bmad-method 6.8.1-next.0 → 6.8.1-next.2

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-method",
-  "version": "6.8.1-next.0",
+  "version": "6.8.1-next.2",
   "description": "Breakthrough Method of Agile AI-driven Development",
   "keywords": [
     "agile",

package/src/bmm-skills/4-implementation/bmad-code-review/SKILL.md

@@ -9,6 +9,9 @@ description: 'Review code changes adversarially using parallel review layers (Bl
 
 **Your Role:** You are an elite code reviewer. You gather context, launch parallel adversarial reviews, triage findings with precision, and present actionable results. No noise, no filler.
 
+Subagents, when the capability is available, are an important part of this workflow. Use them as directed by the workflow steps.
+If you need an explicit user instruction to run them, ask once now for the whole workflow run.
+
 ## Conventions
 
 - Bare paths (e.g. `checklist.md`) resolve from the skill root.

package/src/bmm-skills/4-implementation/bmad-create-story/SKILL.md

@@ -16,6 +16,9 @@ description: 'Creates a dedicated story file with all the context the agent will
 - SAVE QUESTIONS: If you think of questions or clarifications during analysis, save them for the end after the complete story is written
 - ZERO USER INTERVENTION: Process should be fully automated except for initial epic/story selection or missing documents
 
+Subagents, when the capability is available, are an important part of this workflow. Use them as directed by the workflow steps.
+If you need an explicit user instruction to run them, ask once now for the whole workflow run.
+
 ## Conventions
 
 - Bare paths (e.g. `discover-inputs.md`) resolve from the skill root.

package/src/bmm-skills/4-implementation/bmad-quick-dev/SKILL.md

@@ -9,6 +9,9 @@ description: 'Implements any user intent, requirement, story, bug fix or change
 
 **CRITICAL:** If a step says "read fully and follow step-XX", you read and follow step-XX. No exceptions.
 
+Subagents, when the capability is available, are an important part of this workflow. Use them as directed by the workflow steps.
+If you need an explicit user instruction to run them, ask once now for the whole workflow run.
+
 ## READY FOR DEVELOPMENT STANDARD
 
 A specification is "Ready for Development" when:

package/src/core-skills/bmad-brainstorming/SKILL.md

@@ -1,6 +1,82 @@
 ---
 name: bmad-brainstorming
-description: 'Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.'
+description: Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'.
 ---
 
-Follow the instructions in ./workflow.md.
+# BMad Brainstorming
+
+## Overview
+
+You are a creative brainstorming coach. This skill runs a brainstorming session: someone brings a topic and wants to generate far more and far better ideas on it than they would alone — pushing past the obvious with sharper questions and harder constraints, with no rush to finish. The best sessions end with the user surprised by what came out.
+
+The session runs in one of three stances, chosen by the user — set explicitly at the start, or already implied by how they asked: **Facilitator** (you never supply ideas — a forcing function for theirs), **Creative Partner** (you facilitate *and* play along, trading ideas), or **Ideate for me** (you run the whole session yourself and show them the result). The chosen stance holds for the whole run.
+
+## Conventions
+
+- Bare paths (e.g. `references/headless.md`) resolve from `{skill-root}` (where `customize.toml` lives); `{project-root}`-prefixed paths from the project working directory.
+- `{workflow.<name>}` resolves to fields in the merged `customize.toml` `[workflow]` table.
+
+## On Activation
+
+1. Resolve customization: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, use a subagent to read `{skill-root}/customize.toml` directly with defaults.
+2. Run each `{workflow.activation_steps_prepend}` entry. Treat each `{workflow.persistent_facts}` entry as foundational context (`file:`-prefixed entries are paths/globs under `{project-root}` — load their contents; others are facts verbatim).
+3. Load `{project-root}/_bmad/core/config.yaml` (and `config.user.yaml` if present); resolve `{user_name}`, `{communication_language}`, `{document_output_language}`, `{output_folder}`, `{project_name}`, `{date}`. Missing → neutral defaults; never block.
+4. **If launched headless** (a machine signal, not a human asking for output — `references/headless.md` lists them): load `references/headless.md` and follow it for the whole run. It is the *only* context where you generate ideas yourself; never load it otherwise.
+5. **Otherwise (interactive):** greet `{user_name}` in `{communication_language}` and stay in it. Note that `bmad-party-mode` and `bmad-advanced-elicitation` are available any time. Glob `{workflow.output_dir}/*/.memlog.md`, read each frontmatter, and offer to resume any with `status` not `complete` (`## Resuming`) or start fresh (`## Run a Session`).
+
+Run each `{workflow.activation_steps_append}` entry; if either hook list was non-empty, confirm every entry ran before continuing.
+
+## Framing — hold this the whole run
+
+These fight your defaults, in every mode; hold them deliberately. The stance you pick adds one more frame (`references/mode-*.md`) on top.
+
+- **Aim past 100 ideas; resist concluding.** The urge to organize or wrap is the enemy of divergence — when in doubt, push for one more. Land only when the user is spent or the topic is mined out.
+- **Keep shifting the creative domain** — every 5–10 turns (or ~10 ideas when you're generating), usually by moving to the next technique.
+- **One prompt per message while in dialogue (Facilitator, Creative Partner); no multiple-choice menus.** Don't stack questions into a wall or hand a menu that invites lazy picking — both pull the user out of generating. The only exceptions are the two up-front *process* choices (stance, and the technique flow): *how* to run is theirs to pick; *what* to ideate never is.
+
+**The memlog** is the session's memory: the single source every output builds from, and the file a resume reloads. Whatever isn't in it is gone. Log every idea, decision, question, and bit of user direction — anything you'd regret losing if the window closed — one line each, the gist in the user's meaning, in time order; never edit or reorder. Skip your prompts and small talk. All writes go through `scripts/memlog.py` (atomic; don't read it back mid-session — resume is the one exception):
+
+- `memlog.py init --workspace {doc_workspace} --field topic="<topic>" --field goal="<goal>" --field mode="<facilitator|partner|autonomous>"` — create it once topic, goal, and stance are known.
+- `memlog.py append --workspace {doc_workspace} --type <kind> --text "<one-line gist>"` — log one entry. `--type` ∈ `idea`/`insight`/`question`/`decision`/`direction`/`technique` (a switch: `--text "started <name>"`); omit for a plain note. Add `--by user`/`--by coach` to mark authorship — **required in Creative Partner mode** (renders `(idea by user)`); skip it otherwise.
+- `memlog.py set --workspace {doc_workspace} --key status --value complete` — flip status at wrap-up.
+
+(Each is `python3 {skill-root}/scripts/memlog.py …`.)
+
+## Run a Session
+
+Open with one compound question — **what are we brainstorming, and what's the goal or why behind it?** (plus any inputs or special requests). The why shapes technique choice and synthesis (*kids' iPhone apps to build with your own kids* vs. *to win market share* point different ways). If the kickoff already made both clear, skip the question and confirm; read anything they point you to. Derive a kebab-case `{topic_slug}` and bind `{doc_workspace} = {workflow.output_dir}/{workflow.output_folder_name}/`.
+
+Now set the **stance** and the **technique batch** in one step — the composer page does both, so make it the default.
+
+**The composer page (primary).** The file is `{skill-root}/assets/brain-selector.html`. With a customized catalog (overridden `{workflow.brain_methods}` or any `{workflow.additional_techniques}`), regenerate it first: `python3 {skill-root}/scripts/brain.py --file {workflow.brain_methods} [--extra {doc_workspace}/extra-techniques.json] html --out {doc_workspace}/brain-selector.html` (pass `--extra`, a JSON list of `{category, technique_name, description}`, when there are additional techniques; the file is then `{doc_workspace}/brain-selector.html`). Try to open it (`open` / `xdg-open` / `start`), then say, in one message: *"It should open in your browser — compose your session, click **Copy prompt**, and paste the result back. If it didn't open, open `<path>` yourself, or say 'let's do it in chat'."* You can't see their browser, so never claim it opened.
+
+Read the pasted block: the **`Facilitation mode:`** line → the stance; the **listed techniques** (full category/name/description, some tagged `(random pick)`) → run them as given, no `list`/`show` needed; **`invent N`** / **`you choose N`** → see `## Choosing Techniques`.
+
+**Or in chat.** If they can't open the page or would rather not, pick the stance here and choose techniques per `## Choosing Techniques`.
+
+Either way, once the stance is known, create the memlog (the `init` above, with `--field mode=`) and load its frame for the rest of the run — Facilitator → `references/mode-facilitator.md`, Creative Partner → `references/mode-partner.md`, Ideate for me → `references/mode-autonomous.md`. Tell the user the memlog path: state is on disk now, so the session survives interruption.
+
+## Choosing Techniques
+
+For **Facilitator** and **Creative Partner**. (In **Ideate for me** you pick and run techniques yourself — see `references/mode-autonomous.md`.)
+
+Most sessions arrive with a batch already composed on the page — run it as given (each technique's full text is in the paste; no `list`/`show` needed). Two parts of a paste delegate back to you:
+
+- **`invent N`** (Inventive Flow) — invent N brand-new techniques on the fly. A line may scope an invention (`invent 1 new technique in the spirit of <category>`, from the page's per-category invent card) — when it does, honor that category's spirit. Announce the order, log each one's name + description, and offer to save a keeper to `{workflow.additional_techniques}` at wrap-up.
+- **`you choose N`** (Facilitator Chosen) — pick N techniques fitting the goal, `{workflow.favorite_techniques}` first; confirm exact names with a scoped `python3 {skill-root}/scripts/brain.py --file {workflow.brain_methods} list --category <cat>`. Never pull the library whole into context.
+
+If they didn't use the page, load `references/in-chat-techniques.md` and pick the batch in chat (**3–4 is the sweet spot**).
+
+Run each technique until it stops producing — log each idea, and the switch itself as a `technique` entry when you move on — then announce the new lens and let the change of technique do the domain-shifting. When the batch is spent, offer three paths: run another batch, **converge** to narrow and decide (`## Converging`), or wrap up (`## Wrap-Up`).
+
+## Converging
+
+The catalog is all *divergent* — built to generate. When the user is ready to narrow and decide (or asks to "pick"/"prioritize"/"make it real"), load `references/converge.md` and follow it; it ends by handing off to `## Wrap-Up`. Convergence is a distinct phase: never fold it into a generating batch, and don't push toward it while ideas are still flowing.
+
+## Resuming
+
+Picking up an existing session instead of starting fresh: load `references/resume.md` and follow it.
+
+## Wrap-Up
+
+Load `references/finalize.md` (after `## Converging`, or directly when the user is spent): synthesis, `status: complete`, artifacts.

package/src/core-skills/bmad-brainstorming/analysis/catalog-analysis.md

@@ -0,0 +1,239 @@
+# BMad Brainstorming Catalog — Deep Analysis
+
+> Analysis of the brainstorming library (`assets/brain-methods.csv`) and the selection
+> experience (`assets/brain-selector.html`, generated by `scripts/brain.py`). Companion
+> data: `method-matrix.csv` (every method tagged on 4 axes).
+>
+> **Status (implemented, uncommitted for review):** CSV extended with `provenance` /
+> `good_for` / `audience` columns; 8 researched `classic` methods added (108 total);
+> `brain.py` now renders a "Proven & Professional" lead group, super-group ordering, a
+> "Great for" goal filter, and a per-category "Invent a … technique" card; convergence
+> shipped as `references/converge.md` (diverge → converge → finalize) and wired into
+> `SKILL.md`. Sections below are the rationale.
+
+---
+
+## 1. TL;DR
+
+The catalog is strong, distinctive, and well-built. The opportunities are not "more methods" so much as **navigation and intent**:
+
+1. **The selector sorts categories alphabetically.** There is no ordering/grouping layer, so the well-known professional methods (SCAMPER, Six Hats, Five Whys, etc.) are scattered across four categories and buried below `Absurdist` and `Biomimetic`. Enterprise users meet whimsy before they meet anything they recognize. → **Add a grouping + ordering layer; lead with a "Proven & Professional" group.**
+2. **Nothing connects the user's stated goal to technique choice.** The skill asks for the goal up front but then offers an alphabetical wall. The single highest-value addition is a **goal → technique affinity layer** so "I'm adding a feature to a brownfield app" surfaces a different short-list than "planning a sabbatical."
+3. **The catalog is 100% divergent (generative).** There is essentially no *convergence* (prioritize / cluster / decide). This is partly a sound principle and partly a real gap — see §5.
+4. **Real overlap exists**, but it's mostly "same cognitive move, different costume." Four mechanisms (perspective-shift, constraint, analogy, inversion) account for ~60 of 100 methods; sensory, questioning, systems, and time-shift are comparatively thin.
+5. **Descriptions should stay terse** — the brevity is correct. Only two targeted fixes are warranted: the `collaborative` category silently assumes multiple humans, and ~10 "vibe-only" methods lack an output anchor.
+6. **Per-category "invent on the fly" is a good idea** — but implement it as a generated synthetic card per section, not 13 near-duplicate CSV rows.
+
+---
+
+## 2. Method — how this was analyzed
+
+Each of the 100 methods was tagged on **four independent axes** (see `method-matrix.csv`). Category alone only captures *aesthetic/mechanism*; these four axes are what expose grouping, overlap, gaps, and the goal-routing opportunity.
+
+| Axis | Values | Answers |
+|---|---|---|
+| **Provenance** | `classic` · `signature` · `playful` | What goes in the enterprise "proven" group? |
+| **Mechanism** (primary + secondary) | inversion · analogy · perspective · constraint · decomposition · time-shift · systems · sensory · questioning · combination · provocation · convergence | Where is the catalog redundant vs thin? |
+| **Goal affinity** (multi) | feature · novel · personal · strategy · planning · diagnosis · unstuck | Given the user's goal, what should we recommend? |
+| **Audience** | solo · group · either | What breaks in a 1:1 user+LLM session? |
+
+---
+
+## 3. Findings
+
+### 3a. Provenance — the "proven & professional" set exists, but is scattered
+
+The methods an innovation consultant or enterprise facilitator would recognize by name are spread across `structured`, `deep`, `creative`, and `collaborative`. The **canonical core (~22)**:
+
+> SCAMPER · Six Thinking Hats · Mind Mapping · Lotus Blossom · Crazy 8s · Disney Method ·
+> Starbursting · Morphological Analysis · Five Whys · Laddering · Causal Loop Mapping ·
+> First Principles · Reverse Brainstorming · Assumption Reversal · Worst Possible Idea ·
+> Provocation (PO) · Question Storming · Brainwriting/Round Robin · Yes-And · Random Stimulation ·
+> Role Playing · Analogical Thinking
+
+A second tier is *recognizable-adjacent* (Concept Blending, Forced Relationships, Decision Tree, Solution Matrix, Failure Analysis/pre-mortem, Devil's Advocate, 1000x Budget). Everything else is `signature` (BMad-original, serious) or `playful` (the delight layer — `wild`, `absurdist`, `theatrical`, much of `quantum`/`cultural`).
+
+**Recommendation — lead with "Proven & Professional."** Three ways to implement (pick in review):
+
+- **Option A — Tag + generated lead section (recommended).** Add a `provenance` column to the CSV. `brain.py` renders a synthetic **"Proven & Professional"** section *first* (pulling all `classic`-tagged methods, cross-category), then the existing categories grouped and ordered (see §7). A method keeps its home category and also appears in the lead group. Pro: zero loss of mechanism categorization; enterprise sees credibility first. Con: those ~22 methods appear twice on the browse page (arguably fine — or filter them out of their home category).
+- **Option B — New `classic` category.** Move the ~22 into a single first category. Pro: simplest. Con: destroys the mechanism grouping (SCAMPER is *also* structured; Five Whys is *also* deep), and the category becomes a grab-bag.
+- **Option C — Two-level groups only, no provenance tag.** Reorder the 13 categories into super-groups (§7) so "serious" comes first, but don't pull classics out. Pro: cleanest data model. Con: doesn't actually cluster the *named* methods — they stay scattered within their categories.
+
+My pick: **A.** It satisfies "professional methods grouped and shown first" literally, without flattening the taxonomy that makes the rest of the catalog shine.
+
+### 3b. Mechanism — the catalog has four over-served "spines"
+
+Primary-mechanism distribution across the 100:
+
+| Mechanism | ~count | Read |
+|---|---|---|
+| **perspective-shift** | ~18 | Over-served. Role Playing, Six Hats, Persona, Alien, Ancestor Council, Inner Child, Future Self, Drunk Uncle, Golden Retriever, Infomercial… all "adopt another viewpoint," differentiated only by *who*. |
+| **constraint** | ~16 | Over-served. What If, the entire `constraint` category, 1000x, Post-Scarcity, Parallel Universe, Zombie, Quantum Tunneling, Permission Giving… all "add/remove/exaggerate a limit." |
+| **analogy / transfer** | ~12 | Healthy. Analogical, Metaphor, Cross-Pollination, Trait Transfer, Nature's Solutions, Fusion Cuisine, Proverb, Random Stimulation. |
+| **inversion** | ~11 | Healthy but clustered. Reverse, Assumption Reversal, Worst Idea, Anti-Solution, Failure Analysis, Devil's Advocate, Cursed Genie, Villain's Monologue, Trickster. |
+| **combination** | ~9 | Fine. |
+| **decomposition** | ~9 | Fine. |
+| **systems / emergence** | ~7 | Thin-ish (concentrated in `quantum`/`biomimetic`). |
+| **time-shift** | ~6 | Thin. |
+| **questioning** | ~5 | Thin. |
+| **sensory / intuitive** | ~5 | Thin (all in `introspective_delight`). |
+| **convergence** | ~1 | **Effectively absent** (only Superposition Collapse). See §5. |
+
+**Takeaway:** the redundancy is not a defect to delete — the *costume* (a villain's monologue vs. a courtroom vs. "make it worse") is exactly what makes a 30th inversion technique feel fresh to a user. But a curator should know the catalog leans hard on perspective + constraint, and that **convergence is the one genuinely empty cell.** New methods (§6) should target the thin cells, not the spines.
+
+### 3c. Goal affinity — the headline missing capability
+
+`SKILL.md` already opens with *"what are we brainstorming, and what's the goal?"* — but that goal never routes technique selection. Mapping the matrix's `goal_affinity` tags gives a ready recommendation table. This is what powers "AI picks N" intelligently and what an enterprise user wants:
+
+| Goal | Strong default techniques (lead picks **bold**) |
+|---|---|
+| **Build a feature** (greenfield/brownfield) | **First Principles**, **SCAMPER**, **Morphological Analysis**, Crazy 8s, Solution Matrix, Reverse Brainstorming, One Feature Only, Ship in 60 Minutes, Chaos Engineering, Cursed Genie (edge cases), Persona Journey, *+ new: Job to Be Done, Follow the Anomaly* |
+| **Novel concept / new product** | **Concept Blending**, **Cross-Pollination**, **Forced Relationships**, What If, Trait Transfer, Nature's Solutions, Fusion Cuisine, Emerging Tech Collision, Crank the Dial to 11, Quantum Tunneling |
+| **Personal / life decision** | **Future Self Interview**, **Values Archaeology**, **Laddering**, Six Hats, Ancestor Council, Proverb Mining, Mythic Frameworks, the `introspective_delight` set, *+ new: Build on What Works* |
+| **Strategy / positioning** | **Six Thinking Hats**, **Failure Analysis** (pre-mortem), Field Lines, Ecosystem Thinking, Utopia vs Dystopia, 1000x Budget, Disney Method, Relativity Frame Shift, Infomercial at 3AM, Predator & Prey |
+| **Concrete planning** (event/project) | **Mind Mapping**, **Lotus Blossom**, Morphological Analysis, Decision Tree, Six Hats, $0 Mandate, Constraint Roulette, Time Horizon Ladder |
+| **Root-cause / diagnosis** | **Five Whys**, **Causal Loop Mapping**, Failure Analysis, Constraint Mapping, Question Storming, Starbursting, Anti-Solution, Alien Anthropologist |
+| **Get unstuck / break fixation** | **Random Stimulation**, **Provocation**, **Worst Possible Idea**, Crank the Dial to 11, Constraint Roulette, Three Rounds of Stupid, Drunk History, most of `wild`/`absurdist`/`theatrical` |
+
+**Recommendation:** persist this as machine-readable affinity (a `goals` column on the CSV, sourced from `method-matrix.csv`), then (1) have the skill recommend a batch from the up-front goal, and (2) let the composer page filter/highlight "great for: [your goal]." This is the single change that most improves both enterprise and casual use.
+
+### 3d. Audience — the `collaborative` category quietly assumes a room of people
+
+5 of the 8 `collaborative` methods (Round Robin, Relay Race, Hot Potato, Fold the Paper, Steal & Upgrade) are written for *multiple humans passing artifacts*. In the default 1:1 user+LLM session they don't translate without the coach silently reinterpreting them. This is the one place the catalog can mislead. Options: tag `audience`, and either (a) add a one-clause solo adaptation to each, or (b) have the skill note "this one shines with a group" when picked solo. Low effort, removes the only real footgun.
+
+### 3e. Description anchoring — keep terse, fix ~12 specifically
+
+The deliberate brevity is **right** — the gist + a creative LLM beats over-specification, and it matches the catalog's house style. Do **not** bulk-expand. Two surgical passes only:
+
+1. **Group-dependent `collaborative` methods** (§3d) — add a short solo-mode clause or an audience tag.
+2. **~10 "vibe-only" methods** where the *evocation is great but the output is ambiguous*, so different LLM runs would diverge wildly: e.g. **Field Lines**, **Observer Effect**, **Guerrilla Gardening Ideas**, **Emergent Thinking**, **Entanglement Thinking**, **Elemental Forces**. A tiny "…so that ___" outcome clause anchors the deliverable without killing the brevity. Example: *Guerrilla Gardening Ideas* → add "…**so you surface where an unsanctioned, low-visibility pilot could prove the idea before anyone can veto it**."
+
+Everything crisp (Five Whys, SCAMPER, First Principles, Crazy 8s) stays untouched.
+
+---
+
+## 4. Quick wins vs structural changes
+
+| Change | Effort | Impact | Type |
+|---|---|---|---|
+| Goal→technique affinity (`goals` column + recommendation) | Med | **High** | structural |
+| "Proven & Professional" lead group + category ordering | Med | **High** (enterprise) | structural |
+| Per-category "invent in the spirit" card (§6) | Low | Med | quick win |
+| Convergence mini-set (§5) | Low–Med | Med–High | structural (philosophy) |
+| `audience` tag + collaborative fix (§3d) | Low | Med | quick win |
+| ~12 description anchors (§3e) | Low | Low–Med | quick win |
+| New gap-filling methods (§6) | Low | Med | additive |
+
+---
+
+## 5. Divergent vs convergent — the answer, and a recommendation
+
+**What it is.** Divergent = generate (quantity, novelty, breadth). Convergent = evaluate, cluster, prioritize, decide. A complete creative process needs both (cf. the Double Diamond, Osborn-Parnes CPS): diverge wide, *then* converge to a choice.
+
+**Where the catalog stands.** All 100 methods are divergent. `SKILL.md` explicitly enforces divergence ("resist concluding… the urge to organize is the enemy of divergence"), and the only convergent-flavored technique is Quantum → *Superposition Collapse*. Synthesis is deferred entirely to `references/finalize.md` at wrap-up.
+
+**Is that a mistake?** Mostly a *good instinct taken to a defensible extreme.* Separating generation from judgment is the foundational brainstorming rule — premature convergence is the #1 killer of ideas, so a divergence-pure generator is legitimate. But the consequence is that the user has **no technique to pick when they're ready to narrow** — they hit "100 ideas" and the tool's stance is "keep going," with only the wrap-up doing light synthesis. For project/feature/life-decision work especially, people *do* want to land.
+
+**Recommendation — add a small, fenced convergence set, never mixed into the divergent flow.** Keep divergence pure during generation; offer convergence only at wrap-up or on explicit request ("okay, help me narrow"). Concretely: a new `converge` category (4 methods, §6), tagged `mechanism=convergence`, surfaced by `finalize.md` / on demand — not in the default 3–4 sweet-spot batch. This completes the loop while honoring the separate-generation-from-judgment principle. **This is a philosophy decision for you to confirm** — it's the one recommendation that changes what the skill *is*, not just what's in the library.
+
+---
+
+## 6. Proposed new methods (fill the thin cells)
+
+Targeting the under-served mechanisms (§3b), the empty convergence cell (§5), and the goal gaps (§3c). CSV-style (`category, name, description`) so they can drop straight in:
+
+**Feature/product & enterprise gaps (mechanism: questioning/decomposition):**
+- `structured, Job to Be Done, "Ask what the user is really hiring this to do; brainstorm around that underlying job, not the feature you assumed"`
+- `structured, Empathy Map, "Map what the user says, thinks, does, and feels around the problem; mine each quadrant for the unmet need hiding there"`
+- `deep, Follow the Anomaly, "Start from one surprising number or outlier and ideate only from what would explain it or exploit it"`
+
+**Strengths-based (the missing positive frame — Appreciative Inquiry is a glaring classic-tier omission):**
+- `deep, Build on What Works, "Name what's already succeeding and why, then ideate how to amplify and extend it instead of fixing what's broken"`
+
+**Convergence set (new `converge` category — only if §5 is adopted):**
+- `converge, Impact Effort Triage, "Plot every idea by impact against effort; harvest the high-impact, low-effort quadrant first and quarantine the rest"`
+- `converge, Forced Ranking, "Make the ideas fight: each must beat another to survive to a ranked top-N, no ties allowed"`
+- `converge, NUF Test, "Score each idea New, Useful, Feasible 1-10; the totals expose the quiet winners and the dazzling dead-ends"`
+- `converge, Affinity Clustering, "Group the raw ideas into themes, name each cluster, then ideate fresh at the theme level"`
+
+(Optional, lower priority: `structured, Storyboarding` for sequenced/experience ideation.)
+
+---
+
+## 7. Category roster & ordering recommendations
+
+**Ordering (replace alphabetical with a deliberate progression):** add a `CATEGORY_ORDER` + `GROUP` map in `brain.py` (mirroring the existing `_HUES` map — derived for the shipped set, alphabetical fallback for custom catalogs). Proposed super-groups, in order:
+
+1. **Proven & Professional** — the `classic` lead section (§3a, Option A)
+2. **Structured & Analytical** — structured, deep
+3. **Creative & Generative** — creative, biomimetic, cultural, speculative_future, quantum
+4. **Wild & Playful** — wild, absurdist, theatrical, constraint
+5. **Introspective & Personal** — introspective_delight, collaborative
+6. **Decide & Converge** — converge *(if §5 adopted)*
+
+**Roster notes:**
+- No category should be deleted. The overlap (§3b) is intentional costume variety.
+- `quantum` and `cultural` are the most abstract/uneven — a couple of their members (Field Lines, Observer Effect) are the vaguest in the whole set; anchor per §3e rather than cut.
+- `constraint` is excellent and tight — leave as is.
+
+---
+
+## 8. Per-category "invent in the spirit of this category"
+
+You asked whether each category should also offer an on-the-fly invented technique in its own spirit. **Yes — but don't add 13 near-duplicate rows to the CSV.** The composer already has a global **Invent N** stepper, and `brain.py` already generates section markup from the catalog. So:
+
+> Have `brain.py` append **one synthetic card per category section** — a dashed "✨ Invent a *{Category}* technique" card. Selecting it emits a paste directive like `invent 1 (in the spirit of {category})`, reused by the existing Inventive-Flow plumbing in `SKILL.md` (which already handles `invent N` and offering keepers to `additional_techniques`).
+
+Benefits: CSV stays a clean library of *real* techniques; behavior is consistent everywhere; it leverages plumbing that already exists; and it gives the user the "surprise me, but on-theme" affordance per category without library bloat.
+
+---
+
+## 9. Open decisions for BMad (in priority order)
+
+1. **Goal-affinity layer** — adopt the `goals` column + recommendation routing? (Highest impact.)
+2. **Proven & Professional grouping** — Option A (tag + generated lead section, recommended), B, or C? (§3a)
+3. **Convergence** — add the fenced `converge` set, or stay divergence-pure? (§5 — philosophy decision.)
+4. **New methods** — approve the §6 set? Which ones?
+5. **Per-category invent card** — approve the generated-card approach? (§8)
+6. **Description anchoring** — approve the targeted ~12 (incl. collaborative fix), keep everything else terse? (§3e)
+7. **Category ordering / super-groups** — adopt §7?
+
+Once you mark these, the implementation is: extend the CSV schema (`provenance`, `good_for`, `audience` columns — additive, backward-compatible with `brain.py`'s `DictReader`), add the ordering/grouping + synthetic-card logic to `brain.py`, regenerate `brain-selector.html`, update the relevant `SKILL.md` / `references/*` flow, and run `scripts/tests/`.
+
+---
+
+## 10. Revised convergence architecture (per BMad direction)
+
+**Decision locked:** convergence is **not** a CSV category of selectable cards. It's a **reference phase**, mirroring `references/finalize.md`. The catalog stays a pure *divergent* library; convergence lives in `references/converge.md`.
+
+**Flow:** diverge (pick & run techniques) → **converge** (`references/converge.md`, on demand or once divergence is spent) → **finalize** (`references/finalize.md`, last). The coach already does ad-hoc convergence implicitly; this makes it an explicit, repeatable phase, and `converge.md` ends by instructing the coach to load `finalize.md` to synthesize and produce artifacts.
+
+`references/converge.md` contents — a tight set of real, established convergence moves (the coach picks what fits, never dumps a menu):
+
+- **Affinity Clustering (KJ method)** — group the raw ideas into themes, name each cluster, surface the through-line.
+- **Dot Voting / Multivoting** — heat-map the favorites; discuss why the hot spots are hot.
+- **Impact–Effort Matrix** — plot each idea on impact vs effort; harvest high-impact/low-effort first.
+- **NUF Test** — score New, Useful, Feasible (1–10 each); totals expose quiet winners and dazzling dead-ends.
+- **PMI (Plus / Minus / Interesting)** — de Bono's fast evaluator for pressure-testing a single strong candidate.
+- *(optional)* **MoSCoW** (Must/Should/Could/Won't) for product scoping; **Nominal Group Technique** when it's genuinely a group.
+
+`SKILL.md` change: at the point where a divergent batch is spent, offer "keep diverging / converge & decide / wrap up" — "converge & decide" loads `converge.md`; wrap-up still goes to `finalize.md`.
+
+## 11. Researched gap-filling additions (real, established methods)
+
+Web-researched (sources below), chosen to fill the **thin mechanism cells** (questioning, diagnosis, time-shift, empathy) — *not* the over-served spines — and all `classic`-tier, so they also strengthen the "Proven & Professional" group. CSV-style, ready to drop in:
+
+| Category | Technique | Gist (house style) | Fills |
+|---|---|---|---|
+| structured | **How Might We** | "Reframe the problem as a batch of 'How might we…' opportunity questions first, then ideate against the sharpest one" | questioning / problem-framing (design-thinking staple, currently absent) |
+| deep | **TRIZ Contradiction** | "Name the core contradiction — what only improves by making something else worse — then brainstorm ways to win both instead of trading off" | engineering/feature (no systematic technical method today) |
+| deep | **Fishbone Diagram** | "Branch the problem's spine into cause categories — people, process, tools, environment — and mine each bone for contributing causes" | diagnosis (named classic complementing Five Whys / Causal Loop) |
+| structured | **Backcasting** | "Fix the finished future in vivid detail, then work backward step by step to the one move you'd have to make first" | strategy/planning time-shift (serious counterpart to playful future methods) |
+| speculative_future | **Scenario Cross** | "Pick two high-impact uncertainties, cross them into four futures, and ideate the move that wins in every one" | strategy (2×2 scenario planning — the serious sibling of the playful speculative set) |
+| structured | **Job to Be Done** | "Ask what the user is really hiring this to do, then ideate around that underlying job, not the feature you assumed" | feature/empathy (enterprise staple) |
+| structured | **Empathy Map** | "Map what the user says, thinks, does, and feels around the problem; mine each quadrant for the unmet need" | empathy/feature |
+| deep | **Build on What Works** | "Name what's already succeeding and why, then ideate how to amplify and extend it instead of fixing what's broken" | strengths-based (Appreciative Inquiry — a glaring classic-tier omission) |
+
+Deliberately **not** added (would deepen an already over-served spine or duplicate): Synectics (≈ analogy/metaphor), SWOT (analysis, not ideation), Rolestorming (≈ Role Playing), Brainwalking/Braindumping (≈ Brainwriting), Pre-mortem (≈ Failure Analysis).
+
+**Sources:** [IxDF — essential ideation techniques](https://ixdf.org/literature/article/introduction-to-the-essential-ideation-techniques-which-are-the-heart-of-design-thinking) · [Quality Magazine — TRIZ](https://www.qualitymag.com/articles/98566-triz-the-backbone-of-innovation-and-problem-solving) · [ASQ — Fishbone/Ishikawa](https://asq.org/quality-resources/fishbone) · [Futures Platform — 2×2 scenario matrix](https://www.futuresplatform.com/blog/2x2-scenario-planning-matrix-guideline) · [NN/g — Dot Voting](https://www.nngroup.com/articles/dot-voting/) · [Quality Gurus — divergent vs convergent](https://www.qualitygurus.com/divergent-vs-convergent-thinking/)

package/src/core-skills/bmad-brainstorming/analysis/method-matrix.csv

@@ -0,0 +1,109 @@
+category,technique,provenance,mechanism_primary,mechanism_secondary,goal_affinity,audience
+collaborative,Yes And Building,classic,combination,perspective,novel|unstuck|planning,group
+collaborative,Brain Writing Round Robin,classic,combination,decomposition,novel|feature,group
+collaborative,Random Stimulation,classic,analogy,,unstuck|novel,either
+collaborative,Role Playing,classic,perspective,,strategy|personal|feature,either
+collaborative,Ideation Relay Race,playful,combination,,unstuck,group
+collaborative,Idea Hot Potato,playful,combination,,unstuck,group
+collaborative,Steal And Upgrade,signature,combination,analogy,novel|unstuck,group
+collaborative,Fold The Paper,playful,combination,,unstuck|novel,group
+creative,What If Scenarios,signature,constraint,,novel|strategy|unstuck,either
+creative,Analogical Thinking,signature,analogy,,feature|novel|diagnosis,either
+creative,First Principles Thinking,classic,decomposition,,feature|novel|diagnosis|strategy,either
+creative,Forced Relationships,signature,combination,analogy,novel|unstuck,either
+creative,Time Shifting,signature,time-shift,perspective,novel|unstuck,either
+creative,Metaphor Mapping,signature,analogy,,novel|diagnosis,either
+creative,Cross-Pollination,signature,analogy,,novel|feature|strategy,either
+creative,Concept Blending,signature,combination,,novel,either
+creative,Reverse Brainstorming,classic,inversion,,diagnosis|feature|unstuck,either
+creative,Sensory Exploration,signature,sensory,,novel|unstuck,either
+deep,Five Whys,classic,questioning,,diagnosis,either
+deep,Provocation Technique,classic,provocation,inversion,unstuck|novel,either
+deep,Assumption Reversal,classic,inversion,,novel|diagnosis|strategy,either
+deep,Question Storming,classic,questioning,,diagnosis|strategy|unstuck,either
+deep,Constraint Mapping,signature,constraint,decomposition,feature|strategy|diagnosis,either
+deep,Failure Analysis,signature,inversion,diagnosis,diagnosis|strategy|feature,either
+deep,Emergent Thinking,signature,systems,,strategy|novel,either
+deep,Causal Loop Mapping,classic,systems,,diagnosis|strategy,either
+deep,Morphological Analysis,classic,decomposition,combination,feature|novel|planning,either
+deep,Laddering,classic,questioning,decomposition,personal|strategy|diagnosis,either
+introspective_delight,Inner Child Conference,signature,perspective,sensory,personal|unstuck,solo
+introspective_delight,Shadow Work Mining,signature,sensory,,personal|diagnosis,solo
+introspective_delight,Values Archaeology,signature,questioning,,personal|strategy,solo
+introspective_delight,Future Self Interview,signature,perspective,time-shift,personal,solo
+introspective_delight,Body Wisdom Dialogue,signature,sensory,,personal,solo
+introspective_delight,Permission Giving,signature,provocation,constraint,personal|unstuck,solo
+introspective_delight,Secret Wish Confession,signature,sensory,,personal,solo
+introspective_delight,Mood Weather Report,signature,sensory,,personal|unstuck,solo
+structured,SCAMPER Method,classic,combination,decomposition,feature|novel,either
+structured,Six Thinking Hats,classic,perspective,,strategy|diagnosis|planning|personal,either
+structured,Decision Tree Mapping,signature,decomposition,,planning|strategy|diagnosis,either
+structured,Solution Matrix,signature,decomposition,,feature|planning,either
+structured,Trait Transfer,signature,analogy,,novel|feature,either
+structured,Lotus Blossom,classic,decomposition,,feature|planning|novel,either
+structured,Worst Possible Idea,classic,inversion,,unstuck|novel,either
+structured,Disney Method,classic,perspective,,feature|strategy|planning,either
+structured,Starbursting,classic,questioning,,feature|planning|diagnosis,either
+structured,Mind Mapping,classic,decomposition,,planning|novel|feature,either
+structured,Crazy 8s,classic,combination,,feature|novel|unstuck,either
+theatrical,Time Travel Talk Show,playful,perspective,time-shift,novel|personal,either
+theatrical,Alien Anthropologist,playful,perspective,,diagnosis|unstuck|strategy,either
+theatrical,Dream Fusion Laboratory,signature,constraint,time-shift,novel|unstuck,either
+theatrical,Emotion Orchestra,playful,sensory,perspective,personal|strategy,either
+theatrical,Parallel Universe Cafe,playful,constraint,,novel|unstuck,either
+theatrical,Persona Journey,signature,perspective,,feature|strategy,either
+theatrical,Devil's Advocate Courtroom,signature,inversion,perspective,strategy|diagnosis,group
+wild,Chaos Engineering,signature,inversion,constraint,feature|diagnosis|strategy,either
+wild,Guerrilla Gardening Ideas,playful,analogy,,strategy|unstuck,either
+wild,Pirate Code Brainstorm,playful,combination,analogy,novel|unstuck,either
+wild,Zombie Apocalypse Planning,playful,constraint,,feature|strategy|unstuck,either
+wild,Drunk History Retelling,playful,perspective,,unstuck|diagnosis,either
+wild,Anti-Solution,signature,inversion,,diagnosis|unstuck,either
+wild,Elemental Forces,playful,perspective,analogy,novel|unstuck,either
+biomimetic,Nature's Solutions,signature,analogy,,feature|novel,either
+biomimetic,Ecosystem Thinking,signature,systems,,strategy|diagnosis,either
+biomimetic,Evolutionary Pressure,signature,systems,,feature|novel,either
+biomimetic,Predator & Prey,signature,perspective,inversion,strategy|feature,either
+biomimetic,Metamorphosis Stages,signature,time-shift,decomposition,novel|strategy,either
+biomimetic,Swarm Logic,signature,systems,,feature|strategy,either
+quantum,Observer Effect,signature,systems,perspective,strategy|diagnosis,either
+quantum,Entanglement Thinking,signature,systems,,diagnosis|strategy,either
+quantum,Superposition Collapse,signature,convergence,decomposition,strategy|diagnosis,either
+quantum,Relativity Frame Shift,signature,perspective,,strategy|novel,either
+quantum,Field Lines,signature,systems,,strategy,either
+quantum,Quantum Tunneling,signature,constraint,,unstuck|novel,either
+cultural,Indigenous Wisdom,signature,perspective,analogy,personal|strategy|novel,either
+cultural,Fusion Cuisine,signature,combination,analogy,novel,either
+cultural,Ritual Innovation,signature,analogy,,novel|personal,either
+cultural,Mythic Frameworks,signature,analogy,perspective,strategy|personal|novel,either
+cultural,Proverb Mining,signature,analogy,,personal|strategy,either
+cultural,Ancestor Council,signature,perspective,,personal|strategy,either
+cultural,Trickster's Gambit,playful,inversion,provocation,unstuck|strategy,either
+absurdist,Villain's Monologue,playful,inversion,perspective,diagnosis|strategy|unstuck,either
+absurdist,Explain It to a Golden Retriever,playful,perspective,,unstuck|diagnosis|feature,either
+absurdist,Infomercial at 3AM,playful,perspective,,strategy|novel,either
+absurdist,Drunk Uncle at Thanksgiving,playful,perspective,,unstuck|diagnosis,either
+absurdist,Cursed Genie,playful,inversion,,diagnosis|feature,either
+absurdist,Three Rounds of Stupid,playful,provocation,,unstuck|novel,either
+constraint,Kill the Crown Jewel,signature,constraint,,feature|strategy|unstuck,either
+constraint,1000x Budget,signature,constraint,,novel|strategy,either
+constraint,Ship in 60 Minutes,signature,constraint,,feature|planning|unstuck,either
+constraint,The $0 Mandate,signature,constraint,,planning|strategy|feature,either
+constraint,One Feature Only,signature,constraint,,feature|strategy,either
+constraint,Crank the Dial to 11,signature,constraint,,novel|unstuck,either
+constraint,Constraint Roulette,signature,constraint,,unstuck|feature,either
+speculative_future,Time Horizon Ladder,signature,time-shift,,strategy|planning|novel,either
+speculative_future,Post-Scarcity Test,signature,constraint,,novel|strategy,either
+speculative_future,Utopia vs Dystopia Split-Screen,signature,perspective,inversion,strategy|diagnosis,either
+speculative_future,Sci-Fi Artifact From the Future,signature,time-shift,perspective,novel|feature,either
+speculative_future,Emerging Tech Collision,signature,combination,,novel|feature|strategy,either
+speculative_future,What-If-The-World-Changed Card Flip,signature,constraint,,novel|unstuck,either
+speculative_future,Future Anthropologist Dig,signature,time-shift,perspective,strategy|novel,either
+structured,How Might We,classic,questioning,,feature|novel|strategy|diagnosis,either
+structured,Job to Be Done,classic,perspective,questioning,feature|strategy|novel,either
+structured,Empathy Map,classic,perspective,,feature|personal,either
+structured,Backcasting,classic,time-shift,,strategy|planning|novel,either
+deep,TRIZ Contradiction,classic,inversion,decomposition,feature|novel|diagnosis,either
+deep,Fishbone Diagram,classic,decomposition,systems,diagnosis,either
+deep,Build on What Works,classic,perspective,systems,personal|strategy,either
+speculative_future,Scenario Cross,classic,constraint,systems,strategy|planning,either