notion-review
Skill298 starsChanged 6 months agoMITView on GitHub
Set up a Notion verification surface so YALC outputs (qualified leads, qualified visitors, qualified engagers, lead-magnet replies, content drafts) land in a kanban that you approve in Notion before downstream skills act on them. Each output type has ONE Batches kanban — every card is a batch (e.g. one lead list per campaign). Clicking a card opens its page with an INLINE Leads table rendered directly in the body (no extra click). Every item defaults to Status='Qualified'; users mark bad rows as 'Removed' (kill list), then drag the batch from To Review → Approved with one drag. Supports per-user-configured columns. Registers config in ~/.gtm-os/notion-reviews.yaml. Toggles the gate between hard (halt until approved) and autonomous (push + continue). Use when someone says 'set up a review kanban for [output type]', 'create a Notion review surface', 'I want to verify [output type] in Notion', 'let me approve qualified leads before YALC acts on them', 'reconfigure my review kanban', 'turn on Notion verification', 'trust YALC to act on engagers autonomously', or 'turn the verification gate back on for engagers'.
In this repository37 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- answer-linkedin-commentsSkill
- build-routineSkill
- campaign-dashboardSkill
- campaign-strategySkill
- claap-weekly-recapSkill
- cross-platform-schedulerSkill
- debuggerSkill
- enrich-with-signalsSkill
- find-lookalikesSkill
- fullenrich-content-engagersSkill
- fullenrich-event-attendeesSkill
- fullenrich-network-activationSkill
- fullenrich-plg-reverse-lookupSkill
- icp-importSkill
- import-leadsSkill
- integrate-with-yalcSkill
- launch-linkedin-campaignSkill
- lemlist-campaign-from-icpSkill
- list-adaptersSkill
- lost-deal-revival-agentSkill
- personalize-messageSkill
- predictleads-dashboardSkill
- predictleads-lookalikesSkill
- predictleads-signalsSkill
- prospect-discovery-pipelineSkill
- provider-builderSkill
- qualify-leadsSkill
- research-prospectSkill
- run-competitive-intelSkill
- run-doctorSkill
- scrape-post-engagersSkill
- send-cold-emailSkill
- setupSkill
- show-routineSkill
- track-campaignsSkill
- yalc-orientationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Inline child databases: When a batch is pushed, an inline items DB (is_inline: true) is created inside that batch's page — items render …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Notion Review Surface
Execute the procedure in skills/notion-review.md.
The setup is a conversational flow asked ONCE per output type (not per batch / not per campaign).
Required inputs:
- Output type — one of
qualified_lead,qualified_visitor,qualified_engager,lead_magnet_reply,content_draft. - Parent Notion page — URL, page ID, or page title.
Then configuration questions about category name, batch card columns, inline-table columns, and gate mode. Defaults shown — user can accept them and skip.
Optional flags:
--rebuild— force a new Batches DB even if one is registered. Default: reconfigure existing.--mode <hard|autonomous>— forreview:gate.
Hard rules:
- Two separate status state machines. Batch-level on the kanban:
To Review→Approved/Rejected(the gate signal). Item-level inside each card's inline table:Qualified(default) /Removed(kill list). - Inline child databases. When a batch is pushed, an inline items DB (
is_inline: true) is created inside that batch's page — items render directly in the card body, no navigation. - Per-batch items DBs. There is NO global items DB. Each batch owns its own items DB. Clean separation between campaigns; YALC reads back through
getApprovedBatches. - Load-bearing contract:
- Batches DB:
Title,Status,Batch ID,Items DB ID(the last is plumbing — stamped at push time so the read path can locate the items DB). - Per-batch items DB:
Title,Item ID,Status. These are added automatically. Everything else is user-configurable.
- Batches DB:
- Hybrid Notion access: DB + page creation, queries, updates go through
src/lib/services/notion.ts. Kanban + Gallery view creation uses the Notion MCP (mcp__claude_ai_Notion__notion-create-view) — only place in this skill where MCP is used. - Runtime config lives at
~/.gtm-os/notion-reviews.yaml. Never edit by hand — usereview:setup,review:reconfigure,review:gate,review:doctor.
This skill is tenant-agnostic. Config is global (not per-tenant) in v3.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

