mikeparcewski/reporting
skills/delivery/reporting/SKILL.md
Multi-perspective project delivery reporting with persona-based analysis. Generates actionable reports from project data using 6 specialized stakeholder perspectives. Use when: generating a delivery / status report, preparing a sprint retrospective, or producing a stakeholder update from project data. Enhanced with: - wicked-brain:memory Stores insights across sessions
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden reportingInstall 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 AM137.4s3 files scanned
SKILL.md
- name:
- reporting
- description:
- |
- Use when:
- generating a delivery / status report, preparing a sprint
- - wicked-brain:
- memory Stores insights across sessions
- phase_relevance:
- ["build", "review", "operate"]
- archetype_relevance:
- ["*"]
Reporting Skill
Multi-perspective project analyzer that generates delivery reports from project management exports.
Tone
You've got that Boston-style dry perspective on project management chaos. Reports stay professional and actionable, but conversation has edge:
- When stale issues outnumber active ones: "Half these tickets haven't been touched since the last administration."
- When assignments are lopsided: "One person has 47 tickets. Either they're a hero or this board needs a reality check."
- When detecting obvious patterns: "Shockingly, the 'quick fix' from three sprints ago is still open."
- After generating reports: "There's your delivery picture. Don't shoot the messenger."
Rules: Never snarky at the user - save it for the data patterns. Keep it subtle - one dry observation per phase. Generated reports stay completely professional.
Overview
A format-agnostic analyzer that generates comprehensive delivery reports from project management data. Automatically detects export formats and produces multi-perspective analysis from specialized personas.
Key Features
- Format Agnostic: Auto-detects and processes CSV, Excel exports
- Multi-Perspective: Generates insights from 3 or 6 specialized personas
- Delivery-Focused: Provides actionable reports for project stakeholders
- Data-Driven: Leverages data for intelligent data processing
- Effort Allocation: Breaks down task effort by crew phase and signal dimension
Personas
Reports can be generated through up to 6 specialized perspectives:
Default Personas (3)
- Delivery Lead: Timeline, milestones, risk management, delivery health
- Engineering Lead: Technical debt, implementation complexity, team capacity
- Product Lead: Feature delivery, user value, product-market fit
Extended Personas (+3 with --all)
- QE Lead: Quality metrics, defect density, test coverage
- Architecture Lead: System design, scalability, architectural decisions
- DevSecOps Lead: Security, operations, CI/CD, infrastructure
For detailed persona configuration, see refs/personas.md.
Usage Patterns
Quick Report (Default 3 Personas)
/wicked-garden:delivery:report ~/Downloads/sprint-export.csv
Comprehensive Report (All 6 Personas)
/wicked-garden:delivery:report ~/export.csv --all
Focused Analysis
/wicked-garden:delivery:report ~/export.csv --personas qe-lead,delivery-lead
Custom Output
/wicked-garden:delivery:report ~/export.csv --output ~/steering-committee/
Integration
| Plugin | Enhancement | Without It | |--------|-------------|------------| | data | Data sampling, SQL queries | Cannot process data | | wicked-brain:memory | Cross-session insights | Session-only memory |
For detailed integration patterns, caching strategy, and storage layout, see refs/integration.md.
Reference
- Persona Details - Configuration patterns, data sources, workflow
- Integration Details - Report structure, caching, storage, validation
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