> Use with root `twg` for code search, repositories using an API/package, implementation and reverse-dependency discovery, PR status and reviews, repo contributors, hot areas, and issue-to-PR lookups.
npx skills add https://github.com/atlassian/twg-cli --skill twg-engineering-work
Use together with the root twg skill. Exact command grammar must come from
live twg help, twg help <terms>, or twg help describe <path>.
Run twg <command>. On shell command not found, use $HOME/.local/bin/twg
(macOS/Linux) / $env:LOCALAPPDATA\Programs\twg\bin\twg.exe (PowerShell), then
tell user to add that directory to PATH. Do not treat auth or command errors as
PATH failures.
Resolve the engineering anchor:
commits, branches, and repos.
inspect only the source locations needed to verify the requested relationship.
Use matching typed pull-request, Bitbucket, Jira, context, and search commands.
Provider-native PR commands apply only to their host; Bitbucket
activity/comment/task commands never apply to GitHub PRs. Use focused help for
uncertain routes/contracts.
detailed comments or diffs.
ownership and review evidence.
twg-status-rollups; this skillsupplements PR details.
and window.
references/code-search.md.notifications, use twg-status-rollups plus
../twg-status-rollups/references/personal-work-summary.md; this skill owns
PR-only work.
blocked, central, or high-impact PRs.
repos/services, owners, and recency. Do not keep searching for more PRs when
the next batch would only add more examples of the same theme.
state, CI/check or pipeline state, and last activity when the provider surface
exposes them.
person counts.
solely by PR count.
fallback using known repos, people, workitems, or search anchors. If that also
fails, answer from the successful evidence and call out the PR coverage gap.
Query reviewer-scoped open PRs. Sort by waiting time, requested action,
unresolved tasks/comments, failing CI, and project relevance. Hydrate only PRs
that need action.
Find PRs open or waiting beyond the threshold. Group by repo, author, reviewer,
and stage. Identify bottleneck patterns such as missing reviewer, unresolved
tasks, failing CI, repeated request-changes, or owner unavailable.
Use workitem context to find linked PRs, commits, branches, and repos. Fetch PRs
only if the user asks for details, status, or next action.
Query PRs/commits for the repo and time window. Group by files/areas, authors,
reviewers, and themes. For hot areas, prioritize changed area plus frequency and
ownership signals.
Resolve org/team first, then collect PRs for members or repos in the time window.
Group into themes and repos/services. Call out gaps where PR-only evidence omits
Jira, docs, planning, or customer context.
For a single person where the prompt is broader than PRs, switch to
twg-status-rollups and load
../twg-status-rollups/references/personal-work-summary.md.
For queues, include PR, repo, owner, state, reason, next action, and evidence.
For engineering reports, summarize workstreams, contributors, bottlenecks,
risks, and gaps. Include stable URLs or IDs for key artifacts.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
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.
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
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take atlassian/twg-engineering-work from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.