agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/setup-workspace/SKILL.md

setup-workspace

Skill2 starsChanged 2 months agoMITView on GitHub

Initialize this content workspace for a new author, including local preferences and optional Notion or local search setup.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 2 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

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

    Read AGENTS.md, README.md, index.md, workspace.example.json and strategy/notion-schema.md.

    line 11
  2. Very specific:

    Create or merge ignored workspace.local.json from the example.

    line 19
  3. Very specific:

    Use templates/context-interview.md to start capture.

    line 21
  4. Very specific:

    Read strategy/notion.local.json if present, otherwise inspect legacy strategy/notion.json if this installation has one.

    line 27
  5. Very specific:

    Create or map the four databases from strategy/notion-schema.md using the available connector's documented arguments.

    line 29
  6. Distinctive:

    Add supported views. If a connector cannot configure a view or native template, report that specific limitation.

    line 30
  7. Distinctive:

    After any ambiguous write result, inspect the destination before retrying.

    line 33
  8. Very specific:

    If search is requested and qmd is installed, run scripts/qmd-setup.sh, then search a known page through scripts/qmd.sh.

    line 37
  9. Very specific:

    Run scripts/wiki-lint.sh. Report what is connected, what remains blank and the next source to capture.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 7 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

Workspace: all context paths below (identity, audience, strategy, voice, brand, raw, output, index, log, workspace preferences and context scripts) resolve from context/ in the kit root. Read both the root AGENTS.md and context/AGENTS.md. Skill-local references/ and flowchart scripts/ resolve from this skill directory.

Set up the workspace

Read AGENTS.md, README.md, index.md, workspace.example.json and strategy/notion-schema.md. Resolve paths from this skill's repository, not an unrelated current directory.

Local setup

Inspect existing context and local configuration before writing. A populated workspace is not a blank template: preserve its sources, settings and user edits.

Gather the author's name, language, audience, content goal and available source material from the conversation. Ask only for missing choices that affect the requested next step. Time zone, posting days and platform are needed for a dated plan, not for an initial interview.

Create or merge ignored workspace.local.json from the example. Leave unknowns null or empty. Keep credentials in the connected tool's authentication store. This file holds preferences, not evidence for biographical or business claims. Durable decisions go in the relevant context pages with source notes.

Use templates/context-interview.md to start capture. Do not populate identity, proof, voice, hooks or topics with sample answers. No bulk rename is needed to make the generic skills work.

Optional Notion setup

Local drafting works without Notion. Set it up only when included in the request.

  1. Read strategy/notion.local.json if present, otherwise inspect legacy strategy/notion.json if this installation has one. Fetch the configured destination. For a new setup, ask for the parent page or locate the explicitly named one and verify its identity.
  2. Inspect the selected parent's children and existing schemas. Reuse an existing matching setup rather than duplicating it.
  3. Create or map the four databases from strategy/notion-schema.md using the available connector's documented arguments. Store each confirmed ID in strategy/notion.local.json as it is created. Do not copy IDs from the example, another project or an unrelated search result.
  4. Add supported views. If a connector cannot configure a view or native template, report that specific limitation. Do not claim it exists.
  5. Fetch the resulting schemas and query each data source. For a new blank setup, verify all four have no rows. Preserve existing rows when resuming a populated setup.

After any ambiguous write result, inspect the destination before retrying. A database ID and its data source ID may differ.

Optional search and handoff

If search is requested and qmd is installed, run scripts/qmd-setup.sh, then search a known page through scripts/qmd.sh. Otherwise use rg. Do not install packages or embedding models merely to initialize context.

Run scripts/wiki-lint.sh. Report what is connected, what remains blank and the next source to capture. Setup does not schedule content, publish posts or send outreach.

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.