agentleFS
fontezbrooksfontezbrooks/loomDaddy/skills/publish/SKILL.md

publish

Skill1 starsChanged 4 months agoMITView on GitHub

Publish an analyzed action plan to Notion (via your connected Notion MCP), create Todoist tasks for your action items, and optionally Google Drive, then mark the recording processed.

  • Reads credentials

60 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create, ingest and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    create

    Also in 4 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 6 projects that use this

  • genomewalkerSkill

    explore

    RLM-style recursive memory exploration - dynamically navigate the memory graph

    Also in 4 projects that use this

  • GoogleSkill

    translate

    Translates a common phrase into one or more languages.

    Also in 3 projects that use this

  • aakash-dharSkill

    optimize

    Analyzes code for performance issues including slow algorithms, memory leaks, unnecessary re-renders, database query problems, and resource bottlenecks. Use when the user says "this is slow", "optimize this", "performance issue", "why is this taking so long?", or "make this faster".

    Also in 3 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 49 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read artifacts/$1.plan.json.

    line 12
  2. Very specific:

    If the user named a target in this request (e.g.

    line 20
  3. Distinctive:

    Never guess. Then cache the choice:

    line 23
  4. Distinctive:

    If create-pages returned no page URL, the publish did not happen - skip this and step 5 (marking).

    line 40
  5. Distinctive:

    If it is EMPTY, offer setup once: find the "Meetings" project with the Todoist MCP find-projects tool (create it with add-projects if it …

    line 49
  6. Distinctive:

    If the user declines Todoist setup, skip this step.

    line 55
  7. Very specific:

    If the JSON contains "skip": true (tasks already recorded, or no items owned by the user), report the reason and continue to step 4.

    line 60
  8. Distinctive:

    If add-tasks returned no parent task id, do not record.

    line 70

“Common” is measured: kept by at least 6 in 10 of the 49 edited versions of this file we could read. “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

Publish the plan for recording $1. Default target is both: Notion always, Drive only when it is configured. Read --to from $ARGUMENTS.

  1. Read artifacts/$1.plan.json. If it is missing, run /loom-daddy:analyze $1 first.
  2. Notion (when target is notion or both): publish via the connected Notion MCP. No NOTION_TOKEN is used. a. Resolve the destination database. Read the cached id:
    cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/config-get.ts notion.databaseId
    • If the user named a target in this request (e.g. "to my Meeting Notes DB"), OR nothing is cached: find it with the Notion MCP notion-search (query_type internal). If exactly one clear match, use it; if several or none, show the candidates and ask the user to pick. Never guess. Then cache the choice:
      cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/config-set.ts notion.databaseId <id> --name "<name>"
    • Otherwise reuse the cached id. b. Create the page with the Notion MCP create-pages tool. Use whichever Notion MCP is connected (an interactive session exposes the Notion plugin tools; a scheduled run exposes the claude.ai Notion connector). If the database has multiple data sources, fetch it first to get the right data_source_id. Render the page body as Notion Markdown matching the built-in layout: title = recordingName; a Recorded by: <recorderName> paragraph first when the plan has a non-null recorderName; sections Summary; Decisions (each with a timestamp deep link https://www.loom.com/share/$1?t=<sourceTs>); Action Items as a table (item, owner with "(guess)" when ownerIsGuess, priority, timeframe, source link); Open Questions. c. Record the confirmed publish using the page URL the create-pages tool returned:
    cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/record-publish.ts $1 --url <pageUrl>
    If create-pages returned no page URL, the publish did not happen - skip this and step 5 (marking).
  3. Todoist (after a confirmed Notion publish): create tasks for the user's own action items via the connected Todoist MCP. a. Read the cached destination:
    cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/config-get.ts todoist.projectId
    If it is EMPTY, offer setup once: find the "Meetings" project with the Todoist MCP find-projects tool (create it with add-projects if it does not exist), confirm with the user the owner name that identifies them in transcripts, then cache:
    cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/config-set.ts todoist.projectId <id> --name "Meetings" --owner "<name>"
    If the user declines Todoist setup, skip this step. b. Build the payload:
    cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/todoist-payload.ts $1
    If the JSON contains "skip": true (tasks already recorded, or no items owned by the user), report the reason and continue to step 4. c. Create the parent task with the Todoist MCP add-tasks tool using the payload's parent (content, description) and projectId. Then create the subtasks with a second add-tasks call, each with parentId set to the parent task id the first call returned; subtasks carry content, description, priority, and dueString when present. d. Record the confirmed creation:
    cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/record-todoist.ts $1 --task-id <parentTaskId> --count <subtaskCount>
    If add-tasks returned no parent task id, do not record; report it so the user can retry. A Todoist failure never blocks step 4 or step 5.
  4. Drive (when target is drive or both): the built-in publisher also writes the markdown copy. It skips itself when Drive is not configured, so this is safe to run unconditionally:
    cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/publish.ts $1 --drive-only --commit
    (--drive-only skips the built-in Notion write; Notion is handled via MCP above. If it prints [skip] Drive not configured, that is expected when Drive is optional and unset.)
  5. On success, mark the recording processed so the background poller will not republish it:
    cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/mark.ts $1
    mark.ts refuses to mark unless the Notion publish receipt from step 2c exists (pass --force only for a deliberate Drive-only publish with no Notion target).

Report what was published and where, how many Todoist tasks were created (or why the step was skipped), and whether Drive was skipped.

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.