skills/daily-review-suggest-plan/SKILL.md
Read calendar, OKRs, yesterday's activity, and project list to propose today's schedule with task IDs. Part of the daily review workflow.
npx skillsauth add razbakov/skills skills/daily-review-suggest-planInstall 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.
⚠️ Migration in progress (razbakov/ikigai#73): Control Center has moved from Notion to GitHub Issues + Project v2. When this skill references creating/reading/updating Notion cards or pages, translate to GitHub equivalents:
- Create card →
gh issue create --repo <project-repo> --title "<title>" --label agent:<name> --body "<S3 body>"thengh project item-add 5 --owner razbakov --url <issue-url>- Read cards →
gh issue list --repo <repo> --label agent:<name> --state open(or across repos viagh search issues "org:razbakov label:agent:<name> state:open")- Update card status → move on board:
gh project item-editwith the Status field, or close viagh issue close- Board columns: Inbox → To do → In progress → To review → Done
- Do not call any
notion-*MCP tools — the Notion MCP is disabled.
Uses task IDs from the project sync step. Reorganizes tasks by objective, adds risks/unknowns, and picks what matters today.
Invoked as part of /daily-review or independently via /daily-review-suggest-plan.
~/Projects/ikigaigog calREADME.md in ikigai workspace/daily-review-sync-projects (numbered tasks with a/b/c IDs)sessions/YYYY-MM-DD-browser.md, sessions/YYYY-MM-DD-ai-sessions.mdgog cal ls --from today --to today
Read README.md for current OKRs and focus areas.
From browser history, AI sessions, and app usage files — what had momentum?
Scan contacts/*/contact.md for deadlines or promises.
One section per objective, referencing task IDs from the project list:
## Yesterday
<2-3 sentence summary from browser + AI session + app usage files>
## Today's Calendar
<existing events>
## O1: <Objective name>
**Risks:** what could stop us from reaching the objective?
**Unknowns:** what should we figure out to avoid obstacles?
**Next Steps:**
- <id> — <project> — <task>
- <id> — <project> — <task>
## O2: <Objective name>
**Risks:** ...
**Unknowns:** ...
**Next Steps:**
- <id> — <project> — <task>
- <id> — <project> — <task>
### Proposed Schedule
| Time | Tasks |
|------|-------|
| HH:MM-HH:MM | <id>, <id> — <project> — <summary> |
| HH:MM-HH:MM | <id>, <id> — <project> — <summary> |
Format rules:
<id> — <project> — <task>Prioritization rules:
If /suggest-tasks ran before this step (e.g., as part of daily-review step 6.5), include a section:
## Agent Tasks (Suggested)
N new tasks suggested in Notion Control Center:
- <task> → <Agent> (Priority)
- <task> → <Agent> (Priority)
To approve: review in Notion → drag "Suggested" → "To do" → run `/dispatch-approved`
If suggest-tasks did not run, skip this section.
When the proposed schedule includes a lunch or dinner block, invoke /meal-suggestion to populate it with inventory-checked meal options. The meal suggestion output goes into the calendar event description when syncing.
Always check the system clock to avoid suggesting past time blocks.
If today is Saturday, remind about the weekly review + planning ritual (10:00-11:00).
Ask: "Does this plan work, or do you want to adjust?"
The full OKR view with proposed schedule, printed to chat.
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.