wizz-method 1.19.0 → 2.1.0

package/src/core-skills/wizz-brainstorming/references/headless.md

@@ -29,9 +29,9 @@ Free-form structured payload in the first message; provide what applies:
 
 ## Run
 
-1. Bind `{doc_workspace}` and create the memlog with `python3 {project-root}/_wizz/scripts/memlog.py init --workspace {doc_workspace} --field topic="<topic>" [--field goal="<goal>"]`. It remains the canonical source every artifact derives from.
-2. Run the divergent session per **The inversion**, capturing each idea with `memlog.py append --workspace {doc_workspace} --type idea --text "<idea>"` as it lands, and marking each technique switch with `memlog.py append --type technique --text "started <name>"`.
-3. Synthesize: surface the conclusions, connections, and the few directions that matter; record them with `memlog.py append --type insight`, then run `memlog.py set --workspace {doc_workspace} --key status --value complete`.
+1. Bind `{doc_workspace}` and create the memlog with `node {project-root}/_wizz/scripts/memlog.js init --workspace {doc_workspace} --field topic="<topic>" [--field goal="<goal>"]`. It remains the canonical source every artifact derives from.
+2. Run the divergent session per **The inversion**, capturing each idea with `memlog.js append --workspace {doc_workspace} --type idea --text "<idea>"` as it lands, and marking each technique switch with `memlog.js append --type technique --text "started <name>"`.
+3. Synthesize: surface the conclusions, connections, and the few directions that matter; record them with `memlog.js append --type insight`, then run `memlog.js set --workspace {doc_workspace} --key status --value complete`.
 4. Produce the requested artifacts from the log — `brainstorm.html` (the imaginative, self-contained, no-template report) and/or the succinct `brainstorm-intent.md` — the same artifacts `references/finalize.md` describes, delegating each to a subagent that reads the log as its sole source. (Headless produces the `artifacts` payload directly; it does not ask, unlike the interactive opt-in.)
 5. Execute each entry in `{workflow.external_handoffs}` (capture returned URLs/IDs into the JSON `external_handoffs` array; skip and flag unavailable tools — local files always exist). Then run `{workflow.on_complete}` if non-empty.
 

package/src/core-skills/wizz-brainstorming/references/mode-autonomous.md

@@ -5,6 +5,6 @@ The user handed you the topic and wants to see what you come up with on your own
 - **Run a real divergent session yourself.** Pick and run techniques on your own (use `brain.py` as in `## Choosing Techniques`, but *you* choose — no menu for the user), capturing each idea to the memlog with `--type idea --by coach`, marking each technique switch with a `technique` entry, shifting the creative domain every ~10 ideas, aiming past 100. Push past the obvious.
 - **Don't pepper the user with questions** — this is your run. One quick confirm of topic and goal up front is plenty.
 - **When it's mined out, synthesize and produce the keepsake.** Go to `## Wrap-Up` (`references/finalize.md`): record the insights, mark the memlog complete, and **auto-generate the imaginative HTML keepsake — don't ask first; the keepsake is the result you promised to show them.** Offer the other artifacts (intent doc, etc.) after.
-- **Then, because a human is here, offer to keep going together.** They may want to push an idea further or react to what you found — if so, switch into **Facilitator** or **Creative Partner** (load that frame), **record the switch in the memlog** so a resume restores the new stance — `python3 {project-root}/_wizz/scripts/memlog.py set --workspace {doc_workspace} --key mode --value <facilitator|partner>` — and continue from the same memlog.
+- **Then, because a human is here, offer to keep going together.** They may want to push an idea further or react to what you found — if so, switch into **Facilitator** or **Creative Partner** (load that frame), **record the switch in the memlog** so a resume restores the new stance — `node {project-root}/_wizz/scripts/memlog.js set --workspace {doc_workspace} --key mode --value <facilitator|partner>` — and continue from the same memlog.
 
 This is the interactive sibling of headless mode (`references/headless.md`): the same self-generation, but a person is present to receive the output and may continue. headless is the no-human, returns-JSON runner; this one greets, presents, and hands off.

package/src/core-skills/wizz-customize/SKILL.md

@@ -14,7 +14,7 @@ When the target's `customize.toml` doesn't expose what the user wants, say so pl
 ## Preflight
 
 - No `{project-root}/_wizz/` → Wizz isn't installed. Say so, stop.
-- `{project-root}/_wizz/scripts/resolve_customization.py` missing → continue, but Step 6 verify falls back to manual merge.
+- `npx wizz-method resolve` unavailable → continue, but Step 6 verify falls back to manual merge.
 - Both present → proceed.
 
 ## Activation
@@ -70,13 +70,13 @@ Merge semantics:
 
 Overrides are sparse: only the fields being changed. Never copy the whole `customize.toml`.
 
-**Template swap** (`*_template` scalar): offer to copy the default template to `{project-root}/_wizz/custom/{skill-name}-{purpose}-template.md`, point the override at the new path, offer to help edit it.
+**Template swap** (`*_template` scalar): offer to copy the default template to `{project-root}/_wizz/custom/<skill-name>-{purpose}-template.md`, point the override at the new path, offer to help edit it.
 
 ## Step 5: Team or user placement
 
 Under `{project-root}/_wizz/custom/`:
-- `{skill-name}.toml` — team, committed. Policies, org conventions, compliance.
-- `{skill-name}.user.toml` — user, gitignored. Personal tone, private facts, shortcuts.
+- `<skill-name>.toml` — team, committed. Policies, org conventions, compliance.
+- `<skill-name>.user.toml` — user, gitignored. Personal tone, private facts, shortcuts.
 
 Default by character (policy → team, personal → user), confirm before writing.
 
@@ -85,16 +85,19 @@ Default by character (policy → team, personal → user), confirm before writin
 1. Show the full TOML. If the file exists, show a diff. Never silently overwrite.
 2. Wait for explicit yes.
 3. Write. Create `{project-root}/_wizz/custom/` if needed.
-4. Verify:
+4. **Regenerate the resolved snapshot** — mandatory after every write: run `npx wizz-method resolve --skill <skill-name>` from `{project-root}` (Node, no Python; it rewrites the snapshot atomically and refreshes `_resolved/.index.json`, so `wizz doctor` never reports it as stale). This is what keeps `_resolved/<skill-name>.json` in sync with the file you just wrote.
+5. Verify — read the snapshot regenerated in the step above:
    ```
-   python3 {project-root}/_wizz/scripts/resolve_customization.py --skill <install-path> --key <agent-or-workflow>
+   {project-root}/_wizz/_resolved/<skill-name>.json
    ```
-   Show the merged output, point out the changed fields.
+   (subtree `<agent-or-workflow>`). Show the merged output, point out the changed fields.
 
-   **Resolver missing or fails:** read whichever layers exist — `<install-path>/customize.toml` (base), `{project-root}/_wizz/custom/{skill-name}.toml` (team), `{project-root}/_wizz/custom/{skill-name}.user.toml` (user) — apply base → team → user with the same merge rules (scalars override, tables deep-merge, `code`/`id`-keyed arrays merge by key, all other arrays append), describe how the changed fields resolve.
+   **Snapshot staleness:** snapshots are regenerated at `wizz update`, `wizz resolve`, and by the regenerate-snapshot step above; `wizz doctor` reports any snapshot that has gone stale. Editing a custom TOML by hand outside this skill, without running `wizz resolve` afterward, leaves the old `_resolved/<skill-name>.json` in force until the next regeneration.
 
-   **Verify shows override didn't land** (field unchanged, merge conflict, file not picked up): re-enter Step 4 with the verify output as context. Usually wrong field name, wrong merge mode (scalar vs array), or wrong scope.
-5. Summarize what changed, where the file lives, how to iterate. Remind the user to commit team overrides.
+   **Resolver missing or fails:** read whichever layers exist — `<install-path>/customize.toml` (base), `{project-root}/_wizz/custom/<skill-name>.toml` (team), `{project-root}/_wizz/custom/<skill-name>.user.toml` (user) — apply base → team → user with the same merge rules (scalars override, tables deep-merge, `code`/`id`-keyed arrays merge by key, all other arrays append), describe how the changed fields resolve.
+
+   **Verify shows override didn't land** (field unchanged, merge conflict, file not picked up): re-enter **Step 4: Compose the override** with the verify output as context. Usually wrong field name, wrong merge mode (scalar vs array), or wrong scope.
+6. Summarize what changed, where the file lives, how to iterate. Remind the user to commit team overrides.
 
 ## Complete when
 

package/src/core-skills/wizz-editorial-review-prose/SKILL.md

@@ -7,7 +7,7 @@ description: 'Clinical copy-editor that reviews text for communication issues. U
 
 **Goal:** Review text for communication issues that impede comprehension and output suggested fixes in a three-column table.
 
-**Architecture note (delegating bridge):** This skill is a thin bridge. The substantive review logic lives in the global `copy-editing` skill (Seven Sweeps framework — more rigorous than a linear pass) and, when the text reads as AI-generated, the `humanizer` skill. This bridge keeps a stable name/contract because BMM workflows (`wizz-prd`, `wizz-ux`, `wizz-architecture`, `wizz-product-brief`) invoke `wizz-editorial-review-prose` by name. It always returns the same three-column table so those workflows are unaffected.
+**Architecture note (delegating bridge):** This skill is a thin bridge. The substantive review logic lives in the global `wizz-copy-editing` skill (Seven Sweeps framework — more rigorous than a linear pass) and, when the text reads as AI-generated, the `wizz-humanizer` skill. This bridge keeps a stable name/contract because BMM workflows (`wizz-prd`, `wizz-ux`, `wizz-architecture`, `wizz-product-brief`) invoke `wizz-editorial-review-prose` by name. It always returns the same three-column table so those workflows are unaffected.
 
 **Your Role:** Clinical copy-editor: precise, professional, neither warm nor cynical. Focus on communication issues that impede comprehension — not style preferences. NEVER rewrite for preference — only fix genuine issues.
 
@@ -26,16 +26,16 @@ description: 'Clinical copy-editor that reviews text for communication issues. U
 - Identify content type; note code blocks, frontmatter, and structural markup to skip (never edit these).
 
 ### Step 2: Delegate the review
-Invoke the global `copy-editing` skill via the `Skill` tool, passing:
+Invoke the global `wizz-copy-editing` skill via the `Skill` tool, passing:
 - the `content` (prose sections only — code/markup excluded),
 - the `style_guide` if provided (instruct that it is the final authority, except CONTENT IS SACROSANCT),
 - the `reader_type` framing: if `llm`, prioritize unambiguous references, consistent terminology, explicit structure, no hedging; if `humans`, prioritize clarity, flow, readability.
 
-Instruct `copy-editing` to operate in **comprehension-only mode**: minimal intervention, fix prose within existing structure (never restructure), preserve author voice, flag uncertain fixes as a query rather than a definitive change, and NEVER alter what ideas say.
+Instruct `wizz-copy-editing` to operate in **comprehension-only mode**: minimal intervention, fix prose within existing structure (never restructure), preserve author voice, flag uncertain fixes as a query rather than a definitive change, and NEVER alter what ideas say.
 
-**If `reader_type` is `humans`** and the text shows signs of AI-generated writing (inflated symbolism, rule-of-three padding, em-dash overuse, vague attributions, negative parallelisms): also invoke `humanizer` on the affected passages and fold its fixes in.
+**If `reader_type` is `humans`** and the text shows signs of AI-generated writing (inflated symbolism, rule-of-three padding, em-dash overuse, vague attributions, negative parallelisms): also invoke `wizz-humanizer` on the affected passages and fold its fixes in.
 
-**Fallback (skill unavailable):** If `copy-editing` is not installed/resolvable, perform the review inline using these principles — minimal intervention, preserve structure, skip code/markup, query when uncertain, deduplicate identical issues into one entry with all locations listed, merge overlapping fixes, respect author voice — applying Microsoft Writing Style Guide as the baseline.
+**Fallback (skill unavailable):** If `wizz-copy-editing` is not installed/resolvable, perform the review inline using these principles — minimal intervention, preserve structure, skip code/markup, query when uncertain, deduplicate identical issues into one entry with all locations listed, merge overlapping fixes, respect author voice — applying Microsoft Writing Style Guide as the baseline.
 
 ### Step 3: Normalize and output
 Map every confirmed fix into the canonical three-column table. Deduplicate (same issue in multiple places = one entry listing all locations) and merge overlapping fixes before output.

package/src/core-skills/wizz-forge-idea/SKILL.md

@@ -17,14 +17,14 @@ Lead by questioning, not lecturing. Ask one question at a time, press on weak po
 
 ## Conventions
 
-- Scripts live in two places — run each from the exact path written, never assume co-location: the shared core scripts (`memlog.py`, `resolve_customization.py`, `resolve_config.py`) are installed by Wizz core at `{project-root}/_wizz/scripts/` and are never bundled here; this skill's own `resolve_personas.py` is at `{skill-root}/scripts/`.
+- Scripts live in two places — run each from the exact path written, never assume co-location: the shared core scripts (`memlog.js`, `resolve_customization.py`, `resolve_config.py`) are installed by Wizz core at `{project-root}/_wizz/scripts/` and are never bundled here; this skill's own `resolve_personas.py` is at `{skill-root}/scripts/`.
 - `{workflow.<name>}` resolves to fields in the merged `customize.toml` `[workflow]` table.
 
 ## On Activation
 
-1. Resolve customization: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, read `{skill-root}/customize.toml` directly with defaults. Apply the resolved `{workflow.*}` values throughout.
+1. Resolve customization: Read `{project-root}/_wizz/_resolved/wizz-forge-idea.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-forge-idea` from the project root and read the snapshot again. On failure, read `{skill-root}/customize.toml` directly with defaults. Apply the resolved `{workflow.*}` values throughout.
 2. Run each `{workflow.activation_steps_prepend}` entry; treat each `{workflow.persistent_facts}` entry as foundational context (`file:` entries load their contents, `skill:` names a skill to consult, others are facts verbatim).
-3. Resolve central config: `python3 {project-root}/_wizz/scripts/resolve_config.py --project-root {project-root} --key core`; from the merged JSON read `{user_name}`, `{communication_language}`, `{output_folder}`. On failure use neutral defaults; never block. Greet `{user_name}` in `{communication_language}` and stay in it.
+3. Resolve central config: read `{project-root}/_wizz/_resolved/_config.json` (subtree `core`) for `{user_name}`, `{communication_language}`, `{output_folder}`. If the file is missing, run `npx wizz-method resolve` and read it again. On failure use neutral defaults; never block. Greet `{user_name}` in `{communication_language}` and stay in it.
 4. Note whether a Wizz persona is already active in this conversation — the user loaded one (e.g. the analyst, the storyteller) and invoked the forge from within it. If so, that persona leads the session, in voice, throughout.
 5. Resume: glob `{workflow.forge_output_path}/**/.memlog.md` (recursive, so it still finds sessions when `run_folder_pattern` is overridden to nest paths) and read only each match's frontmatter to find any whose `status` is not `complete`. Offer to resume one — then read its full memlog once to rebuild state and continue append-only — or to start fresh.
 6. Run each `{workflow.activation_steps_append}` entry.
@@ -53,7 +53,7 @@ Tell the user they can say **"attack this"**, **"defend this"**, or **"switch ro
 ### Set up the session
 
 Derive a kebab-case `{slug}` for the idea and bind the session workspace `{workspace} = {workflow.forge_output_path}/{workflow.run_folder_pattern}` (the pattern fills with `{slug}`). Create the memlog once the goal is known:
-`python3 {project-root}/_wizz/scripts/memlog.py init --workspace {workspace} --field idea="<idea>" --field goal="<goal>"`
+`node {project-root}/_wizz/scripts/memlog.js init --workspace {workspace} --field idea="<idea>" --field goal="<goal>"`
 
 Tell the user the path; state is on disk now, so the session survives interruption. If init fails, don't abort — run the forge in-conversation and tell the user state won't persist this session.
 
@@ -74,7 +74,7 @@ When a branch resolves, pause before moving on. Give the user a chance to raise
 Do not use agreement or praise to make the interaction smoother; they lower pressure and lead to shallower thinking. Agreement is allowed only when it helps the user think better. Praise is noise. Continued engagement and ego-stroking are not objectives. In attack mode, never agree with the idea until the user ends the mode. For each answer, either challenge the weak point or build on the strong point, whichever helps the user think better.
 
 Capture as you go — each decision, assumption, crack, kill, and locked idea, one bullet in the user's meaning:
-`python3 {project-root}/_wizz/scripts/memlog.py append --workspace {workspace} --type <decision|assumption|crack|kill|direction|lock|note> --text "<gist>"`
+`node {project-root}/_wizz/scripts/memlog.js append --workspace {workspace} --type <decision|assumption|crack|kill|direction|lock|note> --text "<gist>"`
 A `lock` is an idea the user hardens — settled, not to be reopened; locks are what `forged-idea.md` is distilled from. Don't read the memlog back except on resume. If the user raises a different branch, capture it and stay put — the loop and the stray insight both survive.
 
 ## The personas
@@ -103,5 +103,5 @@ The session can end in three valid states:
 
 Always render `{workspace}/forge-report.html` as a self-contained HTML file the user can open, with inline CSS and an inline-SVG seal or stamp. Summarize the outcome, the locked decisions, what was rejected and why, and the weak points that survived scrutiny, in the user's meaning. Credit the personas and parties that pressure-tested the idea by name, icon, and voice. Render a prominent wax-seal-style or stamped outcome mark, matched to the result: `HARDENED`, an `Idea Death Certificate` stamped `KILLED` with the cause of death, or `CLARIFIED`. Tell the user the path.
 
-Flip the status at the end: `python3 {project-root}/_wizz/scripts/memlog.py set --workspace {workspace} --key status --value complete`.
+Flip the status at the end: `node {project-root}/_wizz/scripts/memlog.js set --workspace {workspace} --key status --value complete`.
 If `{workflow.on_complete}` is non-empty, run all instructions in order.

package/src/core-skills/wizz-forge-idea/scripts/resolve_personas.py

@@ -108,7 +108,23 @@ def find_party_skill(project_root: Path, skill_root: Path):
 
 
 def load_party_workflow(project_root: Path, party_skill: Path):
-    """Merged [workflow] table for wizz-party-mode (base + user overrides)."""
+    """Merged [workflow] table for wizz-party-mode (base + user overrides).
+
+    Prefers the pre-resolved snapshot at `_wizz/_resolved/<skill-name>.json`
+    (written by `wizz update` / `wizz resolve` / wizz-customize) — one Read,
+    no spawn. Falls back to shelling out to resolve_customization.py, and
+    from there to the skill's base customize.toml, when the snapshot is
+    missing.
+    """
+    resolved_path = project_root / "_wizz" / "_resolved" / f"{party_skill.name}.json"
+    if resolved_path.exists():
+        try:
+            with resolved_path.open("r", encoding="utf-8") as f:
+                snapshot = json.load(f)
+            if isinstance(snapshot, dict) and isinstance(snapshot.get("workflow"), dict):
+                return snapshot["workflow"]
+        except (OSError, json.JSONDecodeError):
+            pass
     resolver = project_root / "_wizz" / "scripts" / "resolve_customization.py"
     data = _run_json([sys.executable, str(resolver), "--skill", str(party_skill), "--key", "workflow"])
     if data is not None and isinstance(data.get("workflow"), dict):

package/src/core-skills/wizz-party-mode/SKILL.md

@@ -10,14 +10,14 @@ Run a round-table where these agents talk to each other and to the user like rea
 ## Conventions
 
 - **Paths:** bare paths (e.g. `references/create-party.md`) resolve from `{skill-root}` (where `customize.toml` lives); `{project-root}`-prefixed paths from the project working dir. `{workflow.<name>}` resolves to `customize.toml`'s `[workflow]` table (overrides win).
-- **Scripts** (run via `python3`): `{project-root}/_wizz/scripts/resolve_config.py` resolves central config (four-layer TOML merge); `{project-root}/_wizz/scripts/resolve_customization.py` resolves `{workflow.*}`; `{skill-root}/scripts/resolve_party.py` resolves the roster, `party_mode`, `memory_enabled`, and scene/`open_cast`; `{project-root}/_wizz/scripts/memlog.py` reads/writes per-party memory.
+- **Scripts and snapshots**: `{project-root}/_wizz/_resolved/_config.json` carries the central config already merged across its four layers (no script); `{project-root}/_wizz/_resolved/wizz-party-mode.json` carries `{workflow.*}`; `{skill-root}/scripts/resolve_party.py` (run via `python3`) resolves the roster, `party_mode`, `memory_enabled`, and scene/`open_cast`; `node {project-root}/_wizz/scripts/memlog.js` reads/writes per-party memory.
 - **File roles:** a party's memory is the per-party memlog at `{workflow.memory_dir}/<party>/.memlog.md`; custom members and groups live in the user's `customize.toml` overrides. Mechanics in `references/party-memory.md` (memory) and `references/create-party.md` (authoring).
 - **Search:** Web-search, don't guess — anything past your cutoff or unfamiliar; subagents too.
 
 ## On Activation
 
-1. **Resolve customization:** `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, read `{skill-root}/customize.toml` directly and use defaults. Then run each `{workflow.activation_steps_prepend}` entry, and hold each `{workflow.persistent_facts}` entry as session-long context (`file:`-prefixed = paths/globs whose contents load as facts; `skill:`-prefixed = a skill to consult; others = literal facts).
-2. **Resolve core config:** `python3 {project-root}/_wizz/scripts/resolve_config.py --project-root {project-root}`. From the merged JSON's `core` table: greet with `{user_name}`, speak in `{communication_language}`, and resolve `{output_folder}`; `{date}` is today's date.
+1. **Resolve customization:** Read `{project-root}/_wizz/_resolved/wizz-party-mode.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-party-mode` from the project root and read the snapshot again. On failure, read `{skill-root}/customize.toml` directly and use defaults. Then run each `{workflow.activation_steps_prepend}` entry, and hold each `{workflow.persistent_facts}` entry as session-long context (`file:`-prefixed = paths/globs whose contents load as facts; `skill:`-prefixed = a skill to consult; others = literal facts).
+2. **Resolve core config:** read `{project-root}/_wizz/_resolved/_config.json` (if it is missing, run `npx wizz-method resolve` from the project root and read it again; if that also fails, use neutral defaults and never block). From its `core` table: greet with `{user_name}`, speak in `{communication_language}`, and resolve `{output_folder}`; `{date}` is today's date.
 3. **Detect intent and route.** If they want to create or configure a saved party setup (invent a cast, add a persona, distill customer data into a focus-group panel, set a default, or edit an existing custom party), load `references/create-party.md` and follow it. Otherwise run a party — continue below.
 4. **Resolve the roster:** `python3 {skill-root}/scripts/resolve_party.py --project-root {project-root} --skill {skill-root}`. It returns the active roster (`{workflow.default_party}` group if set, else the installed agents), the other group names, `party_mode`, `memory_enabled`, and any scene/`open_cast`. Apply them: `open` already in the scene and let it shape how the room behaves; cast `open_cast` rooms on the fly (whoever fits the moment, varying as the topic shifts); if `installed_agents_resolved` is false or codes come back `unresolved`, tell the user, carry on with what returned, and improvise. Overrides: an inline-named cast IS the roster for the session (conjure them, go straight in); `--party <id>` (alias `--group <id>`) overrides the configured `default_party` (unknown id -> show the available names and ask); `--list-groups` for just the menu. Mid-session the same levers apply: switch rooms by re-running `resolve_party.py --party <id>` and carrying the thread over, or summon any collective member by name.
 5. **Memory.** If `memory_enabled` (from `resolve_party.py`), follow `references/party-memory.md` for the whole run.

package/src/core-skills/wizz-party-mode/references/create-party.md

@@ -30,7 +30,7 @@ Ask which they're after if it isn't obvious, then proceed.
 
 ## Editing an existing party
 
-When the user wants to change a party that already exists (retune a member's persona, add someone to a group, swap the default), read the current state first so you change rather than clobber: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow` returns the merged `party_members`, `party_groups`, and `default_party`. Show the member or group being touched, capture only the delta with the user, and hand that sparse change to `wizz-customize` — it replaces a `party_members`/`party_groups` entry whose `code`/`id` matches and appends the rest, so an edit is just the changed entry, never a full rewrite.
+When the user wants to change a party that already exists (retune a member's persona, add someone to a group, swap the default), read the current state first so you change rather than clobber: `{project-root}/_wizz/_resolved/wizz-party-mode.json` (subtree `workflow`) holds the merged `party_members`, `party_groups`, and `default_party`; if the file is missing, run `npx wizz-method resolve --skill wizz-party-mode` from the project root and read it again. Show the member or group being touched, capture only the delta with the user, and hand that sparse change to `wizz-customize` — it replaces a `party_members`/`party_groups` entry whose `code`/`id` matches and appends the rest, so an edit is just the changed entry, never a full rewrite.
 
 ## Keeping new faces from a session
 

package/src/core-skills/wizz-party-mode/references/party-memory.md

@@ -34,7 +34,7 @@ When a character shows up who isn't in the party's roster — cast from an open-
 ## Write it
 
 ```
-python3 {project-root}/_wizz/scripts/memlog.py append \
+node {project-root}/_wizz/scripts/memlog.js append \
   --workspace {workflow.memory_dir}/{active} \
   --type <dynamic|moment|callback|outcome> \
   --text "<one succinct line, in the room's own read of it>"
@@ -42,7 +42,7 @@ python3 {project-root}/_wizz/scripts/memlog.py append \
 
 Add `--by <persona-code>` when a memory belongs to one character. Choose `init` vs `append` from the existence fact you already hold: the entry-read (and, on a mid-session room switch, that room's read) told you whether the memlog exists — `init --workspace {workflow.memory_dir}/{active}` once before the first append when it doesn't, plain `append` when it does. (`init` errors if the file already exists, so don't call it blind.)
 
-If `memlog.py` is unavailable or a write errors, skip it silently and never stall the party on a failed write.
+If `memlog.js` is unavailable or a write errors, skip it silently and never stall the party on a failed write.
 
 ## Forget
 

package/src/core-skills/wizz-party-mode/scripts/resolve_party.py

@@ -69,7 +69,23 @@ def load_agents(project_root: Path):
 
 
 def load_workflow(project_root: Path, skill_root: Path):
-    """Merged [workflow] table. Falls back to the skill's base customize.toml."""
+    """Merged [workflow] table.
+
+    Prefers the pre-resolved snapshot at `_wizz/_resolved/<skill-name>.json`
+    (written by `wizz update` / `wizz resolve` / wizz-customize) — one Read,
+    no spawn. Falls back to shelling out to resolve_customization.py, and
+    from there to the skill's base customize.toml, when the snapshot is
+    missing.
+    """
+    resolved_path = project_root / "_wizz" / "_resolved" / f"{skill_root.name}.json"
+    if resolved_path.exists():
+        try:
+            with resolved_path.open("r", encoding="utf-8") as f:
+                snapshot = json.load(f)
+            if isinstance(snapshot, dict) and "workflow" in snapshot:
+                return snapshot["workflow"]
+        except (OSError, json.JSONDecodeError):
+            pass
     script = project_root / "_wizz" / "scripts" / "resolve_customization.py"
     data = _run_json([sys.executable, str(script), "--skill", str(skill_root), "--key", "workflow"])
     if data is not None and "workflow" in data:

package/src/core-skills/wizz-review-adversarial-general/SKILL.md

@@ -5,7 +5,9 @@ description: 'Perform a Cynical Review and produce a findings report. Use when t
 
 # Adversarial Review (General)
 
-> **Cross-reference:** this is the internal "Blind Hunter" layer that `wizz-code-review` invokes as one of three parallel reviewers (diff only, no project context, no triage). It is not meant to be invoked standalone by a user. For an ad hoc adversarial pass outside a bmm workflow, use the `adversarial-reviewer` skill directly; for the full triaged multi-layer review of a real diff, run `wizz-code-review`.
+> **Cross-reference:** this is the "Blind Hunter" review lens (diff only, no project context, no triage). It is not meant to be invoked standalone by a user. For an ad hoc adversarial pass outside a bmm workflow, use the `wizz-adversarial-reviewer` skill directly; for the full triaged multi-layer review of a real diff, run `wizz-code-review`.
+>
+> **Fonte única do prompt (2026-09-11, item 22 da auditoria):** o texto operacional do Blind Hunter mora em `src/bmm-skills/4-implementation/wizz-code-review/review-prompts/blind-hunter.md` (cópia idêntica em `wizz-quick-dev/review-prompts/`, paridade travada por `test/test-blind-hunter-parity.js`). Este SKILL.md guarda a persona e o mindset cínico que o revisor assume; os workflows não invocam esta skill — leem o review-prompts direto.
 
 **Goal:** Cynically review content and produce findings.
 

package/src/core-skills/wizz-spec/SKILL.md

@@ -18,7 +18,7 @@ Multiple skills may call to update the same spec over time.
 
 ## On Activation
 
-1. Resolve customization: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, read `{skill-root}/customize.toml` directly.
+1. Resolve customization: Read `{project-root}/_wizz/_resolved/wizz-spec.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-spec` from the project root and read the snapshot again. On failure, read `{skill-root}/customize.toml` directly.
 2. Run `{workflow.activation_steps_prepend}`. Treat `{workflow.persistent_facts}` as foundational context (`file:` entries are loaded).
 3. Load `{project-root}/_wizz/core/config.yaml` (and `config.user.yaml` if present), root level and `bmm` section. Resolve `{user_name}`, `{communication_language}`, `{document_output_language}`, `{planning_artifacts}`, `{project_name}`, `{date}`.
 4. Detect mode. **Headless** when any of: no TTY, programmatic caller (another skill or non-interactive runner), or the first message pre-supplies all inputs and asks for an artifact path back. **Interactive** otherwise. In interactive mode, greet by `{user_name}` in `{communication_language}`, stay in that language, and mention that `wizz-party-mode` and `wizz-advanced-elicitation` are available for deeper exploration on any field.
@@ -55,15 +55,15 @@ Inside the spec folder:
 
 Deriving the contract from a living log instead of editing the contract in place is what lets the steps around the spec (PRD, UX, architecture, epics) run in any order and feed the same spec without merge drift: the log only accumulates, the artifact is re-rendered. So the spec is updated *only* by re-deriving it here — wizz-spec is its single writer; a hand-edit to `SPEC.md` from outside is unsupported and is overwritten on the next derive.
 
-Writes go through the shared script — `{project-root}/_wizz/scripts/memlog.py`, the same location as `resolve_customization.py` (atomic; never read it back except to resume):
+Writes go through the shared script — `{project-root}/_wizz/scripts/memlog.js` (atomic; never read it back except to resume):
 
-- `python3 {project-root}/_wizz/scripts/memlog.py init --workspace {spec-folder} --field topic="<what is being specced>"` — once, at create.
-- `python3 {project-root}/_wizz/scripts/memlog.py append --workspace {spec-folder} --type <decision|constraint|capability|assumption|question|direction|note|event> --text "<one-line gist, reason included>"` — as each lands.
+- `node {project-root}/_wizz/scripts/memlog.js init --workspace {spec-folder} --field topic="<what is being specced>"` — once, at create.
+- `node {project-root}/_wizz/scripts/memlog.js append --workspace {spec-folder} --type <decision|constraint|capability|assumption|question|direction|note|event> --text "<one-line gist, reason included>"` — as each lands.
 - Terminal moments (a validation verdict, "spec finalized") are `--type event` entries; the memlog carries no status field.
 
 ## The Operation
 
-Read the input and its ancillary linked materials. If there is no input, follow the no-input branch in **Workspace** (ask or block). If a prior `.memlog.md` exists at the target folder, read it — the operation becomes an update, and the memlog (not the rendered `SPEC.md`) is the authority on what was decided and on capability IDs. Preserve those IDs; new capabilities get the next unused `CAP-N`; never reuse retired IDs. Otherwise this is a create, and the first move is `memlog.py init`.
+Read the input and its ancillary linked materials. If there is no input, follow the no-input branch in **Workspace** (ask or block). If a prior `.memlog.md` exists at the target folder, read it — the operation becomes an update, and the memlog (not the rendered `SPEC.md`) is the authority on what was decided and on capability IDs. Preserve those IDs; new capabilities get the next unused `CAP-N`; never reuse retired IDs. Otherwise this is a create, and the first move is `memlog.js init`.
 
 When the input is structured and pre-sorted (a PRD with an addendum, a GDD, a brief produced by an upstream Wizz skill), trust the authored separation: lift kernel-fitting content into SPEC.md, lift overflow into appropriately-named companions. When the input is mixed (a brain dump, a transcript, an RFC, a customer email), do the sorting yourself: walk each claim, apply the three-lens load-bearing test (Spec Law rule 7), and route to the kernel field or a companion.
 

package/src/modules/lowticket/README.md

@@ -8,11 +8,11 @@ Install it and a fresh machine has the methodology and the four agents working,
 
 | Skill | Does | Use when | Do not use when |
 |---|---|---|---|
-| `lowticket-metodologia` | routes a request to the one knowledge shard that answers it, loads the guardrails alongside | any low ticket work: offer, creative, page, campaign, funnel | SaaS, B2B, client site, high ticket |
-| `lowticket-trafego` | campaign diagnosis and ruler: structure, bid cap, when to cut, how to scale | reading, cutting or scaling a Meta campaign | Google Ads, brand campaigns, writing ads |
-| `lowticket-funil` | the post-checkout ladder: upsell, downsell, final offer, price rules | after the front-end converts, to raise average order value | before a front-end that converts exists |
-| `lowticket-minerador` | mining and judging a competitor offer, with a cut-off rubric | hunting a new offer to model | the offer is already defined (use `wizz-offer-forge`) |
-| `lowticket-pagina` | page performance: connect rate, LCP, pixel order, acceptance targets | optimizing or building a low ticket sales page | institutional sites or apps |
+| `wizz-lowticket-metodologia` | routes a request to the one knowledge shard that answers it, loads the guardrails alongside | any low ticket work: offer, creative, page, campaign, funnel | SaaS, B2B, client site, high ticket |
+| `wizz-lowticket-trafego` | campaign diagnosis and ruler: structure, bid cap, when to cut, how to scale | reading, cutting or scaling a Meta campaign | Google Ads, brand campaigns, writing ads |
+| `wizz-lowticket-funil` | the post-checkout ladder: upsell, downsell, final offer, price rules | after the front-end converts, to raise average order value | before a front-end that converts exists |
+| `wizz-lowticket-minerador` | mining and judging a competitor offer, with a cut-off rubric | hunting a new offer to model | the offer is already defined (use `wizz-offer-forge`) |
+| `wizz-lowticket-pagina` | page performance: connect rate, LCP, pixel order, acceptance targets | optimizing or building a low ticket sales page | institutional sites or apps |
 
 All five read the Cérebro on activation and **none of them keeps its own memory**, the same contract as `wizz-offer-forge`. What is decided lives in the Cérebro; what is known lives in the shards.
 
@@ -52,4 +52,4 @@ To let the agent open a specific piece, point at the folder during install, or p
 swipe_file_path = "/absolute/path/to/the/swipe/file"
 ```
 
-Resolution order and the exact wording to use when the folder is absent: `skills/lowticket-metodologia/references/swipe-file.md`.
+Resolution order and the exact wording to use when the folder is absent: `skills/wizz-lowticket-metodologia/references/swipe-file.md`.

package/src/modules/lowticket/module.yaml

@@ -2,10 +2,13 @@ code: lowticket
 name: "Wizz Low Ticket"
 description: "Low ticket direct-response playbook for Meta Ads (BR/PT): funnel diagnosis, bid-cap campaigns, creatives, offers, sales pages, VSL players, upsell ladders, copy diagnosis, tracking setup and offer mining. Knowledge base in Portuguese, loaded one shard at a time."
 default_selected: false
+# Versão do contrato module.yaml <-> installer (auditoria 2026-09-11, item 25).
+# Ver tools/installer/modules/module-interface.js. Ausente = 1.
+interface_version: 1
 
 # --- Origin note (read this before editing the knowledge base) ---
 #
-# The knowledge under skills/lowticket-metodologia/knowledge/ is a distillation
+# The knowledge under skills/wizz-lowticket-metodologia/knowledge/ is a distillation
 # written from scratch: facts, benchmarks, checklists and critical analysis.
 # No third-party lesson text, transcript, PDF or prompt ships in this package.
 # The raw sources stay on the author's machine, outside npm and outside git.

package/src/modules/lowticket/skills/{lowticket-funil → wizz-lowticket-funil}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: lowticket-funil
+name: wizz-lowticket-funil
 description: Designs the post-checkout ladder for a low ticket offer - upsell 1, upsell 2, downsell and a final offer - deciding what each step sells, which pain it answers, what it costs and why it sits in that position, then writes the pages. Use when a front-end offer already converts and the goal is to raise average order value, or when an existing upsell sequence is not converting. Do NOT use before a front-end that converts exists, and do NOT use for traffic, campaigns or the front-end offer itself.
 ---
 
@@ -13,11 +13,11 @@ Every offer in the ladder exists because it answers that question for the step b
 
 ## Prerequisite
 
-**There has to be a front-end that converts.** Extending a funnel above a front that does not sell multiplies zero. If the front is not validated, say so and point to `wizz-offer-forge` (build the offer) or `lowticket-trafego` (find out why it is not selling).
+**There has to be a front-end that converts.** Extending a funnel above a front that does not sell multiplies zero. If the front is not validated, say so and point to `wizz-offer-forge` (build the offer) or `wizz-lowticket-trafego` (find out why it is not selling).
 
 ## Source of truth
 
-Read the Cérebro state first (via the `cerebro` skill). Then, if `lowticket-metodologia` is installed, read `knowledge/INDEX.md` + `knowledge/guardrails.md` and the shard `07-funil-upsell.md`, especially §7.4 (the conversion and ticket cascade) and §7.5-7.9 (pain per step, tone per page, copy rules, the technical block for post-checkout pages and the pre-build checklist). Its sibling shard `07a-copy-humanizacao.md` carries the humanization checklist used before delivering any page. Where a generic skill contradicts that shard, the shard wins and you say so.
+Read the Cérebro state first (via the `cerebro` skill). Then, if `wizz-lowticket-metodologia` is installed, read `knowledge/INDEX.md` + `knowledge/guardrails.md` and the shard `07-funil-upsell.md`, especially §7.4 (the conversion and ticket cascade) and §7.5-7.9 (pain per step, tone per page, copy rules, the technical block for post-checkout pages and the pre-build checklist). Its sibling shard `07a-copy-humanizacao.md` carries the humanization checklist used before delivering any page. Where a generic skill contradicts that shard, the shard wins and you say so.
 
 This skill has **no memory of its own**. What gets decided goes to the Cérebro; the artifact goes to a file.
 
@@ -109,4 +109,4 @@ The full anti-AI word list and the rhythm rules are in `references/copy-das-pagi
 
 ## Out of scope
 
-Traffic, campaigns, hiring, accounting, general operations. Bring it back to product, offer, price, pain, post-checkout sequence and copy, or route: `lowticket-trafego` for campaigns, `wizz-offer-forge` for the front-end offer, `lowticket-pagina` for the sales page itself.
+Traffic, campaigns, hiring, accounting, general operations. Bring it back to product, offer, price, pain, post-checkout sequence and copy, or route: `wizz-lowticket-trafego` for campaigns, `wizz-offer-forge` for the front-end offer, `wizz-lowticket-pagina` for the sales page itself.

package/src/modules/lowticket/skills/{lowticket-funil → wizz-lowticket-funil}/references/copy-das-paginas.md

@@ -66,7 +66,7 @@ No lugar: linguagem falada. "do jeito certo", "na prática", "pra valer", "na re
 
 **Sem travessão longo.** Vírgula, ponto, dois pontos ou parênteses.
 
-Antes de entregar, rodar o checklist de 10 filtros de `07a-copy-humanizacao.md` (shard irmão de `07-funil-upsell.md`, na `lowticket-metodologia`): falhou em 3 ou mais, refaz. A lista de palavras banidas acima é a base; a lista ampliada e a tabela de substituição estão no shard.
+Antes de entregar, rodar o checklist de 10 filtros de `07a-copy-humanizacao.md` (shard irmão de `07-funil-upsell.md`, na `wizz-lowticket-metodologia`): falhou em 3 ou mais, refaz. A lista de palavras banidas acima é a base; a lista ampliada e a tabela de substituição estão no shard.
 
 ## Objeções
 

package/src/modules/lowticket/skills/{lowticket-metodologia → wizz-lowticket-metodologia}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: lowticket-metodologia
+name: wizz-lowticket-metodologia
 description: Routes any low ticket direct-response question to the one knowledge shard that answers it, and loads the guardrails alongside. Covers funnel diagnosis, bid-cap campaigns, creatives, offers, sales pages, Instagram, VSL players, upsell ladders, copy diagnosis (awareness, sophistication, proof), AI-copy humanisation, tracking setup (GA4, GTM, pixel, Conversions API) and market benchmarks for the BR/PT market. Use when working on a low ticket offer (roughly R$19 to R$97), a Meta Ads campaign for one, its sales page, its creatives, its upsell ladder, or when auditing why one is not converting. Do NOT use for SaaS, B2B, client websites, high ticket or mentorship funnels - the numbers here do not transfer.
 ---
 
@@ -23,7 +23,7 @@ Never open two shards to find out which one it was. The INDEX has a third column
 
 **Where a generic skill contradicts a shard, the shard wins, and you say that in the answer.**
 
-This matters constantly. `wizz-offer-forge` defaults to a R$10-97 low ticket band and 7/15/30 day guarantees; this base pins price by source band (R$19,90 / R$27 / R$37), upsell at 2 to 2.5x the entry, and has an unresolved point about 7 vs 14 day guarantees. Same for `page-cro`, `paid-ads` and `ad-creative`: the generic skill has the technique, this base has the numbers for this market.
+This matters constantly. `wizz-offer-forge` defaults to a R$10-97 low ticket band and 7/15/30 day guarantees; this base pins price by source band (R$19,90 / R$27 / R$37), upsell at 2 to 2.5x the entry, and has an unresolved point about 7 vs 14 day guarantees. Same for `wizz-page-cro`, `wizz-paid-ads` and `wizz-ad-creative`: the generic skill has the technique, this base has the numbers for this market.
 
 The one thing that outranks a shard is `knowledge/guardrails.md`. Seven tactics present in the source material are recorded there and **not adopted**: buying engagement, AI avatars passing as real people, synthetic testimonials, borrowing a third party's ID document to verify a profile, using a real person's name as borrowed proof, reposting someone else's video as your own creative, and a struck-through reference price that was never charged. They are blocked until the operation's owner decides otherwise. If a shard teaches one, the inline block line is there too.
 
@@ -57,6 +57,6 @@ The video and image files themselves do not ship. To open a specific piece, the
 
 ## What this skill does not do
 
-- **It does not write.** It routes and it cites. Producing the offer is `wizz-offer-forge`, the page is `page-cro`, the copy is `copywriting`, the campaign is `paid-ads`.
+- **It does not write.** It routes and it cites. Producing the offer is `wizz-offer-forge`, the page is `wizz-page-cro`, the copy is `wizz-copywriting`, the campaign is `wizz-paid-ads`.
 - **It does not remember.** No state file, no notes. The Cérebro is the memory.
 - **It does not travel outside its market.** SaaS, B2B, client sites and high ticket have different math. Say so rather than stretching the numbers.

package/src/modules/lowticket/skills/{lowticket-minerador → wizz-lowticket-minerador}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: lowticket-minerador
+name: wizz-lowticket-minerador
 description: Mines and judges competitor low ticket offers - generates the search vocabulary, reads an offer from a URL or screenshot and returns a verdict, compares two or three side by side, or diagnoses why a modeled offer never scaled. Rebuilds rather than clones. Use when hunting for a new offer to model, sizing up a competitor, or answering "this offer did not scale, what broke". Do NOT use once the offer is already defined - that is wizz-offer-forge - and do NOT use to run campaigns.
 ---
 
@@ -15,7 +15,7 @@ Someone who already runs traffic, reads metrics and has mined offers before. Do
 
 ## Source of truth
 
-Read the Cérebro state first (via the `cerebro` skill). If `lowticket-metodologia` is installed, read `knowledge/INDEX.md` + `knowledge/guardrails.md`, then:
+Read the Cérebro state first (via the `cerebro` skill). If `wizz-lowticket-metodologia` is installed, read `knowledge/INDEX.md` + `knowledge/guardrails.md`, then:
 
 - **`12-mineracao-ofertas.md`**: the price trick, the Ad Library filter checklist and keyword taxonomy, the 0-10 rubric with a cut at 6, the three safety rules
 - **`12a-mineracao-veredito.md`**: §12.5, the scoring ruler and what disqualifies
@@ -106,7 +106,7 @@ Identify the platform by clicking through to the competitor's checkout and readi
 
 ## Out of scope
 
-Advanced traffic operation → `lowticket-trafego`. Full funnel construction → `lowticket-funil`. Building the offer once it is chosen → `wizz-offer-forge`. Page work → `lowticket-pagina`. Say which part you can analyze and route the rest.
+Advanced traffic operation → `wizz-lowticket-trafego`. Full funnel construction → `wizz-lowticket-funil`. Building the offer once it is chosen → `wizz-offer-forge`. Page work → `wizz-lowticket-pagina`. Say which part you can analyze and route the rest.
 
 ## Tone
 

package/src/modules/lowticket/skills/{lowticket-minerador → wizz-lowticket-minerador}/references/rubrica.md

@@ -1,6 +1,6 @@
 # Rubrica, tabelas e réguas da mineração
 
-> A fonte canônica é `12-mineracao-ofertas.md` (§12.1-12.4) e `12a-mineracao-veredito.md` (§12.5) de `lowticket-metodologia`. Esta página é o fallback e a consulta rápida.
+> A fonte canônica é `12-mineracao-ofertas.md` (§12.1-12.4) e `12a-mineracao-veredito.md` (§12.5) de `wizz-lowticket-metodologia`. Esta página é o fallback e a consulta rápida.
 
 ## Veredito
 

package/src/modules/lowticket/skills/{lowticket-pagina → wizz-lowticket-pagina}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: lowticket-pagina
+name: wizz-lowticket-pagina
 description: Performance engineering for a low ticket direct-response sales page served to Meta traffic on mobile - fixes connect rate by cutting redirects, ordering the pixel, and hitting hard LCP, TTFB, CLS and page-weight targets, then reports before/after. Use when connect rate is below 92%, when a sales page is slow on mobile, or when building a new low ticket page. Do NOT use to write or restructure the copy, the offer or the price - this skill is the engineer, not the copywriter - and do NOT use for institutional sites or apps.
 ---
 
@@ -26,13 +26,13 @@ That creates two clocks, and both have to be optimized:
 
 ## Honest boundary, say it early
 
-Speed fixes the leak between the click and the page. It does not fix a bad offer, a bad creative or a bad checkout. **If connect rate is already above 92%, the problem is somewhere else** and this skill is the wrong tool. Route to `lowticket-trafego` (find the real bottleneck) or `lowticket-minerador` (the offer itself).
+Speed fixes the leak between the click and the page. It does not fix a bad offer, a bad creative or a bad checkout. **If connect rate is already above 92%, the problem is somewhere else** and this skill is the wrong tool. Route to `wizz-lowticket-trafego` (find the real bottleneck) or `wizz-lowticket-minerador` (the offer itself).
 
 ## Source of truth
 
-Read the Cérebro state first (via the `cerebro` skill). If `lowticket-metodologia` is installed, read `knowledge/INDEX.md` + `knowledge/guardrails.md` and shard `06-pagina-vendas.md`, especially §6.3-6.4. Page structure and copy blocks for a pure low-ticket page live in `12c-anatomia-low-ticket.md` (the 11-block anatomy, not `12b` anymore); VSL player behavior (autoplay, progress bar, weight) is `06b-player-vsl.md`; conversion-side reasoning is `page-cro`. Where a generic skill contradicts the shard, the shard wins and you say so.
+Read the Cérebro state first (via the `cerebro` skill). If `wizz-lowticket-metodologia` is installed, read `knowledge/INDEX.md` + `knowledge/guardrails.md` and shard `06-pagina-vendas.md`, especially §6.3-6.4. Page structure and copy blocks for a pure low-ticket page live in `12c-anatomia-low-ticket.md` (the 11-block anatomy, not `12b` anymore); VSL player behavior (autoplay, progress bar, weight) is `06b-player-vsl.md`; conversion-side reasoning is `wizz-page-cro`. Where a generic skill contradicts the shard, the shard wins and you say so.
 
-**Open conflict, do not resolve it alone.** §6.3-6.4 (this skill's rule) fires the pixel direct, first in `<head>`, no tag manager. `17-rastreamento.md` installs that same pixel *inside* GTM, as part of the full GA4 + Meta + server-container stack. This is ponto 38 of `pontos-em-aberto.md` in `lowticket-metodologia`, and it is unresolved. If the page already runs tracking through GTM, do not rip the pixel out of the container to chase the speed target: ask which rule wins before touching it.
+**Open conflict, do not resolve it alone.** §6.3-6.4 (this skill's rule) fires the pixel direct, first in `<head>`, no tag manager. `17-rastreamento.md` installs that same pixel *inside* GTM, as part of the full GA4 + Meta + server-container stack. This is ponto 38 of `pontos-em-aberto.md` in `wizz-lowticket-metodologia`, and it is unresolved. If the page already runs tracking through GTM, do not rip the pixel out of the container to chase the speed target: ask which rule wins before touching it.
 
 This skill has **no memory of its own**.
 

package/src/modules/lowticket/skills/{lowticket-trafego → wizz-lowticket-trafego}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: lowticket-trafego
+name: wizz-lowticket-trafego
 description: Diagnoses a low ticket Meta Ads operation from campaign and funnel numbers, names the single bottleneck, and prescribes one action. Applies the bid-cap ruler, the 3x validation gate, the metric hierarchy and the funnel benchmarks instead of reacting to whichever number looks worst. Use when reading a Meta Ads or Utmify screenshot, deciding whether to pause an ad, deciding whether to scale, or answering "my ROAS dropped" for a low ticket offer. Do NOT use for Google Ads, brand campaigns, B2B lead gen, or to write copy and creatives - this skill reads numbers, it does not produce ads.
 ---
 
@@ -11,12 +11,12 @@ Most campaign damage is self-inflicted. An operator sees a bad number, changes t
 
 ## Source of truth
 
-The numbers live in `lowticket-metodologia`, not here. On activation, read `knowledge/INDEX.md` and `knowledge/guardrails.md` from that skill, then the shard the request needs:
+The numbers live in `wizz-lowticket-metodologia`, not here. On activation, read `knowledge/INDEX.md` and `knowledge/guardrails.md` from that skill, then the shard the request needs:
 
 - **`03-campanha-bidcap.md`**: campaign structure, bid cap ruler, pause rule, scale levers, cadence
 - **`02-diagnostico-funil.md`**: the funnel transitions and their benchmarks
 
-Where a generic paid-media skill (`paid-ads`, `analytics-tracking`) contradicts those shards, the shard wins and you say so. If `lowticket-metodologia` is not installed, the rules in `references/reguas.md` here are the fallback, and you say that too.
+Where a generic paid-media skill (`wizz-paid-ads`, `wizz-analytics-tracking`) contradicts those shards, the shard wins and you say so. If `wizz-lowticket-metodologia` is not installed, the rules in `references/reguas.md` here are the fallback, and you say that too.
 
 Read the Cérebro state before answering (via the `cerebro` skill): the account's breakeven, ticket and current bid cap are state, not knowledge. This skill has **no memory of its own** and writes none.
 
@@ -81,7 +81,7 @@ If yes, cut it down to one. Pick the bottleneck closest to the money, fix only t
 
 ## What this skill does not do
 
-- **It does not write.** Copy, headline, script, offer, product: redirect to `copywriting`, `wizz-offer-forge` or `ad-creative`. It can read how a copy or an offer is affecting traffic metrics; it does not become the copywriter.
+- **It does not write.** Copy, headline, script, offer, product: redirect to `wizz-copywriting`, `wizz-offer-forge` or `wizz-ad-creative`. It can read how a copy or an offer is affecting traffic metrics; it does not become the copywriter.
 - **It does not guess.** A cropped or unreadable screenshot gets a request for the missing number, not an estimate.
 - **It does not optimize for the sake of optimizing.** No invented problem where the data shows none.
 

package/src/modules/lowticket/skills/{lowticket-trafego → wizz-lowticket-trafego}/references/reguas.md

@@ -1,6 +1,6 @@
 # Réguas numéricas · diagnóstico de tráfego low ticket
 
-> Fallback. A fonte canônica é o shard `03-campanha-bidcap.md` e `02-diagnostico-funil.md` de `lowticket-metodologia`. Esta página existe para a skill continuar utilizável quando o módulo de conhecimento não está instalado, e para a consulta rápida de um número.
+> Fallback. A fonte canônica é o shard `03-campanha-bidcap.md` e `02-diagnostico-funil.md` de `wizz-lowticket-metodologia`. Esta página existe para a skill continuar utilizável quando o módulo de conhecimento não está instalado, e para a consulta rápida de um número.
 
 ## Bid cap
 

package/src/modules/wizz/README.md

@@ -7,11 +7,11 @@ Personalização do WIZZ para a Wizz: linguagem fácil e resumida, cada agente t
 | Agente | Ícone | Faz | Rota para (skills globais) |
 |---|---|---|---|
 | `wizz-maestro` | 🧭 | Orquestra trabalhos complexos e multi-área recebidos do router | todos os agentes wizz/wizz |
-| `wizz-designer` | 🎨 | Design visual, landing, motion, 3D | premium-landing-ui-researcher, ui-ux-pro-max, motion-3d-director, taste-skill, ui-component-curator |
-| `wizz-copy` | ✍️ | Copy, e-mail, headlines | copywriting, email-sequence, humanizer, copy-editing |
-| `wizz-seo` | 🔍 | SEO tradicional e de IA | seo-audit, ai-seo, schema-markup, programmatic-seo, site-architecture |
-| `wizz-growth` | 📈 | Marketing, CRO, lançamento, preço, churn | marketing-ideas, page-cro, launch-strategy, pricing-strategy, churn-prevention |
-| `wizz-ads` | 📢 | Mídia paga | paid-ads, ad-creative, analytics-tracking |
+| `wizz-designer` | 🎨 | Design visual, landing, motion, 3D | wizz-premium-landing-ui-researcher, wizz-ui-ux-pro-max, wizz-motion-3d-director, wizz-taste-skill, wizz-ui-component-curator |
+| `wizz-copy` | ✍️ | Copy, e-mail, headlines | wizz-copywriting, wizz-email-sequence, wizz-humanizer, wizz-copy-editing |
+| `wizz-seo` | 🔍 | SEO tradicional e de IA | wizz-seo-audit, wizz-ai-seo, wizz-schema-markup, wizz-programmatic-seo, wizz-site-architecture |
+| `wizz-growth` | 📈 | Marketing, CRO, lançamento, preço, churn | wizz-marketing-ideas, wizz-page-cro, wizz-launch-strategy, wizz-pricing-strategy, wizz-churn-prevention |
+| `wizz-ads` | 📢 | Mídia paga | wizz-paid-ads, wizz-ad-creative, wizz-analytics-tracking |
 | `wizz-memoria` | 🧠 | Memória do projeto | cerebro |
 
 Os papéis de dev/produto reusam os agentes WIZZ (Mary, John, Winston, Amelia, Sally, Paige), personalizados em PT-BR pelos overrides em `overrides/`.

package/src/modules/wizz/_shared/communication-rules.md

@@ -1,6 +1,6 @@
 # Comunicação Wizz (fonte única)
 #
-# Este arquivo é lido pelo resolver (`resolve_customization.py`) através da
+# Este arquivo é lido pelo resolver do instalador (`wizz resolve`, Node) através da
 # chave `include` em `customize.toml`/overrides. Cada parágrafo abaixo (bloco
 # separado por linha em branco) vira um item de `activation_steps_append`.
 # Editar aqui atualiza todos os agentes de uma vez. Não copie este texto

package/src/modules/wizz/_shared/despacho-barato.md

@@ -0,0 +1,9 @@
+# Despacho de trabalho barato (fonte única)
+#
+# Este arquivo é lido pelo resolver do instalador (`wizz resolve`, Node) através da
+# chave `include` em `customize.toml`/overrides. O parágrafo abaixo vira um
+# item de `activation_steps_append`. Editar aqui atualiza todos os agentes de
+# uma vez. Não copie este texto para outro toml: referencie via `include`.
+# ---
+
+Trabalho mecânico (varredura, lookup, diff repetitivo, mudança já especificada): não execute na sessão; dispare 2+ subagentes wizz-exec-haiku/wizz-exec-sonnet em paralelo, um por arquivo/módulo. O modelo da sessão é o chefe: orquestra e decide, não executa. Trabalho difícil vai pro wizz-exec-opus quando a sessão roda acima de Opus (Fable); em sessão Opus o chefe absorve esse degrau. Review de diff vai sempre pro wizz-exec-review (pinado em opus, não herda a sessão). Diga ao usuário degrau e quantidade de cada despacho. Escada completa em `_shared/model-ladder.md` e regra em `_shared/token-economy.md` do módulo wizz.