agentleFS
JipletJiplet/transformation-os/skills/utility/utility-notion-workboard/SKILL.md

notion-workboard

Skill2 starsChanged 4 months agoMITView on GitHub

Push completed work to Jacob's Notion Work Board kanban. Use this skill when Jacob says "push to notion", "add to kanban", "log in notion", "send to work board", or similar. Also triggers automatically at the end of any session where a major deliverable was produced (Word doc, Excel workbook, PPTX, SQL, analysis output) — Claude should proactively ask "Want me to log this in Notion?" before closing out. If Jacob says yes (or just "yes", "do it", "go ahead"), invoke this skill immediately.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    Before writing anything, extract the following from the current session:

    line 20
  2. Distinctive:

    Before writing to Notion, always show Jacob a confirmation card like this:

    line 43
  3. Distinctive:

    Wait for Jacob to confirm.

    line 63
  4. Very specific:

    After a successful Notion write, update context/work-board.md:

    line 81
  5. Distinctive:

    Add the new entry to the Active section (or update the existing one)

    line 82
  6. Distinctive:

    Do NOT ask if:

    line 97

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Notion Work Board — Push Skill

What this does

Creates or updates a ticket on Jacob's Notion Work Board kanban so work is tracked across sessions.

  • Notion data source ID: <data source id>
  • Work Board URL: https://www.notion.so/<page id>
  • Local cache: context/work-board.md (always keep in sync)

Step 1 — Extract from conversation

Before writing anything, extract the following from the current session:

FieldHow to determine
Task nameShort imperative phrase describing the work, e.g. "State Client Engagement Progress Docs". Prefix with the CLT-N ID if one exists in context/work-board.md.
StatusAlmost always In Progress when first created. Use Review if output was delivered and Jacob is reviewing.
ProjectMatch to the closest option: Leave Liability, Group Spend, Category Analysis, Commercial Interventions, Spend Basetable, Cost-Out Strategy, Program Tracker, Skill Architecture, Ad Hoc, Project, PMO. Use Ad Hoc for one-offs.
SectorOne of: Group / Cross-Sector, Defence & Social Infra, Telecommunications, Transport, Infrastructure Services. Default to Group / Cross-Sector if the work spans BUs or isn't tied to one. Telco-specific work (leave liability telco, telco cost-out) → Telecommunications. State-government facilities client / Defence → Defence & Social Infra.
Use CaseAnalysis, Excel Output, Word Output, PPTX, SQL, Data Request, Program, Strategy, or Other. Pick the primary output type.
Skill UsedZero or more of the registered skill names (see list below).
ObjectiveOne line: what decision or output does this enable.
OutputFile path(s) or URL(s) to the delivered output(s). One per line.
RaisedToday's date (ISO format: YYYY-MM-DD).
Last SessionToday's date.
Body / session logA brief session log: what was done, key findings, blockers, next steps. Use headers (##) for structure. Keep it scannable.

Available Skill Used options

analysis-scenario-model, analysis-data-request, analysis-commercial-insight, documents-davila7-xlsx, documents-docx, documents-pptx, program-epic-builder, program-exec-summary, program-tracker, program-steerco-pack, pipeline-working-construct, pipeline-partner-review, intelligence-market-intel, utility-draw-excalidraw-diagram, Other


Step 2 — Show confirmation card

Before writing to Notion, always show Jacob a confirmation card like this:

📋 Notion Work Board — confirm before logging

Task:       CLT-8, State Client Engagement Progress
Status:     In Progress
Project:    Project
Sector:     Defence & Social Infra
Use Case:   Word Output
Skill Used: documents-docx
Objective:  Progress update docs for 3 programme workstreams
Output:     4 - Projects/analysis/StateClient/StateClient_Engagement_Progress.docx
            4 - Projects/analysis/StateClient/Rating&Ranking/StateClient_RR_Gap_Analysis.docx
Raised:     2026-04-06
Body:       [session log with blockers and next steps]

→ OK to log? (yes / adjust fields)

Wait for Jacob to confirm. If he says adjust, apply his changes and re-show before writing.


Step 3 — Write to Notion

Use mcp__notion__notion-create-pages with:

  • parent.type: data_source_id
  • parent.data_source_id: <data_source_id>

Pass Skill Used as a JSON array string, e.g. '["documents-docx"]'.

Pass dates using the expanded property format: date:Raised:start and date:Last Session:start.


Step 4 — Update local cache

After a successful Notion write, update context/work-board.md:

  • Add the new entry to the Active section (or update the existing one)
  • Format: CLT-ID, task name, status, project, last session date, output paths, next step

This keeps the local cache in sync so future sessions don't need an API call to understand current work state.


Proactive trigger guidance

At the end of a session where you've delivered one or more output files (.docx, .xlsx, .pptx, analysis docs), if you haven't already pushed to Notion this session, ask:

"Want me to log this in Notion?"

One line, no fuss. If Jacob says yes, run the skill immediately. If he says no or ignores it, drop it.

Do NOT ask if:

  • It was a minor fix or iteration (no new output file)
  • Jacob just asked a question
  • The task is already on the board from this session

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.