agentleFS
Sign inStart free
StasPotapovStasPotapov/present/setup/SKILL.md

present-setup

Skill16 starsChanged 9 days agoMITView on GitHub

Set up the portable present pipeline: install Codex or Claude Code adapters, guide other compatible agents, and verify local resources and preview capabilities.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check doctor, repeat setup, resolve both links and validate a local deck.

    line 32
  2. Distinctive:

    Do not install software or log in as a side effect.

    line 34
  3. Distinctive:

    Verify discovery in a fresh session and perform a safe local preview.

    line 36

≈ “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

Set up present

Resolve this directory's real path; the shared root is its parent. Read ../HOST.md and the adapter for the actual session. Use python3 -B ../scripts/present.py doctor with the resolved absolute script path. Python 3.9+ is sufficient. Do not infer the active client from installed executables or run an AI CLI to discover capabilities. For another agent, keep the complete repository and read its SKILL.md and HOST.md in that session. Use its documented skill-loading procedure, if any; do not pass an unknown client to the bundled installer or invent a native installation path.

  1. Identify ownership before installing. For a standalone clone, preview setup --client codex or setup --client claude-code, then repeat with --install-skills to link both whole skill trees. Existing links to this exact root are kept; foreign files, old links and manager-owned destinations stop all writes. Preserve them and update through their owner; never force replacement. A partial link failure removes links created by this invocation.
  2. For a plugin, use its bundled main/setup skills without standalone links. For an environment manager, let it package and deliver both entries and all resources. AI Workspace is optional delivery infrastructure, never a runtime dependency.
  3. There are no independent model roles in present. Use the current session's model; do not create role settings, ask about models or change another client's settings.
  4. Probe available tools in this session: shell/files, image viewer, browser, design and preview. Read ../stages/canvas.md. Codex uses local HTML preview by default; optional Pages, Presentations and Sites have distinct contracts. Claude Code uses Claude Design only when its connector is actually available. Missing tools, auth failures, network failures and untested access are different states.
  5. Check doctor, repeat setup, resolve both links and validate a local deck. Node is needed for the validator's JS syntax checks; browser/PDF tools are separate. Do not install software or log in as a side effect. Without shell, explain that local setup/build is unavailable here; without image access, visual QA is unverified.
  6. Verify discovery in a fresh session and perform a safe local preview. Report static, fixture and live evidence separately. A written adapter does not prove a live Claude session, an authenticated connector, or hosted publication.

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.

Check your setup, free