Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tobihagemann/onboard
Developer onboarding guide that composes architecture mapping, tooling review, and agentic setup review with setup, troubleshooting, and next-steps agents to produce a comprehensive guide at .turbo/onboarding.md and .turbo/onboarding.html.
Passed 6 of 15 test cases with the skill, and 3 of 15 without it.
and 1 more in the full report
4 fixed5 passed either way13 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
During Step 1 of the onboarding pipeline, the Troubleshooting sub-agent encounters an unexpected script exception and fails to complete. Should the whole synthesis process abort immediately without writing files?
| Checked | Without skill | With skill |
|---|---|---|
| Proceeds with report generation using remaining sub-agent results and documents the failure in the report | Missed | Passed |
The instructions your model reads when the skill loads.
Developer onboarding pipeline. Composes $map-codebase, $review-tooling, and $review-agentic-setup with inline agents, then synthesizes everything into .turbo/onboarding.md and .turbo/onboarding.html. Analysis-only.
At the start, use update_plan to track each phase, restating any remaining steps of a parent workflow alongside them:
Issue all 6 spawn_agent calls below in one batch, then collect their results with wait_agent. Do not issue one and await its result before issuing the rest. Each sub-agent inherits the parent model. Each Composed Skills agent invokes its assigned skill by reading and following the installed skill instructions; each Inline Agent follows its exploration brief directly. Every sub-agent's prompt must direct it to treat the shared working tree and its git index as read-only and to explore by reading and reasoning, except that each Composed Skills sub-agent writes the report files its own skill defines. HEAD stays where it is: read other refs with git show <ref>:<path> rather than git checkout or git switch.
Launch one Codex sub-agent call per row. Each agent's prompt instructs it to invoke its assigned skill by reading and following the installed skill instructions.
| Skill | Onboarding role |
|---|---|
$map-codebase | Architecture: structure, stack, APIs, patterns, data flow, dependencies, testing |
$review-tooling | Development workflow: linters, formatters, pre-commit hooks, test runners, CI/CD |
$review-agentic-setup | Agentic coding: CLAUDE.md, AGENTS.md, skills, MCP servers, hooks, cross-tool compatibility |
Launch one Codex sub-agent call each with the exploration brief below.
| Role | Exploration Brief |
|---|---|
| Prerequisites and Setup | Read README.md, CONTRIBUTING.md, and package manager configs (package.json, Gemfile, Cargo.toml, go.mod, pyproject.toml, Package.swift, etc.). Extract: required language runtimes and versions, system dependencies, environment variables, database or service requirements, first-time setup steps (install, build, run, seed), and any bootstrap or setup scripts. |
| Troubleshooting | Search for troubleshooting content in README.md, TROUBLESHOOTING.md, docs/ directory, FAQ files, and GitHub Discussions/Wiki if accessible. Extract common errors, known quirks, platform-specific gotchas, and debugging tips. If no troubleshooting docs exist, report that. |
| Next Steps | Run gh issue list --state open --json number,title,url,reactionGroups,comments,labels --limit 50. Identify: (1) issues labeled good-first-issue or good first issue, (2) top 5 issues by engagement score (sum of reactions weighted 2x for thumbs-up, plus comment count). If gh is not available or not in a GitHub repo, skip and note that. |
Each agent writes its findings as structured markdown.
test cases passed, vs 3 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.