mcpbeat Sign in

Finishing A Development Branch Agent Skill

Use this when you have completed some feature implementation and have written passing tests, and you are ready to create a PR.

824 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 finishing-a-development-branch

What it tells the agent to use

found in the instruction text
Task spawns other agents

The instruction itself

as written by the author

<required>

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

  • Use the Task tool to verify tests by using the project's test suite.
# Run project's test suite
npm test / cargo test / pytest / go test ./...

If tests fail:

Tests failing (<N> failures). Must fix before creating PR:

[Show failures]

Cannot proceed until tests pass.
  • Confirm that there is some formatting/lint/typechecking in the project. If NONE of these exist, ask me if there was something that you missed.
  • Use the Task tool to run any formatters and fix issues in a subagent.
# Node.js/JavaScript/TypeScript
ls package.json 2>/dev/null && jq -r '.scripts | keys[]' package.json | grep -E 'format|lint'

# Rust
ls rustfmt.toml .rustfmt.toml 2>/dev/null

# Python
ls .flake8 pyproject.toml setup.cfg 2>/dev/null

# Go
ls .golangci.yml .golangci.yaml 2>/dev/null
  • Use the Task tool to run any linters and fix issues in a subagent.
# Node.js - check package.json scripts
npm run lint  # or: npm run lint:fix, npm run eslint

# Rust
cargo clippy --fix --allow-dirty --allow-staged

# Python
ruff check --fix .
# or: flake8 ., pylint .

# Go
golangci-lint run --fix
  • Use the Task tool to run type checking and fix issues in a subagent.
  • Use the nori-code-reviewer subagent to do a self review. You do *NOT* have to follow the subagent's suggestions. This is merely a way to get a fresh pair of eyes on the code.
  • Run the test-scenario-hygiene skill in a subagent to do test review. You do *NOT* have to follow the subagent's suggestions. This is merely a way to get a fresh pair of eyes on the code.
  • Confirm that you are not on the main branch. If you are, ask me before proceeding. NEVER push to main without permission.
  • Push and create a PR.
# Push branch
git push -u origin <feature-branch>

# Create PR
gh pr create --title "<title>" --body "$(cat <<'EOF'
## Summary
🤖 Generated with [Nori](https://www.npmjs.com/package/nori-ai)

<2-3 bullets of what changed>

## Test Plan
- [ ] <verification steps>

Share Nori with your team: https://www.npmjs.com/package/nori-skillsets
EOF
)"

10. Merge main and resolve conflicts if necessary.

git fetch && git merge main

11. Make sure the PR branch CI succeeds.

<system-reminder> If you do not see any CI, this is likely because of merge conflicts. Go back to step 10. </system-reminder>

# Check if the PR CI succeeded
gh pr checks

# If it is still running, sleep and check again
sleep 60 && gh pr checks

If CI did not pass, examine why and fix the issue.

  • Make changes as needed, push a new commit, and repeat the process.

<system-reminder> It is *critical* that you fix any ci issues, EVEN IF YOU DID NOT CAUSE THEM. </system-reminder>

12. If this was a change to a webapp, spin up the server and the ui in a demo localhost link and show me the link so that I can review the changes.

<system-reminder> If you are in a worktree, make sure you copy any gitignored env or config files that are necessary to start the server </system-reminder>

</required>

Other skills for the same job

different authors, same section of the catalogue
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
Github Release Management
by ComeOnOliver
×3

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management

10k tokens
Migrate To Shoehorn
by mxyhi
×2

Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

965 tokens
Bun Development
by ComeOnOliver
×2

Modern JavaScript/TypeScript development with Bun runtime. Covers package management, bundling, testing, and migration from Node.js. Use when working with Bun, optimizing JS/TS development speed, or migrating from Node.js to Bun.

8k tokens
Framework Migration Deps Upgrade
by ComeOnOliver
×2

You are a dependency management expert specializing in safe, incremental upgrades of project dependencies. Plan and execute dependency updates with minimal risk, proper testing, and clear migration pa

8k tokens
Debugging Strategies
by ComeOnOliver
×2

Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.

6k tokens
Backend Dev Guidelines
by ComeOnOliver
×2

Opinionated backend development standards for Node.js + Express + TypeScript microservices. Covers layered architecture, BaseController pattern, dependency injection, Prisma repositories, Zod validation, unifiedConfig, Sentry error tracking, async safety, and testing discipline.

36k tokens
Javascript Typescript Jest
by github
vendor ×1

Best practices for writing JavaScript/TypeScript tests using Jest, including mocking strategies, test structure, and common patterns.

558 tokens

How to use it

Copy the folder

Take microsoft/finishing-a-development-branch 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.