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
- furkandvrc/conductortheir own version, first seen Nov 16, 2026
- futorio/red-greentheir own version, first seen Nov 16, 2026
- JCodesMore/jobs-for-ai-agentstheir own version, first seen Nov 16, 2026
- finolabs/finolabs-vibecodetheir own version, first seen Nov 16, 2026
- vincentventalon/claude-code-video-editing-skilltheir own version, first seen Nov 15, 2026
- vincentventalon/my-claude-skillstheir own version, first seen Nov 15, 2026
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.
juancruzmunozalbeloSkilladd-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
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-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
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 36ksame name
- garrytan/gbrain★ 33ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.4ksame name
- pytorch/executorch★ 5.2ksame name
- aws/agent-toolkit-for-aws★ 3.5ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- approval-gateSkill
- cleanupSkill
- fresh-reviewSkill
- git-styleSkill
- interviewSkill
- no-tombstonesSkill
- orchestrateSkill
- repo-styleSkill
- task-planSkill
- using-anythingSkill
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
- Distinctive: line 17
Read existing project instructions and relevant documentation when accessible.
- Distinctive: line 19
Check current capabilities and permissions only as needed to carry out setup.
- Distinctive: line 21
When files are inaccessible, use the context the user supplies and return a proposed instruction file as text.
- Distinctive: line 25
Use the interview skill if available, or ask directly.
- Distinctive: line 27
Consider the applicable choices:
- Very specific: line 40
Start from assets/agents-template.md, keeping only applicable sections.
- Distinctive: line 42
Create the root AGENTS.md when absent and local instruction edits are authorized.
- Very specific: line 44
If an anything-managed block exists, update only that block.
- Distinctive: line 45
If markers are malformed or repeated, preserve the file and clarify the intended edit instead of guessing a replacement range.
- Distinctive: line 54
Read the result back. Check that unrelated content is intact, links and documented commands have a source, and no placeholders or …
“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.
Files
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
- Identify the target directory from the request or current context. Clarify it only if ambiguous.
- 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.
- Separate observed facts, explicit preferences, and open choices. Follow existing conventions unless the user wants to change them.
- 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.mdwhen 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.
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
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.

