setup
Skill41 starsChanged 2 months agoMITView on GitHub
Use when the user asks for /thiscode setup, step-by-step ThisCode onboarding, tmux-only Discord bot launch guidance, YOLO/safe-mode selection, or progress reporting cadence setup.
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 repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- bootstrapSkill
- codex-exec-bridgeSkill
- create-botSkill
- create-discord-botSkill
- create-slack-botSkill
- helpSkill
- initSkill
- install-hooksSkill
- meetingsSkill
- promptSkill
- self-updateSkill
- shared-memorySkill
- slack-bridgeSkill
- slack-configureSkill
- thiscode-agySkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Run thiscode init for guided setup.
- Very specific: line 22
Use tmux for Discord bot runtime windows on macOS/WSL/Linux.
- Very specific: line 28
Ask progress_report_cadence: per_task, 1m, 3m, 5m, off, or custom.
- Very specific: line 38
Read docs/RECENT-CHANGES.md and apply anything not yet reflected — it is the newest-first digest of contract/behavior changes a fresh …
- Distinctive: line 69
Do not turn a copied skill into a completed setup claim.
- Very specific: line 78
Use this skill during initial setup phase to configure ThisCode environment.
“Common” is measured: kept by at least 6 in 10 of the 170 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
ThisCode Setup Skill
Generated through the mandatory /prompt workflow:
/prompt --batch GPT-5.6 상세 ThisCode setup skill: create a step-by-step installer-facing skill that invokes thiscode init, explains tmux-only Discord connection, safe-vs-YOLO mode, and asks progress_report_cadence.Goal
Guide thiscode setup / thiscode init through a reason-first setup path.
Required Flow
- Run
thiscode initfor guided setup. - Confirm repo root and any bot working directory before generating aliases.
- Use tmux for Discord bot runtime windows on macOS/WSL/Linux. Do not use cmux
for this flow. On Windows native (PowerShell), do NOT introduce
tmux/WSL — follow
docs/10-windows-powershell-bots.md: one PowerShell window per bot, and generate a$PROFILEfunction (e.g.function mybot { $env:DISCORD_STATE_DIR=...; claude ... }) as the alias equivalent. - Present safe mode first. YOLO/danger-full-access requires explicit opt-in.
- Ask
progress_report_cadence:per_task,1m,3m,5m,off, orcustom.per_taskmeans a meaningful subtask or milestone completion, not every raw model turn boundary. - Wire hooks: run the
/thiscode:install-hooksskill (safejqmerge into~/.claude/settings.json, existing hooks preserved). This registers the SessionStart helper (injectssoul.mdpersona + working-dir memory index + the situational rules routerrules/INDEX.md) and the active-meeting Stop reread (hooks/meeting-stop-reread.sh). Confirm SessionStart and Stop hooks are registered with the install-hooks verify step. Without this, recent rule / meeting-protocol behavior does not auto-apply. - Read
docs/RECENT-CHANGES.mdand apply anything not yet reflected — it is the newest-first digest of contract/behavior changes a fresh install must adopt (e.g. the Stop-hook output contract). - Generate the shell aliases / launcher — REQUIRED, never skip silently
(2026-08-12 regression fix: real setups were observed ending without this
step; a setup with no alias is incomplete unless the user explicitly
declined, and the decline must be recorded in the completion contract
below). Then tell the user to
sourcethe generated alias script/block; only add it to a shell rc file if they explicitly want it permanent. On Windows the target is the PowerShell profile: write the function into$PROFILEand apply with. $PROFILE(if blocked by ExecutionPolicy,Set-ExecutionPolicy -Scope CurrentUser RemoteSignedonce). - Finish with
thiscode doctoror the nearest available verify command, and echo the completion contract below in the final report.
Completion Contract (yaml 규약 — 2026-08-12)
The final setup report MUST echo this block with real values. aliases may
never be empty or omitted — a silent skip reads as an incomplete setup:
setup_completion:
aliases: installed | declined(<reason>) # step 8 — REQUIRED (bot 생성 흐름은 create-bot 의 $BOT_DIR/bot.yaml 을 기준으로 삼는다)
wd_docs: created | declined(<reason>) # WD CLAUDE.md — create-bot Step 6 결과(bot.yaml wd_docs 와 동일, REQUIRED)
hooks_wired: true # step 6 — install-hooks verify passed
doctor: pass # step 9Guardrails
- Do not turn a copied skill into a completed setup claim.
- Missing decisions stop with the next command instead of guessed values.
- A setup report without the completion contract (or with
aliasesempty) is not a finished setup — go back and run the skipped step.
How to Use This Skill
Use this skill during initial setup phase to configure ThisCode environment. Handles dependency verification, environment detection, and configuration file generation for your specific OS and setup context.
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.

