@luquimbo/bi-superpowers 5.0.0 → 5.0.2

package/README.md

@@ -7,16 +7,19 @@
 
 **BI Agent Superpowers** is an open-source toolkit that gives AI coding agents practical Power BI Desktop capabilities.
 
-It installs reusable agent skills, configures Microsoft MCP servers, and provides a small CLI called `super` so Claude Code, GitHub Copilot, Codex, Gemini CLI, and Kilo Code can work with Power BI projects using the same operating contract.
+It installs reusable agent skills, configures Microsoft MCP servers, and provides a small CLI called `super` so Codex, Claude Code, GitHub Copilot, Gemini CLI, and Kilo Code can work with Power BI projects using the same operating contract.
 
 This is not a loose prompt pack. It is a reproducible Power BI agent layer:
 
-- **4 skills** for session startup, BI project analysis, Power BI Desktop connection, and PBIR report generation.
+- **6 skills** for Power BI/project work: session startup, project bootstrap, semantic-model design and audit, DAX authoring and optimization, performance profiling with Tabular Editor 2 / BPA integration, and Power BI Desktop MCP connection.
 - **2 Microsoft MCP servers** for Power BI Desktop modeling and Microsoft Learn documentation.
 - **1 CLI** (`super`) for install, updates, local plugin generation, checks, and regeneration.
-- **Claude Code plugin artifacts** with slash commands, discoverable skills, and MCP configuration.
+- **Codex-first skill and MCP installation**, plus compatibility adapters for other agents.
+- **Claude Code plugin artifacts** for users who explicitly want that local plugin format.
 
 > Status: `v5.0.x` is the current stable release line. The v5 line standardizes every public slash command under the `/bi-*` namespace.
+>
+> Validation baseline: BI Agent Superpowers is developed and stress-tested first in **Codex**. Other agent adapters are shipped as compatibility targets and may work, but they are not currently tested end-to-end with the same depth unless a release note says otherwise.
 
 ---
 
@@ -32,7 +35,6 @@ This is not a loose prompt pack. It is a reproducible Power BI agent layer:
 - [CLI Reference](#cli-reference)
 - [Plugin File Tree](#plugin-file-tree)
 - [Requirements](#requirements)
-- [BI Report Runtime](#bi-report-runtime)
 - [Updates](#updates)
 - [What Ships To npm](#what-ships-to-npm)
 - [Development](#development)
@@ -51,12 +53,12 @@ Power BI work with AI agents usually breaks down in predictable places:
 3. The agent invents DAX, PBIR, or setup steps without validating them against real tools.
 4. Each agent has different skill and MCP configuration paths.
 
-BI Agent Superpowers fixes that by giving each supported agent the same Power BI workflow:
+BI Agent Superpowers fixes that by giving Codex the primary tested Power BI workflow and exposing the same operating contract to compatible agents:
 
 - project context through reusable skills;
 - Power BI Desktop access through the Microsoft Power BI Modeling MCP;
 - current Microsoft documentation through the Microsoft Learn MCP;
-- generated Claude Code plugin artifacts for local project work;
+- optional Claude Code plugin artifacts for local project work;
 - update checks so old plugin bundles do not silently stay stale.
 
 The goal is simple: open a Power BI project, ask your agent for help, and have the agent know what tools, files, prerequisites, and guardrails apply.
@@ -67,7 +69,7 @@ The goal is simple: open a Power BI project, ask your agent for help, and have t
 
 ### All Supported Agents
 
-Use this when you want one command path for Claude Code, GitHub Copilot, Codex, Gemini CLI, and Kilo Code.
+Use this when you want one command path for Codex and the compatibility adapters for Claude Code, GitHub Copilot, Gemini CLI, and Kilo Code.
 
 ```bash
 npm install -g @luquimbo/bi-superpowers
@@ -106,7 +108,7 @@ super install --agent kilo --yes
 
 ### Claude Code Marketplace Install
 
-If you only use Claude Code, the marketplace path is the cleanest install experience:
+If you use Claude Code, the marketplace path is the cleanest install experience for that agent. Claude Code is a compatibility target; Codex remains the primary end-to-end validation baseline.
 
 ```text
 /plugin marketplace add luquimbo/bi-superpowers
@@ -271,7 +273,7 @@ Use it when:
 
 ### `bi-connect`
 
-Power BI Desktop connection skill. It helps the agent connect to the open Power BI Desktop model through the Microsoft Power BI Modeling MCP.
+Power BI Desktop connection skill. It helps the agent connect to the open Power BI Desktop model through the Microsoft Power BI Modeling MCP. Model writes go through MCP; PBIP files are treated as saved/exported version-control snapshots.
 
 Use it when:
 
@@ -280,20 +282,6 @@ Use it when:
 - you want the agent to inspect or modify the semantic model through Desktop.
 - you want to write or review DAX user-defined functions using current Microsoft Learn syntax and DAXLIB patterns.
 
-### `bi-report`
-
-PBIR report generation skill. It turns a ready semantic model into Power BI report pages using bundled Node scripts, PBIR references, visual allowlists, layouts, themes, and validation.
-
-Use it when:
-
-- the model is ready and you want pages;
-- you want native Power BI visuals generated as PBIR files;
-- you want a report draft that can be opened and reviewed in Power BI Desktop.
-
-Current runtime requirement: Windows + Power BI Desktop standalone + Python 3.10+ + `pipx` + `pbi-cli-tool`.
-
----
-
 ## Quick Demos
 
 ### Start A Session
@@ -305,7 +293,7 @@ Current runtime requirement: Windows + Power BI Desktop standalone + Python 3.10
 Expected result:
 
 - update check;
-- menu of 4 skills;
+- menu of 6 skills;
 - environment hints;
 - next-step recommendation.
 
@@ -321,7 +309,7 @@ Expected result:
 - project map;
 - risks and missing context;
 - recommended implementation path;
-- handoff to `bi-connect` or `bi-report` when appropriate.
+- handoff to `bi-connect` when appropriate.
 
 ### Connect To Power BI Desktop
 
@@ -350,32 +338,15 @@ Expected result:
 - DAXLIB-aware pattern selection without vendoring external code by default;
 - tested function draft and validation steps.
 
-### Generate A Report Page
-
-```text
-/bi-report
-Create an executive sales page with KPI cards, monthly trend, product ranking, and a slicer panel.
-```
-
-Expected result:
-
-- prerequisite checks;
-- page/layout plan;
-- PBIR visual generation;
-- validation against native visual types;
-- instructions to open and verify in Power BI Desktop.
-
----
-
 ## Supported Agents
 
-| Agent | Skill install path | MCP config path | Primary usage |
-|---|---|---|---|
-| Claude Code | `~/.claude/skills/` or marketplace plugin | `~/.claude.json` | Slash commands and natural language |
-| GitHub Copilot | `~/.copilot/skills/` | `~/.copilot/mcp-config.json` | Natural language with skills and MCPs |
-| Codex | `~/.agents/skills/` | `~/.codex/config.toml` | Natural language with skills and MCPs |
-| Gemini CLI | `~/.gemini/skills/` | `~/.gemini/settings.json` | Natural language |
-| Kilo Code | `~/.kilo/skills/` | `~/.kilo/mcp_settings.json` | Natural language |
+| Agent | Skill install path | MCP config path | Primary usage | Validation status |
+|---|---|---|---|---|
+| Codex | `~/.agents/skills/` | `~/.codex/config.toml` | Natural language with skills and MCPs | Primary end-to-end test baseline |
+| Claude Code | `~/.claude/skills/` or marketplace plugin | `~/.claude.json` | Slash commands and natural language | Compatibility target; not the primary end-to-end QA baseline |
+| GitHub Copilot | `~/.copilot/skills/` | `~/.copilot/mcp-config.json` | Natural language with skills and MCPs | Compatibility target; not the primary end-to-end QA baseline |
+| Gemini CLI | `~/.gemini/skills/` | `~/.gemini/settings.json` | Natural language | Compatibility target; not the primary end-to-end QA baseline |
+| Kilo Code | `~/.kilo/skills/` | `~/.kilo/mcp_settings.json` | Natural language | Compatibility target; not the primary end-to-end QA baseline |
 
 The installer always writes the universal skill copy to `~/.agents/skills/`, then links or copies agent-specific skill directories as needed.
 
@@ -412,7 +383,7 @@ bi-superpowers help
 Common commands:
 
 ```bash
-super install          # Install 4 skills + 2 MCPs for selected agents
+super install          # Install 6 skills + 2 MCPs for selected agents
 super kickoff          # Advanced: generate optional local Claude Code plugin files
 super recharge         # Regenerate optional local Claude Code plugin artifacts
 super powers           # List available skills
@@ -449,8 +420,7 @@ project/
 ├─ commands/
 │  ├─ bi-start.md
 │  ├─ bi-kickoff.md
-│  ├─ bi-connect.md
-│  └─ bi-report.md
+│  └─ bi-connect.md
 ├─ skills/
 │  ├─ bi-start/
 │  │  ├─ SKILL.md
@@ -461,22 +431,6 @@ project/
 │  ├─ bi-connect/
 │  │  ├─ SKILL.md
 │  │  └─ scripts/update-check.js
-│  └─ bi-report/
-│     ├─ SKILL.md
-│     ├─ scripts/
-│     │  ├─ apply-theme.js
-│     │  ├─ create-visual.js
-│     │  ├─ ensure-pbi-cli.sh
-│     │  ├─ update-check.js
-│     │  └─ validate-pbir.js
-│     └─ references/
-│        ├─ cli-commands.md
-│        ├─ cli-setup.md
-│        ├─ native-visuals.md
-│        ├─ pbi-desktop-installation.md
-│        ├─ troubleshooting.md
-│        ├─ layouts/
-│        └─ themes/
 └─ config.json
 ```
 
@@ -510,39 +464,6 @@ flowchart TD
 - Power BI Desktop open.
 - Power BI Modeling MCP available to the agent.
 
-### For `bi-report`
-
-- Windows.
-- Power BI Desktop standalone, not the Microsoft Store build.
-- Python 3.10 or newer.
-- `pipx`.
-- `pbi-cli-tool`.
-- PBIR/TMDL enabled when applicable.
-
----
-
-## BI Report Runtime
-
-`bi-report` uses bundled Node scripts for PBIR visual and theme authoring:
-
-- `create-visual.js`
-- `apply-theme.js`
-- `validate-pbir.js`
-
-It still uses `pbi-cli-tool` for the current runtime flow:
-
-- `pbi connect`
-- `pbi measure list`
-- `pbi table list`
-- `pbi column list`
-- `pbi report add-page`
-- `pbi report list-pages`
-- `pbi report validate`
-
-This means `pbi-cli-tool` is not optional for `bi-report` today.
-
----
-
 ## Updates
 
 ### Claude Code Marketplace
@@ -583,6 +504,7 @@ bin/
 commands/
 skills/
 src/content/
+templates/
 desktop-extension/
 config.json
 config.example.json
@@ -597,16 +519,16 @@ The npm package does not include:
 
 ```text
 docs/superpowers/
-examples/smoke-test/
 validation/
 validation.local.example.json
 validation.local.json
 node_modules/
 *.test.js
+**/.pbi/localSettings.json
 ```
 
-`examples/smoke-test/` is intentionally repo-only. It is used for QA and manual validation, not for user installs.
-`validation/` is also repo-only. It stores sanitized validation descriptors and playbooks for project QA; private project paths live in `validation.local.json`, which must never be committed.
+`templates/` ships canonical reference templates (today: `templates/sales/`). Each template is a complete PBIP package with `AGENTS.md`, semantic model, and report definition — used as the canonical "template-as-reference" by all specialist skills, and as the source for the upcoming `bi-kickoff` "create from template" branch (which will copy `templates/<domain>/` into `<user-repo>/pbip-files/<projectName>.*` with renaming).
+`validation/` is repo-only. It stores sanitized validation descriptors and playbooks for project QA; private project paths live in `validation.local.json`, which must never be committed.
 
 ---
 
@@ -661,7 +583,7 @@ Power BI work without committing customer repositories.
 Public fixtures live in:
 
 ```text
-examples/smoke-test/
+templates/sales/
 ```
 
 Sanitized validation metadata lives in:
@@ -683,7 +605,7 @@ map client projects on your own machine.
 Run the structural validation:
 
 ```bash
-super validate-projects --project super-test
+super validate-projects --project sales-template
 ```
 
 Run every descriptor, treating skipped private projects as failures:
@@ -751,10 +673,6 @@ If npm's global bin directory is not in `PATH`, fix `PATH` or use your package m
 3. Confirm the Power BI Modeling MCP is installed.
 4. Restart the agent after MCP installation.
 
-### `bi-report` Stops Because Power BI Desktop Is The Microsoft Store Build
-
-Install the standalone Power BI Desktop build. The Store build can block flows required by CLI/MCP tooling.
-
 ### `pbi-cli-tool` Is Missing
 
 Install Python, `pipx`, and `pbi-cli-tool`:
@@ -772,19 +690,17 @@ pbi --version
 
 ### Does This Replace Power BI Desktop?
 
-No. Power BI Desktop remains the visual/runtime verification tool. The plugin helps agents work with project files, MCPs, PBIR, and semantic-model context more reliably.
+No. Power BI Desktop remains the visual and report authoring tool. The plugin helps agents inspect project files and use MCPs for semantic-model work, but PBIP files are treated as version-control snapshots. Agents must not patch `.Report/**` PBIR JSON, `visual.json`, bookmarks, slicer/card settings, themes, or report resources directly.
+
+The only report-side exception is template adaptation through the dedicated plugin field-swap/rebind command. Agents must not patch PBIR JSON by hand, even for a "simple measure replacement." The command may write PBIR only for data bindings (`projections`, `prototypeQuery`, query refs, field parameters, and sort/filter field references when required), with dry-run, backup, validation, and an explicit source-to-target mapping. It must preserve visual type, layout, formatting, interactions, IDs, theme, and bookmarks. Until that tool exists, report field swaps remain manual Desktop work.
 
 ### Does It Work Outside Windows?
 
-The CLI and several skills can run outside Windows. Workflows that depend on Power BI Desktop, especially `bi-connect` and `bi-report`, are Windows-first.
+The CLI and several skills can run outside Windows. Workflows that depend on Power BI Desktop, especially `bi-connect`, are Windows-first.
 
 ### Do I Need Claude Code?
 
-No. Claude Code has the richest plugin/slash-command experience, but the npm installer supports GitHub Copilot, Codex, Gemini CLI, and Kilo Code too.
-
-### Do I Need `pbi-cli-tool`?
-
-For `bi-report`, yes. For `bi-start`, `bi-kickoff`, and `bi-connect`, not necessarily.
+No. Codex is the primary development and end-to-end validation baseline for this plugin. Claude Code has a useful compatibility path through marketplace/local plugin artifacts, but it is not the canonical test base unless a release note explicitly says that release was tested there.
 
 ### Can I Use Only The MCP Servers?
 

package/bin/cli.js

@@ -159,7 +159,7 @@ Usage:
   super <command> [options]
 
 Primary commands:
-  install           Install the 4 skills + 2 MCPs user-level across your AI agents
+  install           Install ${TOTAL_SKILL_COUNT || 'the'} skills + 2 MCPs user-level across your AI agents
   kickoff [path]    Optional: generate a repo-local Claude Code plugin
   recharge [path]   Optional: regenerate an existing repo-local Claude Code plugin
   build-desktop     Build the .mcpb extension for Claude Desktop

package/bin/commands/diff.js

@@ -331,8 +331,8 @@ function diffCommand(args, config) {
   let skillFiles = [];
 
   if (options.skill) {
-    // normalizeSkillName accepts `dax`, `dax.md`, `bi-report`, or
-    // `bi-report/SKILL.md` and returns the canonical skill name.
+    // normalizeSkillName accepts `dax`, `dax.md`, `folder-skill`, or
+    // `folder-skill/SKILL.md` and returns the canonical skill name.
     const skill = skillsByName.get(normalizeSkillName(options.skill));
     if (skill) {
       skillFiles = [skill.path];

package/bin/commands/install.js

@@ -18,10 +18,8 @@
  * expected config file in the format that agent requires (JSON for
  * most, TOML for Codex) — see `lib/mcp-config.js` for details.
  *
- * Fully open source (MIT). The user-facing messages are in Spanish to
- * match the primary Spanish-speaking audience of the project; code
- * comments and JSDoc stay in English so contributors from any language
- * can work on the source.
+ * Fully open source (MIT). CLI copy, comments, and JSDoc stay in English
+ * so contributors from any language can work on the source.
  *
  * Usage:
  *   npx @luquimbo/bi-superpowers install
@@ -89,8 +87,8 @@ async function selectMultiple(rl, items, preselected = []) {
     console.log(`  ${i + 1}) ${marker} ${item.name}`);
   });
   console.log();
-  console.log('  Ingresá números separados por comas (ej: 1,2,3)');
-  console.log('  Presioná Enter para los detectados, o "a" para todos');
+  console.log('  Enter numbers separated by commas (for example: 1,2,3)');
+  console.log('  Press Enter for detected agents, or "a" for all agents');
 
   const answer = await prompt(rl, '\n  > ');
 
@@ -161,11 +159,11 @@ function copySkillDir(srcDir, destDir) {
  */
 function formatFsError(err, context) {
   const codeHints = {
-    EACCES: 'Permiso denegado. Revisá los permisos del directorio.',
-    EPERM: 'Operación no permitida. En Windows, probá ejecutar como Administrador.',
-    ENOSPC: 'No hay espacio en disco.',
-    ENOENT: 'Archivo o directorio no existe.',
-    EROFS: 'Sistema de archivos en solo lectura.',
+    EACCES: 'Permission denied. Check the directory permissions.',
+    EPERM: 'Operation not permitted. On Windows, try running as Administrator.',
+    ENOSPC: 'No disk space left.',
+    ENOENT: 'File or directory does not exist.',
+    EROFS: 'Read-only filesystem.',
   };
   const hint = codeHints[err.code] || '';
   return `${context}: ${err.message}${hint ? `\n  ${hint}` : ''}`;
@@ -188,7 +186,9 @@ function parseArgs(args) {
       const next = args[i + 1];
       if (next === undefined || next.startsWith('-')) {
         // Missing value — warn and skip this flag instead of crashing.
-        console.warn(`⚠ Flag ${args[i]} sin valor. Uso: ${args[i]} <agente-id>. Ignorando.`);
+        console.warn(
+          `⚠ Flag ${args[i]} is missing a value. Usage: ${args[i]} <agent-id>. Ignoring.`
+        );
         continue;
       }
       opts.agentFlags.push(next);
@@ -212,8 +212,8 @@ async function resolveSelectedAgents(opts, baseDir, chalk) {
     const known = opts.agentFlags.filter((a) => AGENTS[a]);
     const unknown = opts.agentFlags.filter((a) => !AGENTS[a]);
     if (unknown.length > 0) {
-      console.log(chalk.yellow(`  Agentes desconocidos: ${unknown.join(', ')}`));
-      console.log(chalk.gray(`  Disponibles: ${Object.keys(AGENTS).join(', ')}\n`));
+      console.log(chalk.yellow(`  Unknown agents: ${unknown.join(', ')}`));
+      console.log(chalk.gray(`  Available agents: ${Object.keys(AGENTS).join(', ')}\n`));
     }
     return known;
   }
@@ -224,11 +224,11 @@ async function resolveSelectedAgents(opts, baseDir, chalk) {
 
   // Interactive mode — detect installed agents and prompt the user.
   const detected = detectAgents(baseDir);
-  console.log(chalk.cyan('  Seleccioná los agentes donde querés instalar:\n'));
+  console.log(chalk.cyan('  Select the agents where you want to install:\n'));
 
   const items = Object.entries(AGENTS).map(([id, agent]) => ({
     id,
-    name: detected.includes(id) ? `${agent.name} ${chalk.green('(detectado)')}` : agent.name,
+    name: detected.includes(id) ? `${agent.name} ${chalk.green('(detected)')}` : agent.name,
   }));
 
   const rl = createReadline();
@@ -330,9 +330,7 @@ function performInstall(skillsSourceDir, skillDirs, selectedAgents, baseDir) {
  * @returns {Array<{agent: string, success: boolean, configPath?: string, error?: string}>}
  */
 function configureMcpsForAgents(selectedAgents, packageDir, baseDir, chalk) {
-  console.log(
-    chalk.cyan('\n  Configurando MCP servers (Power BI Modeling + Microsoft Learn)...\n')
-  );
+  console.log(chalk.cyan('\n  Configuring MCP servers (Power BI Modeling + Microsoft Learn)...\n'));
 
   const results = [];
   for (const agentId of selectedAgents) {
@@ -374,7 +372,7 @@ async function installCommand(args, config) {
   if (!fs.existsSync(skillsSourceDir)) {
     console.error(
       chalk.red(
-        'Directorio de skills no encontrado. Reinstalá el paquete con: npm install -g @luquimbo/bi-superpowers'
+        'Skills directory not found. Reinstall the package with: npm install -g @luquimbo/bi-superpowers'
       )
     );
     process.exit(1);
@@ -390,7 +388,7 @@ async function installCommand(args, config) {
       )
       .map((d) => d.name);
   } catch (err) {
-    console.error(chalk.red(formatFsError(err, 'No pude leer los skills')));
+    console.error(chalk.red(formatFsError(err, 'Could not read skills')));
     process.exit(1);
   }
 
@@ -400,7 +398,7 @@ async function installCommand(args, config) {
       chalk.bold.cyan('BI Agent Superpowers') +
         chalk.gray(` v${config.version}`) +
         '\n' +
-        chalk.gray('Instalador multi-agente'),
+        chalk.gray('Multi-agent installer'),
       {
         padding: 1,
         borderStyle: 'round',
@@ -409,21 +407,19 @@ async function installCommand(args, config) {
     )
   );
 
-  console.log(chalk.gray(`  Ruta de instalación: ~/${UNIVERSAL_DIR}/`));
-  console.log(chalk.gray(`  Skills: ${skillDirs.length} disponibles\n`));
+  console.log(chalk.gray(`  Install path: ~/${UNIVERSAL_DIR}/`));
+  console.log(chalk.gray(`  Skills available: ${skillDirs.length}\n`));
 
   // Resolve which agents to configure.
   const selectedAgents = await resolveSelectedAgents(opts, baseDir, chalk);
 
   if (selectedAgents.length === 0) {
-    console.log(chalk.yellow('\n  Ningún agente seleccionado. Nada que instalar.'));
+    console.log(chalk.yellow('\n  No agent selected. Nothing to install.'));
     return;
   }
 
   console.log(
-    chalk.cyan(
-      `\n  Instalando ${skillDirs.length} skills para ${selectedAgents.length} agentes...\n`
-    )
+    chalk.cyan(`\n  Installing ${skillDirs.length} skills for ${selectedAgents.length} agents...\n`)
   );
 
   // Phase 1: copy skills and create symlinks per agent.
@@ -434,7 +430,7 @@ async function installCommand(args, config) {
     agentResults = result.agentResults;
     copyFallbacks = result.copyFallbacks;
   } catch (err) {
-    console.error(chalk.red(formatFsError(err, 'Falló la instalación de skills')));
+    console.error(chalk.red(formatFsError(err, 'Skill installation failed')));
     process.exit(1);
   }
 
@@ -455,9 +451,9 @@ async function installCommand(args, config) {
   if (copyFallbacks > 0) {
     console.log(
       chalk.yellow(
-        `\n  ⚠ ${copyFallbacks} agente(s) usaron copia en vez de symlink ` +
-          '(probable Windows sin permisos de admin).\n' +
-          "    Re-ejecutá 'super install' tras cada upgrade; la copia se espeja y elimina runtimes viejos."
+        `\n  ⚠ ${copyFallbacks} agent(s) used copy fallback instead of symlink ` +
+          '(probably Windows without admin permissions).\n' +
+          "    Re-run 'super install' after each upgrade; copied installs are mirrored and stale runtimes are removed."
       )
     );
   }
@@ -471,36 +467,34 @@ async function installCommand(args, config) {
   const mcpFailures = mcpResults.filter((r) => !r.success);
   const hasFailures = mcpFailures.length > 0;
 
-  const successMsg = `Instalados ${skillDirs.length} skills + 2 MCPs para ${totalAgents} agentes`;
-  const failureMsg = `Instalados ${skillDirs.length} skills. MCPs: ${mcpSuccess}/${mcpResults.length} agentes ✓, ${mcpFailures.length} con errores.`;
+  const successMsg = `Installed ${skillDirs.length} skills + 2 MCPs for ${totalAgents} agents`;
+  const failureMsg = `Installed ${skillDirs.length} skills. MCPs: ${mcpSuccess}/${mcpResults.length} agents ok, ${mcpFailures.length} failed.`;
   const headerLine = hasFailures ? chalk.yellow.bold(failureMsg) : chalk.green.bold(successMsg);
 
   const failureDetail = hasFailures
     ? '\n' +
-      chalk.red('Agentes con errores en MCP:') +
+      chalk.red('Agents with MCP errors:') +
       '\n' +
       mcpFailures.map((r) => chalk.red(`  ✗ ${r.agent}: ${r.error}`)).join('\n') +
       '\n'
     : '';
 
+  const skillSummary = skillDirs
+    .map((skillName) => `  /${skillName.padEnd(15)} — ${describeSkill(skillName)}`)
+    .join('\n');
+
   console.log(
     boxen(
       headerLine +
         failureDetail +
         '\n\n' +
-        chalk.gray(`MCPs configurados en ${mcpSuccess}/${mcpResults.length} agentes.`) +
+        chalk.gray(`MCPs configured in ${mcpSuccess}/${mcpResults.length} agents.`) +
         '\n' +
-        chalk.gray('Reiniciá tu agente AI para que tome los MCPs nuevos.') +
+        chalk.gray('Restart your AI agent so it loads the new MCP configuration.') +
         '\n\n' +
-        chalk.gray('Los 4 skills disponibles:') +
-        '\n' +
-        chalk.gray('  /bi-start         — Arrancar una sesión: menú + update + conexión') +
+        chalk.gray(`Skills available (${skillDirs.length}):`) +
         '\n' +
-        chalk.gray('  /bi-kickoff  — Analizá tu proyecto BI (proyecto nuevo)') +
-        '\n' +
-        chalk.gray('  /bi-connect      — Conectá Power BI + guía UDF DAX') +
-        '\n' +
-        chalk.gray('  /bi-report    — Generá reportes PBIR para Power BI Desktop (Windows)'),
+        chalk.gray(skillSummary),
       {
         padding: 1,
         margin: { top: 1 },
@@ -526,3 +520,22 @@ module.exports.copySkillDir = copySkillDir;
 module.exports.formatFsError = formatFsError;
 module.exports.AGENTS = AGENTS;
 module.exports.UNIVERSAL_DIR = UNIVERSAL_DIR;
+
+function describeSkill(skillName) {
+  switch (skillName) {
+    case 'bi-start':
+      return 'Session opener, update check, and routing';
+    case 'bi-kickoff':
+      return 'Analyze or start a new BI project';
+    case 'bi-modeling':
+      return 'Design and audit semantic models';
+    case 'bi-dax':
+      return 'Write, debug, and optimize DAX';
+    case 'bi-performance':
+      return 'Performance profiling, VertiPaq, and BPA';
+    case 'bi-connect':
+      return 'Connect Power BI Desktop and guide DAX UDF work';
+    default:
+      return 'Specialized BI skill';
+  }
+}

package/bin/commands/lint.js

@@ -366,7 +366,7 @@ function lintCommand(args, config) {
   // Determine which files to lint. Use the shared skill loader so we
   // catch both flat (`<name>.md`) and folder-based (`<name>/SKILL.md`)
   // skills — a previous version filtered with `f.endsWith('.md')` and
-  // silently skipped every folder-based skill (e.g. `bi-report`).
+  // silently skipped every folder-based skill.
   const allSkills = readSkillDirectory(skillsDir);
   const skillsByName = new Map(allSkills.map((s) => [s.name, s]));
   let filesToLint = [];
@@ -379,7 +379,7 @@ function lintCommand(args, config) {
           return f;
         }
         // Look up by skill name. normalizeSkillName accepts `dax`,
-        // `dax.md`, `bi-report`, or `bi-report/SKILL.md`.
+        // `dax.md`, `folder-skill`, or `folder-skill/SKILL.md`.
         const skill = skillsByName.get(normalizeSkillName(f));
         if (skill) return skill.path;
 

package/bin/commands/validate-projects.js

@@ -9,7 +9,7 @@
  *
  * Usage:
  *   super validate-projects
- *   super validate-projects --project super-test
+ *   super validate-projects --project sales-template
  *   super validate-projects --root C:\path\to\bi-superpowers
  */
 

package/bin/lib/generators/claude-plugin.js

@@ -20,12 +20,21 @@ const {
 } = require('../microsoft-mcp');
 const { parseSkillMetadata, getSkillPurpose } = require('./shared');
 
-// Currently the plugin ships 4 skills (bi-start, bi-kickoff,
-// bi-connect, bi-report). bi-start is the session-opener that
-// routes to the other three; the rest are specialists.
+// Currently the plugin ships 6 command skills:
+// - bi-start: session-opener that routes to the BI specialists.
+// - bi-kickoff: new-project bootstrap with AGENTS.md scaffolding.
+// - bi-modeling / bi-dax / bi-performance: model design, DAX, profiling.
+// - bi-connect: MCP connection + DAX UDFs.
 // The old reference-skills split is kept as an empty set so that any
 // downstream code that checks `REFERENCE_SKILLS.has(x)` still works.
-const COMMAND_SKILLS = new Set(['bi-start', 'bi-kickoff', 'bi-connect', 'bi-report']);
+const COMMAND_SKILLS = new Set([
+  'bi-start',
+  'bi-kickoff',
+  'bi-modeling',
+  'bi-dax',
+  'bi-performance',
+  'bi-connect',
+]);
 
 const REFERENCE_SKILLS = new Set();
 
@@ -163,7 +172,7 @@ node "{skillBundleDir}/scripts/update-check.js" --silent-if-uptodate --silent-if
 
 - Empty output or \`UPTODATE\` — proceed with the skill silently. No message.
 - \`UPDATE_AVAILABLE <installed> <latest>\` — tell the user exactly once this conversation, before diving into the skill:
-  > "Hay **bi-superpowers v{latest}** disponible (estás en v{installed}). Actualizá con \`super upgrade\` (o \`/plugin update bi-superpowers\` en Claude Code) cuando te venga bien. Si estás usando un plugin local generado con \`super kickoff\`, después corré \`super recharge\` en ese repo."
+  > "bi-superpowers v{latest} is available (you are on v{installed}). Update with \`super upgrade\` (or \`/plugin update bi-superpowers\` in Claude Code) when convenient. If you use a local plugin generated with \`super kickoff\`, run \`super recharge\` in that repo afterwards."
 
   Then continue with the skill below.
 - \`SNOOZED <iso>\` — proceed silently.

package/bin/lib/generators/shared.js

@@ -65,9 +65,15 @@ function parseSkillMetadata(content) {
  */
 const SKILL_PURPOSES = {
   'bi-start': 'Session opener — environment snapshot, update check, and routing to other skills',
-  'bi-kickoff': 'Project analysis and planning',
-  'bi-connect': 'Power BI Desktop connection and DAX UDF authoring',
-  'bi-report': '3-page PBIR report generation for Power BI Desktop (Windows)',
+  'bi-kickoff':
+    'New-project bootstrap — AGENTS.md, ROADMAP.md, foundation model with fictitious data',
+  'bi-modeling':
+    'Semantic model design and audit — star schema, relationships, Date Table, health checklist',
+  'bi-dax':
+    'DAX authoring, debugging, and optimization — measures, calculation groups, SE/FE timing, Sallieri patterns',
+  'bi-performance':
+    'Performance profiling — Performance Analyzer, VertiPaq DMVs, refresh diagnostics, Tabular Editor 2 / BPA',
+  'bi-connect': 'Power BI Desktop MCP connection and DAX UDF authoring',
 };
 
 /**
@@ -205,8 +211,6 @@ function getFormatFooter() {
 ## Resources
 
 - Skills: \`skills/*/SKILL.md\` - BI workflow instructions
-- Report design references: \`skills/bi-report/references/\` - PBIR layouts, themes, native visuals, and troubleshooting
-- Runtime scripts: \`skills/bi-report/scripts/\` - PBIR visual, theme, and validation helpers
 
 ---