mikeparcewski/onboarding-guide
skills/delivery/onboarding-guide/SKILL.md
Guide new developers through team onboarding. Analyzes project health, team patterns, delivery metrics, and codebase structure to produce a personalized onboarding plan with specific first tasks, graduated complexity, and human connections. A guided walkthrough, not an agent identity. Use when: "onboard a new developer", "getting-started guide", "team orientation for new hire", "first week plan", "day-one productivity".
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden onboarding-guideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 7, 2026, 6:25 AM157.4s2 files scanned
SKILL.md
- name:
- onboarding-guide
- description:
- |
- Use when:
- onboard a new developer", "getting-started guide", "team
- phase_relevance:
- ["build", "review", "operate"]
- archetype_relevance:
- ["*"]
Onboarding Guide
Produces a personalized onboarding path for a new developer by combining team health signals, codebase structure, and sprint state into a structured week-by-week plan with concrete first tasks.
Quick Start
Invoke this skill when someone new is joining the team. Typical outputs:
- Team health snapshot (sprint state, velocity, blockers)
- Recommended first tasks (ranked by learning value + risk + impact)
- Key systems overview (what to learn in what order)
- Team patterns (branching, review, testing, communication)
- Structured weekly plan (orientation → first contribution → independence)
- People to connect with (who owns what)
First Strategy: Use wicked-* Ecosystem
- Delivery reports:
/wicked-garden:delivery:reportfor team health overview - Memory:
wicked-brain:memory(recall mode) for team conventions and past decisions - Search:
wicked-garden:searchfor codebase navigation (backed by the codebase-narrator skill for architectural overview) - Tasks: Inspect native tasks via TaskCreate/TaskUpdate with
metadata={event_type, chain_id, source_agent, phase}
Process
1. Gather Team Context
From delivery reports (if CSV/export available):
/wicked-garden:delivery:report {data_file}
From native tasks:
Read session tasks under ${CLAUDE_CONFIG_DIR}/tasks/{session_id}/ — filter
by metadata.event_type=="task" for human-visible items.
From memory:
Skill(skill="wicked-brain:memory", args="recall \"team conventions\"")
Skill(skill="wicked-brain:memory", args="recall \"architecture decisions\"")
Skill(skill="wicked-brain:memory", args="recall \"onboarding\"")
From codebase (FTS5 over indexed code, docs, wiki):
wicked-brain:search README
wicked-brain:search "TODO|FIXME|HACK"
2. Assess Team Health
- Sprint status: in flight, blocked, done
- Velocity: tasks/week, points/sprint
- Blockers: what's stuck and why
- Team capacity: who's working on what
Present as a concise snapshot, not a data dump.
3. Identify Good First Tasks
Rank candidates by:
- Learning value — introduces key systems
- Risk — low-risk preferred (isolated blast radius)
- Team impact — helpful contributions preferred
- Independence — minimal coordination needed
Sources: unassigned low-priority items, documentation gaps, small bugs, test coverage gaps.
4. Map Key Systems
Create a systems overview:
- Core services — what the project does
- Architecture — high-level component map
- Data flow — how data moves through the system
- Deployment — how code ships to production
- Dependencies — external services and integrations
Hand off to the codebase-narrator skill for the full architectural walk.
5. Explain Team Patterns
Document:
- Branching strategy (trunk-based, git-flow, etc.)
- Review process (PR template, required reviewers, merge criteria)
- Testing approach (what tests are expected per change)
- Communication (where decisions happen — Slack, meetings, docs)
- On-call / support (how incidents are handled)
6. Build the Week-by-Week Plan
See refs/plan-template.md for the full structure.
Shape:
- Week 1 — Orientation: read docs, set up env, meet people, pick first task
- Week 2 — First Contribution: complete first task with pair programming, submit first PR, attend sprint ceremonies
- Week 3 — Independence: take a medium-complexity task, review someone else's PR, identify an improvement, share feedback
Quality Standards
Good onboarding plans have:
- Concrete first tasks — not "explore the codebase" but specific tickets
- Context before code — team health and patterns before diving in
- Graduated complexity — easy → medium → harder
- Human connections — who to talk to about what
- Feedback loop — check-in points to adjust the plan
Common Pitfalls
- Information overload on day one
- Assuming knowledge of team-specific tools
- Skipping team culture and patterns
- Starting with the hardest problem
- No check-in points to course-correct
See Also
- refs/plan-template.md — full output template
skills/search/codebase-narrator— architectural walk-through/wicked-garden:delivery:report— team health input
Related Skills
mikeparcewski/skills/engineering/large-scale-migration
development
VerifiedTrustedCommunity
--- name: large-scale-migration description: How to execute a LARGE MECHANICAL change across any codebase with LEVERAGE instead of an agent-grind or hand-edits — a cross-cutting migration, refactor, rename, dialect/framework/DB port, library adoption, or bulk transform. The map→transform→gate pattern: a deterministic transform driven by a source-of-truth map, proven by a differential-equivalence gate. Use when the work is "migrate all X to Y", "rename Z everywhere", "port to a new DB/dialect/fra
8SKILL.mdUpdated Jun 3, 2026
mikeparcewski/wicked-garden:classify
testing
VerifiedTrustedCommunity
v11 LLM-based work-shape classifier. Replaces the regex archetype detector with the model's own reasoning. Reads the user's prompt, picks the right archetype(s) from the catalog, identifies signals (blast_radius, novelty, reversibility, etc.), and persists to SessionState so subsequent turns steer correctly. Use when: the prompt_submit hook emitted a `<wg classify-due />` directive, OR explicitly invoked at session start, OR when re-classifying after the user changes scope mid-session.
8SKILL.mdUpdated May 26, 2026
mikeparcewski/wicked-garden:archetype
tools
VerifiedTrustedCommunity
v11 work-shape archetype runner. When a prompt has been routed to one of the 9 archetypes (triage, explore, specify, decide, ship, review, incident, build, migrate), this skill is the entry point. It picks the right per-archetype playbook from refs/ and executes the phase shape declared in `.claude-plugin/archetypes.json`. Use when: a `<wg archetype="X">` or `<wg archetypes>` system-reminder tag appears, an explicit "let's run the X archetype" request, or when one of the per-archetype slash commands resolves to this skill.
8SKILL.mdUpdated May 8, 2026
mikeparcewski/intent
development
VerifiedTrustedCommunity
Show or set the session intent variable. Intent gates how loud the framework is — simple-edit (silent), feature/research (synthesis directive), rigor (full crew context). Auto-detected on turn 1; this skill overrides explicitly. Sticky for the session. Use when: "set intent", "intent override", "/wicked-garden:intent", "make the framework quiet", "force rigor", "what's my intent".
8SKILL.mdUpdated May 6, 2026