skills/smaht/intent/SKILL.md
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".
npx skillsauth add mikeparcewski/wicked-garden intentInstall 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.
Session intent is the keystone of v10's steer-not-block model. It's auto-detected from the first turn's prompt and made sticky for the rest of the session. This skill lets you (or a command on your behalf) override that auto-detection without using flags or fighting validators.
Four values, locked. To change the vocabulary, run a brainstorm — don't add ad-hoc.
| Intent | When to set | What fires |
|---|---|---|
| simple-edit | Trivial turns, status checks, continuations | Nothing — silent |
| feature | Building / fixing / refactoring code | Synthesis directive (wicked-brain pull) |
| research | Conceptual questions, "explain how", "why does" | Synthesis directive (wicked-brain pull) |
| rigor | Crew sessions, multi-phase work, audit trail required | Synthesis directive + active-chain context |
/wicked-garden:intent # show effective current value
/wicked-garden:intent rigor # set explicit override
/wicked-garden:intent simple-edit # quiet the framework
state.intent and state.intent_explicit=True in session state via scripts/_session.py::SessionState.update.<wg intent="X" t=N /> label in the next system-reminder so the model knows the user (or a command) steered the framework.# Show or set session intent. Pass nothing to display; pass a value to override.
# Heredoc is single-quoted (<<'PY') so the shell does NOT expand $variables
# inside the Python source — the script reads CLAUDE_PLUGIN_ROOT via
# os.environ instead, which is inherited by the subprocess.
ARG="${1:-}"
sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" - "$ARG" <<'PY'
import os
import sys
plugin_root = os.environ.get("CLAUDE_PLUGIN_ROOT")
if not plugin_root:
print("error: CLAUDE_PLUGIN_ROOT not set", file=sys.stderr)
sys.exit(1)
sys.path.insert(0, os.path.join(plugin_root, "scripts"))
from _session import SessionState
VALID = ("simple-edit", "feature", "rigor", "research")
arg = (sys.argv[1] if len(sys.argv) > 1 else "").strip()
state = SessionState.load()
if not arg:
eff = state.intent or "(not set; auto-detect runs on next turn)"
src = "explicit" if state.intent_explicit else "auto-detected" if state.intent else "n/a"
print(f"intent: {eff} ({src})")
sys.exit(0)
if arg not in VALID:
print(f"error: '{arg}' not in {VALID}", file=sys.stderr)
sys.exit(1)
state.update(intent=arg, intent_explicit=True)
print(f"intent set: {arg} (explicit override; sticky until session end)")
PY
crew:start could call /wicked-garden:intent rigor to ensure the rigor directive fires from turn 1, even if the user's first prompt was short.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
Git worktree hygiene — when to create, how to clean up, and what fails silently. Captures three classes of bug that recur with worktree-based agent isolation: subagent dangling commits, orphan branches with unique work, and time-sensitive dangling-commit garbage collection. Includes detection commands, the salvage decision flow, and the trust-but-verify rule for subagent commit reports. Use when: a subagent reports a commit SHA, after a worktree-based agent finishes, cleaning up `.claude/worktrees/`, salvaging old crew worktrees, "is this branch in main?", verifying agent-claimed commits actually landed, planning multi-agent parallel work in worktrees.