mikeparcewski/issue-reporting
skills/crew/issue-reporting/SKILL.md
Automated GitHub issue detection and filing from Claude sessions. Tracks tool failures and task completion mismatches. Files issues automatically at session end or on demand via /wicked-garden:report-issue. Includes duplicate detection, codebase research, memory recall, SMART criteria validation, and advisory quality gate before filing. Use when: "file a bug", "report issue", "something went wrong", "not working as expected", "create issue", reporting UX friction, logging unmet outcomes, or investigating tool failures.
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden issue-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 AM249.0s2 files scanned
SKILL.md
- name:
- issue-reporting
- description:
- |
- end or on demand via /wicked-garden:
- report-issue. Includes duplicate detection,
- Use when:
- file a bug", "report issue", "something went wrong", "not working as expected",
- user-invocable:
- false
- phase_relevance:
- ["*"]
- archetype_relevance:
- ["*"]
Issue Reporting
Detects and reports bugs, UX friction, and unmet outcomes as structured GitHub issues. The manual filing command runs research, validates quality, and enriches the issue body before filing.
How It Works
Automatic Detection (Hooks)
Three hooks monitor your session:
| Hook | Watches For | Action |
|------|------------|--------|
| PostToolUseFailure | Same tool failing 3+ times | Queues issue for session end |
| PostToolUse(TaskUpdate) | Task completed with mismatch signals | Logs mismatch for review |
| Stop (async) | Session end | Files queued issues via gh |
Auto-filed issues include acceptance criteria, failure details, and session context.
Manual Filing
/wicked-garden:report-issue bug # File a bug report
/wicked-garden:report-issue ux-friction # Report UX friction
/wicked-garden:report-issue unmet-outcome # Log an unmet outcome
/wicked-garden:report-issue --list-unfiled # View/file unfiled issues
Manual filing runs a full research and quality pipeline before opening the issue:
- Collect fields — interactive prompts by issue type
- Research — duplicate detection, codebase search, memory recall
- SMART validation — acceptance criteria checked for specificity and measurability
- Quality gate — advisory checklist (title length, AC count, verb prefix, etc.)
- Confirm and file — preview shown before any
ghcall
Issue Types
| Type | Label | When To Use |
|------|-------|-------------|
| Bug Report | bug | Tool failures, crashes, incorrect behavior |
| UX Friction | ux | Confusing workflows, missing feedback, rough edges |
| Unmet Outcome | gap | Session goal not achieved, partial results |
Each issue type has a structured template requiring:
- Steps to reproduce or context
- Expected vs actual behavior
- Acceptance criteria for the fix (SMART-validated)
- Desired outcome
Research Pipeline (Manual Filing Only)
Before composing the issue body, the command runs three research steps:
Duplicate Detection
Searches open issues by title keywords:
gh issue list --repo {repo} --search "{keywords}" --state open --json number,title,state --limit 10
Results are appended as a Duplicate Check section. Requires gh CLI.
Codebase Research
Greps the repository for files related to the issue keywords. Up to 5 relevant files are listed in a Related Code section.
Memory Recall
Queries the wicked-brain memory store for prior context about the issue area:
Skill(skill="wicked-brain:memory", args="recall {keywords}")
Relevant memories are appended as a Prior Context section.
All three steps are additive — they never block filing.
SMART Criteria Validation
Every acceptance criterion is validated before the issue body is finalized:
| Criterion | Requirement | Bad Example | Good Example |
|-----------|-------------|-------------|--------------|
| Specific | References a concrete behavior, file, or artifact | "should work better" | "Bash hook returns {\"ok\": true}" |
| Measurable | Verifiable assertion that is clearly true or false | "no errors occur" | "passes /wg-check" |
ACs that fail are auto-improved in non-interactive mode, or surfaced with a suggested rewrite in interactive mode.
Quality Gate
An advisory checklist runs before the issue preview is shown. All items are warnings only — they never block filing:
| Check | Criteria | |-------|----------| | Title length | Under 80 characters | | Title descriptiveness | Not a single word or generic phrase | | Steps to reproduce | For bugs: at least 2 numbered steps | | Acceptance criteria count | At least 2 ACs | | AC verb prefix | Each AC starts with an action verb | | AC independence | Each AC is independently verifiable | | Duplicate check | Duplicate search completed |
Configuration
| Setting | Default | Override |
|---------|---------|---------|
| Failure threshold | 3 | WICKED_ISSUE_THRESHOLD env var |
| Max issues per session | 3 | Hardcoded in session_outcome_checker.py |
| Stale session cleanup | 48h | Hardcoded in auto_issue_reporter.py |
Prerequisites
ghCLI installed and authenticated (gh auth login)- Current directory is a GitHub repository
Without gh, the manual filing fallback uses a three-step sequence (see below).
Fallback When gh Unavailable
When gh CLI is not installed or no repo is detected, manual filing follows this order:
- Print to screen: Full issue displayed as formatted markdown (title, body, labels) — immediately visible for copy-paste
- Generate GitHub URL: Pre-filled
issues/newURL withurllib.parse.quote()-encoded title, body, and labels — open in browser to file directly - Ask to save locally: User chooses whether to cache the issue for later filing
https://github.com/{owner}/{repo}/issues/new?title={encoded}&body={encoded}&labels={encoded}
If user agrees to save: issue is queued in {storage_root}/unfiled-issues/ for later filing via --list-unfiled.
Note: Hook auto-filing paths (PostToolUseFailure, Stop hook) bypass this flow and silently cache to the unfiled queue without prompting.
References
- Issue Templates — Full body templates for all three issue types, including Research and Duplicate Check sections
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