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/wicked-garden-engineering-conformance-reviewer
development
VerifiedTrustedCommunity
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
8SKILL.mdUpdated Jul 22, 2026
mikeparcewski/wicked-garden-domain
tools
VerifiedTrustedCommunity
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-modeler
development
VerifiedTrustedCommunity
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-extractor
tools
VerifiedTrustedCommunity
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).
8SKILL.mdUpdated Jul 15, 2026