npm - @cubis/foundry - Versions diffs - 0.3.82 → 0.3.83 - Mend

@cubis/foundry 0.3.82 → 0.3.83

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (633) hide show

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/electron-qa/SKILL.md CHANGED Viewed

@@ -80,8 +80,12 @@ Deliver:
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/expo-app/SKILL.md CHANGED Viewed

@@ -86,8 +86,12 @@ Guide the design and implementation of production-grade Expo applications using
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/express-nodejs/SKILL.md CHANGED Viewed

@@ -73,8 +73,12 @@ Load only what the current step needs.
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/fastapi/SKILL.md CHANGED Viewed

@@ -67,8 +67,12 @@ Provide implementation code, Pydantic model definitions, dependency functions, c
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/frontend-design/SKILL.md CHANGED Viewed

@@ -84,8 +84,12 @@ Load only what the current task requires.
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/gin-golang/SKILL.md CHANGED Viewed

@@ -69,8 +69,12 @@ Load only what the current step needs.
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/git-workflow/SKILL.md CHANGED Viewed

@@ -61,8 +61,12 @@ When advising on git workflows, provide:
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/go-fiber/SKILL.md CHANGED Viewed

@@ -69,8 +69,12 @@ Load only what the current step needs.
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/golang-best-practices/SKILL.md CHANGED Viewed

@@ -72,8 +72,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/google-workspace/SKILL.md CHANGED Viewed

@@ -84,8 +84,12 @@ Guide the design and implementation of production-grade Google Workspace API int
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/huggingface-ml/SKILL.md CHANGED Viewed

@@ -83,8 +83,12 @@ Guide the design and implementation of machine learning workflows using the Hugg
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/integration-testing/SKILL.md CHANGED Viewed

@@ -98,8 +98,12 @@ Provide a structured methodology for writing integration tests that verify corre
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/java-best-practices/SKILL.md CHANGED Viewed

@@ -67,8 +67,12 @@ Produces Java code using records, sealed types, pattern matching switch expressi
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/javascript-best-practices/SKILL.md CHANGED Viewed

@@ -67,8 +67,12 @@ Produces JavaScript code using ESM modules, native runtime APIs, explicit async
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/kaizen-iteration/SKILL.md CHANGED Viewed

@@ -93,8 +93,12 @@ Provide a structured, metrics-driven framework for continuous improvement in sof
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/kotlin-best-practices/SKILL.md CHANGED Viewed

@@ -67,8 +67,12 @@ Produces Kotlin code using data classes, sealed hierarchies, structured coroutin
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/kubernetes-deploy/SKILL.md CHANGED Viewed

@@ -71,8 +71,12 @@ Provide complete Kubernetes manifests in YAML with inline comments explaining no
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/laravel/SKILL.md CHANGED Viewed

@@ -61,8 +61,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/llm-eval/SKILL.md CHANGED Viewed

@@ -67,8 +67,12 @@ Provide eval suite designs as structured JSON or YAML with assertion definitions
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/mcp-server-builder/SKILL.md CHANGED Viewed

@@ -83,8 +83,12 @@ Guide the design and implementation of production-grade Model Context Protocol (
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/microservices-design/SKILL.md CHANGED Viewed

@@ -77,8 +77,12 @@ Load only what the current task requires.
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/nestjs/SKILL.md CHANGED Viewed

@@ -67,8 +67,12 @@ Provide implementation code, module definitions, decorator usage, configuration
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/nextjs/SKILL.md CHANGED Viewed

@@ -80,8 +80,12 @@ Load detailed guidance based on context:
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/observability/SKILL.md CHANGED Viewed

@@ -71,8 +71,12 @@ Provide complete instrumentation code, configuration files, and alert rule defin
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/owasp-security-review/SKILL.md CHANGED Viewed

@@ -96,8 +96,12 @@ Perform structured, OWASP-standards-based security reviews of application code a
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/pentest-skill/SKILL.md CHANGED Viewed

@@ -97,8 +97,12 @@ Provide structured guidance for authorized penetration testing engagements follo
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/performance-testing/SKILL.md CHANGED Viewed

@@ -111,8 +111,12 @@ Provide a systematic methodology for designing, executing, and interpreting perf
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/php-best-practices/SKILL.md CHANGED Viewed

@@ -80,8 +80,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.

package/workflows/workflows/agent-environment-setup/platforms/gemini/skills/playwright-interactive/SKILL.md CHANGED Viewed

@@ -78,8 +78,12 @@ Deliver:
 ## Gemini Platform Notes
-- Use `activate_skill` to invoke skills by name from Gemini CLI or Gemini Code Assist.
-- Skill files are stored under `.gemini/skills/` in the project root.
-- Gemini does not support `context: fork` — all skill execution is inline.
+- Workflow and agent routes are compiled into `.gemini/commands/*.toml` TOML command files.
+- Commands use `{{args}}` for user input, `!{shell command}` for shell output, `@{file}` for file content.
+- Specialists are internal postures (modes of reasoning), not spawned subagent processes.
+- Gemini does not support `context: fork` — all skill execution is inline within the current session.
+- Skills are loaded via MCP when the Cubis Foundry MCP server is configured. Local `.agents/skills/` paths serve as hints.
 - User arguments are passed as natural language in the activation prompt.
-- Reference files are loaded relative to the skill directory under `.gemini/skills/<skill-id>/`.
+- Rules file: `.gemini/GEMINI.md`.
+- Reference files are loaded relative to the skill directory under `.agents/skills/<skill-id>/`.
+- MCP skill tools (`skill_search`, `skill_get`, `skill_validate`, `skill_get_reference`) are available when MCP is connected.