setup
Skill1 starsChanged 3 months agoMITView on GitHub
Onboard this workflow into the project — index the flow's output locations (runtime config, house style, glossary, ADRs, plans) in the project's memory file so every agent session starts oriented. Run once per project.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 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★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame 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 repository10 other files it gives its agents.
- blueprintSkill
- codebase-designSkill
- diagnoseSkill
- grill-with-docsSkill
- improve-codebase-architectureSkill
- integrateSkill
- quickSkill
- setup-runtimeSkill
- setup-styleSkill
- tddSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
3
Distinctive
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
- Distinctive: line 15
Ask in plain text, one line answerable.
- Distinctive: line 44
Ask: "Add this index block to {memory file}?
- Distinctive: line 50
If the user has hand-written pointers to the same paths elsewhere in the file, point them out and let the user remove the duplicates — do …
“Common” is measured: kept by at least 6 in 10 of the 171 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
Register the workflow's output locations in the project's memory file. This is the only skill that ever writes to the memory file, and the only thing it writes there is one marker-wrapped index block — pointers, never content.
Rules
- Write one thing only: the
<!-- setup:index -->block. Touch nothing else in the memory file — not even to fix typos. - The index holds addresses, not content. Point at the canonical paths even when the files do not exist yet — their skills create them lazily.
- Ask in plain text, one line answerable. No checkbox tools.
- First write requires the user's explicit confirmation. If declined, do not write and do not re-ask within this run.
Steps
1. Find the memory file
CLAUDE.mdexists → that is the memory file.- Else
AGENTS.mdexists → that is the memory file. - Neither exists → the project has no injection channel. Ask: "No memory file found — create one so agent sessions start oriented?
CLAUDE.md(Claude Code) orAGENTS.md(Codex and others), or skip." If skipped, stop and report.
2. Present the draft
The block is fixed — five entries, one line each:
<!-- setup:index -->
## Workflow Outputs
- Runtime configuration (verified by /setup-runtime): docs/agents/runtime.md
- House style (recorded by /setup-style): docs/house-style.md
- Domain glossary: CONTEXT.md
- Architecture decisions: docs/adr/
- Implementation blueprints: docs/plans/
<!-- /setup:index -->In a multi-context repo, point the glossary entry at CONTEXT-MAP.md instead.
Ask: "Add this index block to {memory file}? It gives every agent session a map of the workflow's outputs."
3. Write
- Markers already present → replace the block between them (keep the markers). If the content is already identical, report "index up to date" and write nothing.
- No markers → on confirmation, append the block at the end of the file.
- If the user has hand-written pointers to the same paths elsewhere in the file, point them out and let the user remove the duplicates — do not edit those lines.
4. Handoff
Report what was written, then:
"Onboarding has two more steps: /setup-runtime verifies the dev loop and records the runtime configuration; /setup-style captures the team's coding conventions. Their outputs will already be indexed — run them when ready."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

