project-onboard
Skill0 starsChanged 5 months agoMITView on GitHub
Use when setting up a new repository or bringing an existing one up to Infinite Room Labs conventions -- routes to the template-repo cut-and-fill flow for new repos, applies the harness/toolchain delta to existing ones, and hands off to /new-goal-loop.
- Reads credentials
5 other projects use a version of this.
Adopted by
Most recently taken up by
- Zions-store/project-ledgertheir own version, first seen Oct 15, 2026
- manastalukdar/ai-devstudiotheir own version, first seen Oct 13, 2026
- bogdanmatasaru/claude-code-guidetheir own version, first seen Jun 4, 2026
- jcmissmeng/super-skillstheir own version, first seen May 31, 2026
- mkSteady/mkSkillstheir own version, first seen Jan 18, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- mkSteady/mkSkills★ 9same name
- manastalukdar/ai-devstudio★ 1same name
- bogdanmatasaru/claude-code-guide★ 0same name
- jcmissmeng/super-skills★ 0same name
- Zions-store/project-ledger★ 0same name
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 repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architectureSkill
- code-reviewSkill
- debugSkill
- dep-auditSkill
- deploy-checklistSkill
- documentationSkill
- end-agent-sessionSkill
- incident-responseSkill
- likec4-dslSkill
- load-agentSkill
- manual-testSkill
- market-scanSkill
- new-agentSkill
- new-goal-loopSkill
- nexus-microSkill
- nexusSkill
- nexus-sprintSkill
- orchestration-cost-policySkill
- persona-forgeSkill
- prompt-refinerSkill
- public-readinessSkill
- release-prepSkill
- render-mermaidSkill
- secrets-syncSkill
- standupSkill
- system-designSkill
- tech-debtSkill
- testing-strategySkill
- tmux-session-captureSkill
- tsdocSkill
- web-ui-automation-componentsSkill
- web-ui-automation-surveySkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Follow the checklist in the new repo's README.md, section "Using this template": replace the six placeholders, pin the toolchain in …
- Distinctive: line 38
Add configuration the project does not need yet, install dependencies, or write a placeholder README.
“Common” is measured: kept by at least 6 in 10 of the 3 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
Project Onboard
A router, not a scaffolder. The canonical layout lives in InfiniteRoomLabs/template-repo and is tested there; this skill never re-implements it.
1. New repo
- Cut it from
InfiniteRoomLabs/template-repo("Use this template" on GitHub, orgh repo create <org>/<name> --template InfiniteRoomLabs/template-repo --private). - Follow the checklist in the new repo's
README.md, section "Using this template": replace the six placeholders, pin the toolchain inmise.toml, fill the gate steps inscripts/check.sh, describe the system indocs/architecture/model.c4,mise run arch:gen, truncateCHANGELOG.md, delete the section. mise install && mise run checkmust be green before the first push.- Run
/new-goal-loop <what you are building>.
2. Existing repo
Apply the delta by copying from a fresh clone of template-repo; do not hand-author these:
.claude/settings.json(marketplaces + default plugins +enabledMcpjsonServers) and.claude/.gitignore; then the.gitignoreallowlist lines (.claude/*,!.claude/.gitignore,!.claude/settings.json) and secret/tool wiring ignores (fnox.toml,mise.local.toml,.env*,.envrc,.worktrees/)..claudeignore(must not blanket-ignore.claude/).mise.toml(merge into an existing one: keep the repo's tools, add[tasks.check]and thearch:*tasks) andscripts/check.sh,scripts/arch-gen.sh,scripts/redaction-check.sh.docs/architecture/(config +spec.c4/model.c4/views.c4) and.mcp.json.CHANGELOG.md(Keep a Changelog,[Unreleased]on top) andLICENSEif missing.- Merge the template's
CLAUDE.mdsections (First run, Toolchain, Working conventions, Architecture, Gotchas) into the repo's own, keeping its project-specific content. Add the thinAGENTS.mdCodex pointer.
Then mise run check green, and /new-goal-loop to install the treadmill.
Do not
- Duplicate the treadmill artifacts (GOAL.md,
docs/phases/_templates/,docs/progress.md);skills/new-goal-loop/templates/is their only source. - Blanket-ignore
.claude/-- that hides load-bearing settings and hooks (reversed in infra 2026-08-27). - Add configuration the project does not need yet, install dependencies, or write a placeholder README.
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.