mikeparcewski/discovery
skills/smaht/discovery/SKILL.md
Contextual command discovery — suggests related commands based on what was just used. Discovers relationships dynamically from command/skill content, not a static map. Invoked by the Stop hook and smaht:briefing to surface one relevant suggestion.
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden discoveryInstall 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 8, 2026, 5:54 AM132.3s1 file scanned
SKILL.md
- name:
- discovery
- description:
- |
- Invoked by the Stop hook and smaht:
- briefing to surface one relevant suggestion.
- user-invocable:
- false
- phase_relevance:
- ["*"]
- archetype_relevance:
- ["*"]
Contextual Discovery
After a command or skill runs, suggest ONE related command the user hasn't tried.
How It Works
Relationships are discovered dynamically, not hardcoded:
1. Parse the just-used command/skill
Read the command's .md file from commands/{domain}/{command}.md. Look for:
- Explicit references to other commands (e.g.,
/wicked-garden:search:blast-radius) - "See also" or "Integration" sections listing related commands
- Agent dispatches (
subagent_type="wicked-garden:{domain}:{agent}") — the dispatched agent's domain has related commands - Skill references (
Skill(skill="wicked-garden:{domain}:{skill}")) — related domain commands
2. Check what the user has already used this session
Query session state for commands invoked in this session. Only suggest commands NOT already used.
3. Rank candidates
Priority:
- Commands explicitly referenced in the just-used command's
.mdfile - Commands in the same domain (sibling commands)
- Commands in domains listed in the "Integration" section
- Cross-domain commands that share the same specialist role
4. Select ONE suggestion
Pick the highest-ranked candidate the user hasn't used. Frame contextually:
- Include a specific argument from the current context when possible
- Use the user's own terms (file paths, symbol names, project descriptions)
Selection Rules
- Pick ONE suggestion (never more)
- Only suggest commands the user has NOT used in this session
- Match based on the most recent command, not full session history
- If no good match, suggest nothing — silence is better than noise
- Frame as a question: "You might find X useful" not "Run X"
- Include specific arguments from context when possible (symbol name, file path)
Common Patterns
These natural workflows emerge from command cross-references:
- Review → Impact: After reviewing code, check what depends on it
- Search → Plan: After finding a symbol, plan the change
- Brainstorm → Store: After deciding something, persist the decision
- Analyze → Synthesize: After understanding data, generate recommendations
- Scenarios → Automate: After defining test scenarios, generate test code
- Security → Compliance: After security scan, check regulatory alignment
- Incident → Store: After resolving an incident, capture learnings
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