, or update localized README variants in a GitHub-style repository.

5k tokens

How to use it

Copy the folder

Take microsoft/writing-plans from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.