SSO, RBAC & audit · Any model, your keys · No seat tax
The weekly shipping-brief runbook: window, PR-count sources, the leaderboard + streak format, the standup thread, the ledger, and Slack posting mechanics.
kortix marketplace install kortix-starter:weekly-leaderboard-skillleaderboard agent is a thin wrapper around this skill, fired by the
weekly-leaderboard cron in kortix.yaml.
since=$(date -u -d '7 days ago' +%Y-%m-%d 2>/dev/null || date -u -v-7d +%Y-%m-%d)
for repo in {{target_repos}}; do
gh pr list --repo "$repo" --state merged --search "merged:>=$since" --limit 200 \
--json number,title,author,mergedAt,labels
done | jq -s 'add | group_by(.author.login)
| map({author: .[0].author.login, count: length, prs: map({number,title,mergedAt})})'
app/dependabot, app/github-actions,
any agent-*, and any login ending in [bot]. Count them on a separate line:
"+ N bot/agent PRs (dependabot ×N, …)". Do NOT exclude a PR a human drove even
if an agent helped write it — attribute to the human who opened/merged it.# githubLogin -> Display Name
# alice-gh -> Alice
# bob-eng -> Bob
for repo in {{target_repos}}; do
gh api "repos/$repo/commits?since=${since}T00:00:00Z&per_page=100" --paginate \
--jq '.[] | {sha: .sha[0:8], author: .commit.author.name, msg: (.commit.message | split("\n")[0])}'
done
memory/weekly-digests.md — the ### PR Leaderboard and
### Streaks of the most recent entry — for last week's per-person counts
(compute +N / -N) and current streak counts.slack channels --limit 1000
slack history --channel <main-channel-id> --limit 200
slack search --query "shipped after:$since"
ENG/PRODUCT weekly — <one-line takeaway><n> PRs merged · <n> active shippers · <n> major discussions• *Area:* outcome → why it mattered — *Owner(s)* (<url|#PR>)
Lead with outcomes, collapse fixups into one shipped thing, include Slack-only
events. Banned filler: "great", "big week", "kudos", "various improvements".*PR leaderboard — week of YYYY-MM-DD*
🥇 Alice ██████ 6 (+2)
🥈 Bob ████ 4 (=)
🥉 Carol ███ 3 (-1)
Dave ██ 2 (new)
+ 12 bot/agent PRs (dependabot ×8, agent ×4)
█ per PR, max 10 wide (scale past 10). Delta vs last week
(+N/-N/=, new if 0 last week). 🥇🥈🥉 for top 3. Only people with ≥1 PR.
If nobody merged any, skip this and note it in the snapshot.🔥 Alice — 8-week streak
Read/update counts from the ledger (increment shippers, reset the rest). Only
show if at least one streak ≥2.🗓 Monday async standup — reply in this thread by EOD
• What did you ship last week? (link PRs or describe)
• Top priority this week?
• Any blockers?
{{team_mentions}}
The role-to-grant policy, extra-scrutiny cases, the approval handshake, and how an applied grant gets logged.
Get a complete picture of any company or person before outreach. This skill always works with web search, and gets significantly better with enrichment and CRM data.
Daily runbook for budget pacing, CPA/ROAS drift, underperformer detection, and anomaly flags across Google Ads and Meta Ads, plus how to rank and word optimization recommendations.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Extract-and-match runbook for incoming vendor invoices: line-item extraction, PO/prior-invoice matching, duplicate + overcharge detection, and the ledger + approval hand-off.
Search, dedupe against the seen-mentions ledger, classify sentiment and notability, and post a digest with suggested response drafts — the daily brand-monitor runbook.