skills/scrum/SKILL.md
Check status of all dispatched agents. Use when user says '/scrum'. Lists all wf-* tmux sessions with their status: running, done, failed, needs-input. Reads agent logs and git status.
npx skillsauth add razbakov/skills scrumInstall 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.
Check the status of all background agents dispatched via /inbox.
tmux list-sessions -F "#{session_name} #{session_created}" 2>/dev/null | grep "^wf-"
wf-* session, determine statusFor each session, check these signals in order:
a) Is the claude process still running?
tmux list-panes -t SESSION -F "#{pane_pid}" | xargs -I{} pgrep -P {} claude 2>/dev/null
b) Check agent.log for completion signals
TASK_DIR=$(find ~/Tasks -maxdepth 1 -name "*$(echo SESSION | sed 's/wf-//')*" -type d | head -1)
tail -20 ${TASK_DIR}/agent.log 2>/dev/null
Look for:
AGENT_FINISHED → agent completedEXIT_CODE=0 → DONE (success)EXIT_CODE= (non-zero) → FAILEDError:, fatal:, SIGTERM, panic) → FAILEDpermission denied, needs input, waiting for → NEEDS INPUTc) For agents without task dirs, capture tmux pane output
tmux capture-pane -t SESSION -p 2>/dev/null | tail -10
d) Check git status in worktree
cd ${TASK_DIR} && git status --short 2>/dev/null
git log --oneline main..HEAD 2>/dev/null
Go beyond raw git status — check what was actually produced:
a) For agents with commits: get commit messages
cd ${TASK_DIR} && git log --oneline main..HEAD
b) For agents that pushed branches: check for open PRs
# ALWAYS use --json url to get real PR URLs — never construct URLs from directory names
cd ~/Projects/PROJECT && gh pr list --state open --json number,title,headRefName,state,url
c) For PRs: check CI status and review state
gh pr checks PR_NUMBER --json name,state
gh pr view PR_NUMBER --json reviewDecision --jq '.reviewDecision'
d) For research/output agents: list produced files with sizes
find ${TASK_DIR} -name "*.md" -not -name "agent-prompt.md" -not -name "agent.log"
wc -l < OUTPUT_FILE
DO NOT present a flat table of all sessions. Instead, group related agents and present them with their real deliverables.
For PR-producing agents, show a PR table:
### WeDance — N PRs open, CI status, review status
| PR | Title | CI | Review |
|----|-------|----|--------|
| #23 | Add hero image to festival page | 3/3 passed | Pending |
For research/batch agents, show a summary table:
### Platform Research (campaign name) — N/N complete
| Platform | Output | Size |
|----------|--------|------|
| LinkedIn | research-post-linkedin.md | 475 lines |
For other agents, show a details table:
### Other Agents
| Session | Project | Status | Details |
|---------|---------|--------|---------|
| wf-process-telegram-inbox | ikigai | DONE | Produced inbox/2026-03-21.md |
End with a concise summary showing counts and key actions:
23 agents: 0 running, 22 done, 1 stale
7 PRs ready to review (all CI green)
11 research reports ready to commit
1 stale agent needs manual review
For any open PRs found in step 3b, check for unresolved review threads:
gh api graphql -f query='query { repository(owner: "OWNER", name: "REPO") { pullRequest(number: N) { reviewThreads(first: 50) { nodes { isResolved } } } } }' \
--jq '[.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false)] | length'
If any PRs have unresolved threads, add to recommended actions:
N PRs have unresolved review threads — run /review-all-prs to address them
Prioritized list of what to do next:
/review-all-prs to dispatch review agentsgit diff commandsIf the user says /scrum quick, skip enrichment (PRs, CI, file sizes) and just show the grouped status tables + summary.
If the user says /scrum clean, kill all DONE and STALE sessions and remove their worktrees:
# For each DONE/STALE session:
tmux kill-session -t SESSION
git -C ~/Projects/PROJECT worktree remove ~/Tasks/TASK_DIR --force
Always confirm before cleaning: "Kill N sessions and remove N worktrees?"
tools
--- name: handoff description: Get an agent past a browser/UI wall it can't (or must not) cross on its own — a login-gated dashboard, a CAPTCHA, a 2FA prompt, an API that keeps rejecting the write, or an irreversible click that policy says a human must make. This skill is an ESCALATION LADDER, not a first move: it tells you to try the automated browser surfaces FIRST (Chrome-in-Claude, computer-use, an autonomous browser sub-agent) and only fall back to the Handoff app — a wrapper browser that h
documentation
Summarize one or more YouTube videos from their links. Use this whenever the user pastes a youtube.com or youtu.be URL (or several) and wants to know what it's about — phrasings like "summarize to telegram", "tldr these videos", "what do these say", "summary of this talk", or just dropping links with no instruction at all. Fetches each video's real transcript via yt-dlp (not the page text, which never contains the transcript), cleans the captions, and writes a per-video summary. Default delivery is Telegram; honor any other surface the user names ("to my notes", "just here in chat", "email it"). Trigger even when the user only pastes bare links — bare YouTube links almost always mean "tell me what's in these".
data-ai
Daily Digest — Chief-of-Staff role consolidates the six top-managers into one Telegram message to the Commander, instead of six. Implements the protocol from agent-proactivity.md.
development
Seed a new or empty Instagram account with a 9-post grid (3×3) so the profile looks established the moment a new visitor lands. Designed for festivals, new businesses, product launches, conferences, communities — any time an empty IG profile would hurt conversion from external traffic (QR scans, flyer drops, cross-promo). Generates assets via /image-from-gemini (per content-publishing rules — never HTML), writes captions with hashtag sets, and outputs a posting order + cadence plan. Trigger generously: phrases like '9 posts for instagram', 'fill my IG', 'starter grid', 'launch grid', 'instagram seed', '9-post grid', 'IG account not to look empty', 'first instagram posts', 'feed bootstrap', '3x3 grid', 'instagram launch content'. Even if the user mentions only one piece (just the images, just the captions, just the order), use this skill — the grid only works as an integrated bundle.