Claude Skills by lttr

Review code changes from current branch, an Azure DevOps PR, a git ref, or a diff/patch file. Trigger when user says "review this", "code review", "/df:code-review", or provides a PR id/URL, ticket URL, git ref, or diff path. Read-only — never posts comments.

Use this skill when the user asks to test, verify, interact with, or automate web pages and browsers. Trigger for requests involving Chrome automation, browser testing, web scraping, screenshot capture, element selection, or checking web applications. Also trigger when user mentions "browser tools" explicitly.

Automate a real browser with the agent-browser CLI — open pages, snapshot interactive elements, click/fill by ref, extract content. Use when the user wants to browse, open a page, visit a URL, navigate a site, click or fill a form element, scrape, take a screenshot of a page, test a web app, or says "agent-browser". Works as a general-purpose browser automation tool in any repo, even ones without a local browser skill installed.

Structure AI work artifacts under .aiwork/{YYYY-MM-DD}_{slug}/ folders using the project's protocol (triage, research, spec, prd, areas, plan, review, notes, docs/). Use when the user asks to plan, make a spec, triage, research a task, write a report, code review, summarize findings, save the work, document decisions, record this, write that down, persist findings, or references any path under .aiwork/. Also use when starting a non-trivial task that needs a plan or spec before implementation,...

Review code changes from the current branch, staged changes, a git ref, or a diff/patch file. Pure git-native — no platform/PR awareness. Trigger when user says "review this", "review diff", "/aiwork:code-review-diff", or provides a git ref or diff path. Read-only — never posts comments.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (GLOSSARY.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Implement a whole spec by orchestrating subagents over its ticket graph; auto-detects the most recent task folder when no argument is given.

Implement a single ticket or a small inline change in one pass, in this session.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Turn the current conversation context into a spec. Use when user wants to create a spec (or PRD) from the current context.

Break a plan, spec, or the current conversation into vertical-slice tickets, each declaring its blocking edges.

Triage requirements, specs, or tickets. Detect input (pasted text, markdown path, tracker ticket id/URL, or empty prompt). Explore codebase + docs, score completeness, ask clarifying questions, write a markdown report. Trigger when user says "triage", "review this spec", "is this requirement complete", or provides a ticket/spec to assess.

Stop — that last message did not land. Re-pitch it in plain language.

Show recent Claude Code changes personalized to user's setup. Trigger when user asks about changelog, "what's new", "cc changelog", "claude code updates", "recent changes", or wants to know what changed in Claude Code.

Audit context files (CLAUDE.md, .claude/ tree, READMEs, docs) for broken references and verifiably stale content. Runs a deterministic offline link/path checker first, then a bounded semantic review where every finding must cite evidence. Reports findings; fixes only on request.

Write ~/.claude/custom-handoff.md to hand off current work to the next session

List all built-in Claude Code tools

List all configured hooks

Audit this repo's auto-memory files and suggest promoting each one to a more persistent layer — user or repo CLAUDE.md, an existing or new skill, a settings.json hook, or a checked-in reference doc. Use when the user says "audit memory", "promote memory", "clean up memories", "memory-promote", or wants to move ephemeral memory into durable config.

This skill should be used when creating, modifying, or managing Claude Code plugins and plugin marketplaces. Trigger when working with plugin manifests (plugin.json, marketplace.json), creating plugin directory structures, adding plugin components (commands, skills, agents, hooks), version bumping, or when discussing plugin development workflows.

Guide for creating and editing Claude Code skills. Use when user wants to create a new skill, create a new slash command (skills are the unified primitive - commands live in skills/ now), update an existing skill, or needs help structuring a SKILL.md file.

This skill should be used when working with Azure DevOps from the command line. Trigger when user mentions az devops, az repos, az pipelines, az boards, or asks about managing PRs, work items, pipelines, or repositories in Azure DevOps. Also trigger for questions about Azure DevOps CLI setup, authentication, or querying work items.

Create a feature branch from an Azure DevOps ticket. Fetches ticket title, slugifies, creates `feature/<id>-<slug>`, and optionally transitions ticket to Active. Trigger when user says "feature branch", "create branch", "/dev-azdo:feature-branch", or provides a ticket id/URL to start work on.

Generate codebase activity summaries (daily/weekly/catchup/view) from Azure DevOps PRs, work items, local git, and optionally Confluence. Trigger when user says "/dev-azdo:insights", asks "what happened", "codebase activity", "team summary", or wants a PR/commit roll-up.

Manage Azure DevOps PR comments — post new code comments, read and assess existing threads. Trigger when user says "/dev-azdo:pr-comments", asks to add/post a comment on a PR, review PR feedback, or check PR comment status. Input is PR id/URL, or empty to use current branch's PR.

Manage Azure DevOps pull requests — create, checkout, list, complete. Trigger when user says "/dev-azdo:pr <op>", "create PR", "checkout PR 123", "list PRs", "complete PR", or otherwise asks to operate on an AZDO pull request.

Add, update, or delete a comment on an Azure DevOps work item (the Discussion thread) via the dedicated Comments REST API, with Markdown rendering. Trigger when the user says "comment on ticket #N", "add a comment to the work item", "update/edit the AzDO comment", "delete a work-item comment", or asks to post discussion notes on a ticket. Use INSTEAD OF patching `System.History` whenever the comment should render as Markdown or may need to be edited or deleted later.

Create an Azure DevOps work item (Technical task / User Story / Bug …) with a Markdown description, parent link, area/iteration, and tags, in a single `az rest` call. Trigger when the user says "create azdo ticket", "new work item", "create technical task", "child ticket under #N", or asks to spawn a follow-up ticket from code or plan context. Use INSTEAD OF `az boards work-item create` whenever the description should render as Markdown (that command cannot pass the format flag).

Transition Azure DevOps work item state. Trigger when user says "ticket <id> active", "set ticket cr", "/dev-azdo:ticket", or wants to move a work item between states (active, code-review, ready, closed).

This skill should be used when working on Nuxt projects (v3+). Use it for building Vue applications with Nuxt's file-based routing, server-side rendering, and auto-import features. Trigger when working with .vue or .ts files in Nuxt directories (pages/, server/, composables/, middleware/), nuxt.config.ts, or when the project contains a nuxt dependency in package.json. Also trigger for questions about Nuxt concepts like composables, auto-imports, server routes, SSR/SSG patterns, or file-based ...

Use this skill when the user wants to convert a lecture, presentation, or talk video into text formats (transcript, outline, or article). Trigger when user mentions processing video recordings, creating transcripts from lectures, or generating articles from recorded presentations.