skills/ground/SKILL.md
Pull deeper context from brain + bus when uncertain. Use when: getting mixed signals from the codebase, about to commit to a non-obvious decision, prior decisions might exist for this exact problem, or you want to verify an assumption before action. Returns relevant brain memories, recent bus events, and linked priors ranked by relevance — not a wall of text. NOT for: routine "what does this code do" questions (use Read or Grep), broad codebase exploration (use Agent(Explore)), or fetching specific symbols (use wicked-brain:search directly).
npx skillsauth add mikeparcewski/wicked-garden groundInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are uncertain. Pull what's known into focus.
question argument (free text from the user / Claude's internal state)wicked-brain:query — conceptual grounding ("what do we know about X")wicked-brain:search — specific decisions, patterns, gotchas (top 5 results)wicked-bus:query — recent bus events matching the question (last 50, filter by
relevance to question terms)brain/memory, brain/wiki, brain/chunk, or bus/eventwicked-brain:read {path} depth=2){most relevant path}, use
wicked-brain:read {path} depth=2"When invoked with a question:
Step 1 — Decompose the question into 3–5 search terms. Extract noun phrases,
named entities, and technical terms. Example: "v8 daemon projection model" →
["daemon", "projection", "v8 architecture", "state machine"].
Step 2 — Parallel execution. Invoke all three in a single parallel batch:
# Brain conceptual query
Skill(wicked-brain:query, question="{question}", session_id="{session}")
# Brain symbol/decision search (repeat per term if ≥2 terms)
Skill(wicked-brain:search, query="{term1}", limit=5, session_id="{session}")
Skill(wicked-brain:search, query="{term2}", limit=5, session_id="{session}")
# Bus recent events
Skill(wicked-bus:query, query="{question}", limit=50)
Step 3 — Rank and dedupe. Collect all results. Score by:
Keep the top 5–10 unique signals. Drop results where two sources say the same thing — keep the higher-priority source.
Step 4 — Format output. Use this shape:
## Grounding: {question}
### What the brain knows
1. [brain/memory] {one-line relevance} — `{path}` → suggest: wicked-brain:read {path}
2. [brain/wiki] {one-line relevance} — `{path}`
3. [brain/chunk] {one-line relevance} — `{path}`
### Recent bus activity
4. [bus/event] {event_type} @ {timestamp} — {one-line relevance}
5. [bus/event] {event_type} @ {timestamp} — {one-line relevance}
### If you need more depth
`wicked-brain:read {most relevant path} depth=2`
Step 5 — If zero results from both brain and bus, say so explicitly:
"No prior decisions or recent events found for this question. Proceeding without
grounding — consider storing the decision you reach with wicked-brain:memory."
Never block progress. Ground is a focusing tool — absence of prior context is itself a useful signal.
If you reach a decision that others should know about:
wicked-brain:memory (store mode)wicked-bus:emit with the relevant event typeThe value of grounding compounds when decisions are written back.
development
--- 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
testing
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.
tools
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.
development
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".