project-onboarding
project-onboarding
When starting work on a new codebase, the agent has zero context. This leads to hallucinated conventions, ignored project patterns, and wasted turns re-explaining the stack. This skill crawls a target directory, infers everything it can automatically, and generates a structured PROJECT.md that the agent loads for all future work on that project.
When to invoke
Invoke this skill when:
- Starting work on a codebase for the first time
- The agent begins making assumption errors about the project structure
- A new team member (agent) is added to an existing project
Onboarding protocol
Step 1 — Crawl the directory Scan the project root for:
package.json,pyproject.toml,Cargo.toml,go.mod,pom.xml, etc. → infer tech stackMakefile,justfile,scripts/→ infer build/test commands.github/workflows/→ CI commands and quality gates- Test file patterns (
__tests__/,spec/,*_test.go) → testing conventions
More from archieindian/openclaw-superpowers
context-window-management
Prevents context overflow on long-running OpenClaw sessions. Use when approaching context limits.
28heartbeat-governor
Enforces per-skill execution budgets for scheduled cron skills — pauses runaway skills that exceed their token or wall-clock budget before they drain your monthly API allowance.
27using-superpowers
Bootstrap skill — teaches the agent how to find and invoke skills. Use when starting any new task or session.
23long-running-task-management
Breaks multi-hour tasks into checkpointed stages with resume capability. Use when a task is expected to take more than 30 minutes or multiple sessions.
22fact-check-before-trust
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
21persistent-memory-hygiene
Keeps OpenClaw's memory store clean, structured, and useful. Use at session end and during periodic maintenance.
20