code/get-up-to-speed/SKILL.md
Reviews the latest git history, branch state, Linear ticket, and open work to build a concise situational summary. Use when picking up work after another agent, resuming a session, or onboarding to a branch mid-flight.
npx skillsauth add mostafa-drz/claude-skills get-up-to-speedInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Quickly build situational awareness for a branch/ticket so work can continue without re-reading everything.
On startup, use the Read tool to load ~/.claude/skills/get-up-to-speed/preferences.md. If it doesn't exist, use defaults.
On startup, use Bash to detect: current git branch, repo root, and git remote URL. Skip any that fail.
Check $ARGUMENTS:
help → display help then stopconfig → interactive setup then stopreset → delete preferences file, confirm, stopAIS-XXXX — if argument looks like a Linear issue ID, use it as the ticketGet Up to Speed — Situational summary of branch, git history, and ticket
Usage:
/get-up-to-speed Auto-detect ticket from branch name
/get-up-to-speed AIS-1043 Specify a ticket explicitly
/get-up-to-speed "extra context" Add context for the summary
/get-up-to-speed config Set preferences
/get-up-to-speed reset Clear preferences
/get-up-to-speed help This help
Examples:
/get-up-to-speed Summarize current branch + ticket
/get-up-to-speed AIS-810 Summarize with a specific ticket
/get-up-to-speed "focus on the settings panel changes"
Current preferences:
(read from preferences.md)
Use AskUserQuestion to collect:
.claude/plans/ for active plansSave to ~/.claude/skills/get-up-to-speed/preferences.md.
Delete ~/.claude/skills/get-up-to-speed/preferences.md and confirm: "Preferences cleared. Using defaults."
If no preferences file exists, proceed with defaults:
Use Bash to get:
git branch --show-current
git remote get-url origin
Extract the Linear ticket ID from the branch name. Pattern: */ais-{number}-* → AIS-{number}.
If $ARGUMENTS contains an AIS-XXXX pattern, use that instead.
If no ticket ID found, note it and continue without Linear data.
Run these in parallel:
git log --oneline -20 (or -30 for detailed mode)git status --shortgit diff --stat (unstaged) and git diff --cached --stat (staged)git log --oneline main..HEAD to see what's unique to this branchgit log -1 --format="%H%n%s%n%b" for the most recent commit message and bodyIf a ticket ID was found, use the Linear MCP tools:
mcp__claude_ai_Linear__get_issue with the issue IDmcp__claude_ai_Linear__list_comments for the issueExtract: title, status, description summary, assignee, project, and last 3-5 comments.
If Linear tools aren't available or the call fails, skip gracefully.
If auto-read plans is enabled, check for active plan files:
ls -t .claude/plans/*.md 2>/dev/null | head -3
If a plan file exists, read it and note its status (complete, in-progress, pending).
Read these if they exist (skip if not found):
CLAUDE.md — scan for relevant sectionsMEMORY.md — check for notes related to the current branch or ticketDon't dump the full contents — just extract what's relevant to the current branch/ticket.
If $ARGUMENTS contained extra context (not a ticket ID, not a subcommand), incorporate it as a focus area for the summary.
Output a structured summary in this format:
## Up to Speed: [branch-name]
**Ticket:** [AIS-XXXX — Title] ([Status])
**Project:** [Project name]
**Branch:** `branch-name` — [N commits ahead of main]
### What's been done
- [Bullet summary of completed work from commits + ticket description]
- [Group related commits into logical chunks, not 1:1 commit list]
### Current state
- [Uncommitted changes if any]
- [What the last few commits were doing — the trajectory]
- [Active plan file summary if exists]
### What's pending
- [Open items from ticket description/checklist]
- [Unresolved comments from Linear]
- [Any items flagged in plan as not yet started]
### Key files touched
- [List of most-changed files from git log, grouped by feature area]
### Context notes
- [Relevant memory entries]
- [Extra context from arguments]
- [Any warnings: merge conflicts, stale branch, failing checks, etc.]
Keep it concise — this is a briefing, not a novel. Focus on what someone needs to know to start working RIGHT NOW.
development
--- name: triage-board description: >- Generates a structured triage artifact from the current conversation's findings — a self-contained Desktop folder with a JSON Schema, schema-conformant report.json, prose markdown, and a single-file HTML viewer. Viewer ships with MD / CSV / JSON download buttons in the header and a per-finding "Copy as Markdown" action that produces a GitHub/Linear/Notion-ready ticket block. Stateless — triage state lives in the user's ticket system, not in the
development
Runs a beginner-mind end-to-end UI audit of any running app — local dev server, staging, production, or a specific URL. Drives Chrome through every interactive element on the target surface, collects structured findings (severity, category, where, symptom, impact, repro, triage), and hands the result off to `/triage-board` which produces the Desktop folder (schema + JSON + Markdown + single-file HTML viewer with MD/CSV/JSON exports and a per-finding Copy as Markdown button). Use when you want fresh-eyes verification of a feature, page, modal, flow, branch, or whole app — before shipping, before review, before a demo, or any time the UI deserves a careful poke.
development
Reviews the user's past Claude Code conversations from a wellbeing perspective — sentiment, tone, emotional arc, recurring patterns — and generates a supportive, science-grounded report in both Markdown and HTML. Default lookback is 48 hours across all projects. Uses recognised emotion frameworks (Plutchik, Ekman, Russell's circumplex, Pennebaker linguistic markers) and cites the science behind every observation. Learns the user's baseline tone over time so future reports flag genuine shifts, not noise. Use when the user asks for an emotional/wellbeing recap, mood check, sentiment review, or wants to understand their own ups and downs across recent work sessions.
development
--- name: workflow-advisor description: >- Analyzes recent Claude Code conversations and local Claude state (skills, settings, memory files, CLAUDE.md), researches the latest Claude Code features and best practices online, and suggests one workflow improvement at a time with reasoning and a concrete action item. Can save accepted suggestions to memory for tracking. Use when you want to discover underused Claude Code features, improve your development workflow, stay current with the lat