onboard
Skill0 starsChanged 5 months agoMITView on GitHub
Codebase orientation for new contributors or fresh AI sessions. Reads CLAUDE.md, AGENTS.md files, recent git history, and audit reports to produce a quick briefing.
165 other projects use a version of this.
Adopted by
Most recently taken up by
- ggoosen/Digital-Workforcetheir own version, first seen Nov 8, 2026
- joeldevz/skynex-pitheir own version, first seen Nov 8, 2026
- eggs-gd/career-spacetheir own version, first seen Nov 8, 2026
- Codename-11/SubFrametheir own version, first seen Nov 8, 2026
- passion4it-gmbh/passionfruit-sitetheir own version, first seen Nov 5, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
Used with
Projects with it also use soak-test, team-live-ops 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.
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 9 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 9 projects that use this
HK-hubSkillteach-impeccable
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
Also in 19 projects that use this
CoralGameSkillproject-stage-detect
Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.
Also in 15 projects that use this
CoralGameSkillteam-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Also in 11 projects that use this
- +5 more from lilangMax
- +2 more from CoralGame
Other versions165 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 165
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- nateherkai/AIS-OS★ 1.4ksame name
- poshan0126/dotclaude★ 871same name
- talesofai/cohub★ 585same name
- me2resh/apexyard★ 542same name
- nexmoe/DayBee★ 424same name
- nexmoe/eve★ 424same name
155 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 repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- src/AGENTS.mdAGENTS.md
- .cursor/rules/publish-version-bump.mdcCursor rule
- .cursor/rules/release-version-sync.mdcCursor rule
- antigravitySkill
- auditSkill
- autoplanSkill
- bootstrapSkill
- brainstormSkill
- browseSkill
- ceo-reviewSkill
- clarifySkill
- cleanupSkill
- code-reviewSkill
- codexSkill
- component-inventorySkill
- context-restoreSkill
- context-saveSkill
- critiqueSkill
- cronSkill
- csoSkill
- cursorSkill
- debugSkill
- deepen-planSkill
- design-reviewSkill
- devex-reviewSkill
- document-reviewSkill
- eng-reviewSkill
- executing-plansSkill
- fableSkill
- finishSkill
- frontend-designSkill
- grill-meSkill
- grokSkill
- implementSkill
- learnSkill
- office-hoursSkill
- plan-design-reviewSkill
- planSkill
- polishSkill
- qaSkill
- reviewSkill
- shipfastSkill
- shipthoroughSkill
- simplifySkill
- specSkill
- statusSkill
- subagent-driven-developmentSkill
- test-driven-developmentSkill
- ui-auditSkill
- ui-ux-pro-maxSkill
- using-git-worktreesSkill
- verification-before-completionSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 153 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
If you are running this skill in Codex, read ../references/codex-compatibility.md before following host-specific tool instructions.
- Very specific: line 20
Before reading anything else, check if a Soloship checkpoint exists for the current branch (written by /context-save):
- Distinctive: line 29
If a checkpoint exists for this branch:
- Distinctive: line 30
Read it first — it has the most relevant context (what was being worked on, decisions made, what's left to do)
- Distinctive: line 32
Check freshness: if older than 7 days, note "Checkpoint is N days old — codebase may have changed.
- Distinctive: line 37
If no checkpoint exists, proceed directly to Step 1.
- Very specific: line 52
If docs/architecture/COMPONENTS.md exists, read it before creating or specifying UI components — reuse or extend an existing component on …
- Distinctive: line 59
If stale, note in the briefing: "Audit report is N days old (expires after M days) — findings may not reflect current codebase."
“Common” is measured: kept by at least 6 in 10 of the 153 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
Host Compatibility
If you are running this skill in Codex, read ../references/codex-compatibility.md before following host-specific tool instructions. Claude Code should continue to use the Claude-specific tools and command wrappers described here.
Soloship Onboard
Your job is to quickly orient someone (human or AI agent) to this codebase. Produce a concise briefing that answers: "What is this, how does it work, and where do I start?"
Step 0: Check for Checkpoint
Before reading anything else, check if a Soloship checkpoint exists for the
current branch (written by /context-save):
SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
CHECKPOINT_DIR="$HOME/.soloship/projects/$SLUG/checkpoints"
BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")If a checkpoint exists for this branch:
- Read it first — it has the most relevant context (what was being worked on, decisions made, what's left to do)
- Check freshness: if older than 7 days, note "Checkpoint is N days old — codebase may have changed. Cross-referencing with current git history."
- Present the checkpoint summary before the full briefing: "Last session on this branch: [summary]. Picking up from there."
If no checkpoint exists, proceed directly to Step 1.
Why: A returning user doesn't need the full tour. They need to know where they left off. The checkpoint is the fastest path to productive work.
Step 1: Read Everything Available
In parallel, read:
CLAUDE.md(if exists)AGENTS.mdat root and in subdirectories (if exist)README.md(if exists)docs/audit/AUDIT-*.md(most recent, if exists)- Recent git history:
git log --oneline -20 docs/architecture/REGISTRY.md(if exists)<!-- concern:component-reuse -->Ifdocs/architecture/COMPONENTS.mdexists, read it before creating or specifying UI components — reuse or extend an existing component on purpose match, cite what you found, and apply the rule of three (seereferences/component-inventory.md). Surface the inventory in the briefing so a new contributor learns the reusable-component surface immediately.
Freshness check: For audit reports, check frontmatter date and ttl_days.
If stale, note in the briefing: "Audit report is N days old (expires after M days) —
findings may not reflect current codebase."
Step 2: Produce the Briefing
Present a structured orientation:
What This Project Is
[One paragraph: what it does, who it's for, what stack it uses]
How It's Organized
[Directory map with one-line descriptions of each major area]
The Important Files
[5-8 files that are most critical to understand, with one-line purpose each]
How Things Connect
[3-5 key relationships: "X calls Y to do Z"]
Active Work
[From git history: what's been worked on recently, any open branches]
How to Work Here
[Quick commands (build, test, dev server), workflow process, where to put plans]
Watch Out For
[Any documented pitfalls, cross-cutting contracts, or things that commonly break. Pull from solution docs if they exist.]
Step 3: Offer Next Steps
"That's the lay of the land. What would you like to work on? I can help you
/brainstorm,/plan, or/debugfrom here."
Verification
Onboard is not complete until ALL of these are true:
- Checkpoint checked for current branch (present summary if found, note if stale)
- All available sources read (CLAUDE.md, AGENTS.md, README, audit, git log, registry)
- Briefing contains all 7 sections (What, How Organized, Important Files, Connections, Active Work, How to Work, Watch Out)
- Next steps offered
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.

