agentleFS
ronedgecombronedgecomb/anything/skills/setup/SKILL.md

setup

Skill1 starsChanged 9 days agoApache-2.0View on GitHub

Initialize or update a project's workflow preferences in its root AGENTS.md. Use only when the user explicitly requests setup or project instruction configuration. Never select this skill automatically for ordinary work.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 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.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read existing project instructions and relevant documentation when accessible.

    line 17
  2. Distinctive:

    Check current capabilities and permissions only as needed to carry out setup.

    line 19
  3. Distinctive:

    When files are inaccessible, use the context the user supplies and return a proposed instruction file as text.

    line 21
  4. Distinctive:

    Use the interview skill if available, or ask directly.

    line 25
  5. Distinctive:

    Consider the applicable choices:

    line 27
  6. Very specific:

    Start from assets/agents-template.md, keeping only applicable sections.

    line 40
  7. Distinctive:

    Create the root AGENTS.md when absent and local instruction edits are authorized.

    line 42
  8. Very specific:

    If an anything-managed block exists, update only that block.

    line 44
  9. Distinctive:

    If markers are malformed or repeated, preserve the file and clarify the intended edit instead of guessing a replacement range.

    line 45
  10. Distinctive:

    Read the result back. Check that unrelated content is intact, links and documented commands have a source, and no placeholders or …

    line 54

“Common” is measured: kept by at least 6 in 10 of the 168 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

Setup

Configure the project only after an explicit user request. Discussing, implementing, or reviewing this skill does not invoke it. If it was loaded without a setup request, return to the user's task without changing instructions or starting an interview.

Setup is optional. The other skills provide defaults without it.

Learn the project

  1. Identify the target directory from the request or current context. Clarify it only if ambiguous.
  2. Read existing project instructions and relevant documentation when accessible. Inspect enough of the directory to understand its purpose, organization, and known commands. The directory need not contain code or Git.
  3. Separate observed facts, explicit preferences, and open choices. Follow existing conventions unless the user wants to change them.
  4. Check current capabilities and permissions only as needed to carry out setup. Do not save today's tool availability as a permanent project constraint.

When files are inaccessible, use the context the user supplies and return a proposed instruction file as text. State what you could not inspect.

Resolve preferences

Use the interview skill if available, or ask directly. Ask only about choices whose answers materially affect future work. Use short rounds, recommendations with reasons, and more discovery when the topic needs it. Do not require answers to a fixed questionnaire.

Consider the applicable choices:

  • The project's purpose, typical tasks, and what a good result looks like.
  • How much clarification and planning different tasks need, and where durable task records belong.
  • Whether delegation is welcome, its resource limits, and any requirement for independent review.
  • Appropriate verification and documentation for the work.
  • Existing Git message, branch, and integration conventions when Git is used.
  • Actions the user wants to retain control over, within the environment's permission limits.

Use lightweight defaults where no preference is stated: proportionate planning and checks, consequential questions, useful and permitted delegation with direct execution as a fallback, concise documentation, and Conventional Commits when Git has no other convention. Existing authorization applies within its scope; new or unclear scope needs clarification.

Record the result

Start from assets/agents-template.md, keeping only applicable sections. Fill or remove every placeholder. The result should be short and useful without the anything plugin installed.

  • Create the root AGENTS.md when absent and local instruction edits are authorized.
  • Preserve existing instructions, comments, and unrelated content. Reuse existing sections where sensible.
  • If an anything-managed block exists, update only that block. Otherwise add a small <!-- anything:start --> / <!-- anything:end --> block for missing preferences. Do not duplicate or contradict existing policy.
  • If markers are malformed or repeated, preserve the file and clarify the intended edit instead of guessing a replacement range.
  • Resolve material conflicts with the user; keep settled instructions while a choice remains open.
  • Record known facts and chosen preferences. Omit unverified commands, secrets, temporary permissions, absolute machine paths, and a snapshot of available workers.
  • Summarize useful behavior instead of requiring future agents to have particular sibling skills installed.

An explicit setup request can already authorize these local edits. Do not add a separate approval round unless an unresolved choice or applicable rule requires it. Setup does not authorize repository restructuring, tool installation, Git initialization, or external actions.

Verify and report

Read the result back. Check that unrelated content is intact, links and documented commands have a source, and no placeholders or conflicting rules remain. Report what changed and any unresolved choice.

Instruction-file discovery varies by host and version. Do not assume that writing AGENTS.md makes it active everywhere, or silently replace another entry point. Explain a known discovery issue and the smallest documented way to load the shared instructions. If writing is unavailable, provide the draft and clearly state that it was not saved.

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.