.claude/skills/readme-style-guide/SKILL.md
Canonical README template and validation rules for Wicked Garden marketplace plugins. Use when: "write a README", "plugin README template", "README structure", "marketplace README", "README style guide", "validate README"
npx skillsauth add mikeparcewski/wicked-garden readme-style-guideInstall 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.
Standard structure, tone, and content rules for Wicked Garden plugin READMEs.
Every plugin README follows this structure. Sections marked CONDITIONAL include their trigger rule.
1. # wicked-garden ← h1 + tagline (REQUIRED)
2. ## {Lifecycle/Value Section} ← CONDITIONAL: value invisible in single command
3. ## Quick Start ← REQUIRED: 3 commands max
4. ## {Core Workflows} ← REQUIRED: 2-3 real scenarios with output
5. ## Commands ← REQUIRED: reference table
6. ## When to Use What ← CONDITIONAL: 3+ commands with overlapping scope
7. ## How It Works ← CONDITIONAL: mechanism is part of value prop
8. ## Agents / Skills ← REQUIRED if plugin has agents or skills
9. ## Data API ← CONDITIONAL: plugin exposes CP data sources
10. ## Integration ← REQUIRED: 3-column table
11. ## License ← REQUIRED
The first line after the h1 heading is the tagline. It must:
GOOD: "Structural code intelligence across 73 languages — trace a JSP field to its database column."
BAD: "A code search plugin for Claude Code."
GOOD: "Cross-session memory with signal-based recall and automatic decay."
BAD: "A memory management plugin."
Exactly 3 commands, labeled:
No prose explanations in Quick Start. That goes in Workflows or How It Works.
Appears BEFORE the Commands reference table. Workflows persuade; Commands reference.
Each workflow: heading + code block (3-5 commands) + optional expected output block. Show real output when possible — what does the user actually see?
Three columns are mandatory. The "Without It" column converts a dependency list into a value story.
| Plugin | What It Unlocks | Without It |
|--------|----------------|------------|
| wicked-mem | Decisions persist across sessions | Brainstorming works, but insights aren't stored |
Use active voice in "What It Unlocks" to imply directionality (who calls whom).
| Section | Include When | |---------|-------------| | Lifecycle | Core value requires multiple invocations to see | | When to Use What | 3+ commands with overlapping scope | | How It Works | Internal mechanism is part of the value proposition | | Data API | Plugin exposes data via DomainStore or external integrations | | Agents & Skills | Merge tables if combined rows ≤5; split if either has 5+ |
refs/template.mdrefs/rules.mddevelopment
--- 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".