@cubis/foundry 0.3.82 → 0.3.84

package/workflows/workflows/agent-environment-setup/platforms/copilot/skills/python-best-practices/SKILL.md

@@ -81,8 +81,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 
 ## Copilot Platform Notes
 
-- Skill files are stored under `.github/prompts/` (prompt files) and `.github/instructions/` (instruction files).
-- Copilot does not support subagent spawning — all skill guidance executes within the current conversation context.
+- Custom agents live under `../../agents/` relative to the mirrored skill directory and use YAML frontmatter such as `name`, `description`, `tools`, `model`, and `handoffs`.
+- Agent `handoffs` can guide workflow transitions (for example, `@planner` → `@implementer`).
+- Skill files are stored under `.github/skills/` (skill markdown) and `.github/prompts/` (prompt files).
+- Path-scoped instructions live under `../../instructions/` and provide file-pattern-targeted guidance via `applyTo` frontmatter.
 - User arguments are provided as natural language input in the prompt, not through a `$ARGUMENTS` variable.
-- Frontmatter keys `context`, `agent`, and `allowed-tools` are not supported; guidance is advisory only.
+- Frontmatter keys `context: fork` and `allowed-tools` are not natively supported; guidance is advisory.
 - Reference files can be included via `#file:references/<name>.md` syntax in Copilot Chat.
+- MCP configuration lives in `.vscode/mcp.json`. MCP skill tools are available when configured.
+- Rules file relative to the mirrored skill directory: `../../rules/copilot-instructions.md` — broad and stable, not task-specific.

package/workflows/workflows/agent-environment-setup/platforms/copilot/skills/react/SKILL.md

@@ -85,8 +85,12 @@ Load detailed guidance based on context:
 
 ## Copilot Platform Notes
 
-- Skill files are stored under `.github/prompts/` (prompt files) and `.github/instructions/` (instruction files).
-- Copilot does not support subagent spawning — all skill guidance executes within the current conversation context.
+- Custom agents live under `../../agents/` relative to the mirrored skill directory and use YAML frontmatter such as `name`, `description`, `tools`, `model`, and `handoffs`.
+- Agent `handoffs` can guide workflow transitions (for example, `@planner` → `@implementer`).
+- Skill files are stored under `.github/skills/` (skill markdown) and `.github/prompts/` (prompt files).
+- Path-scoped instructions live under `../../instructions/` and provide file-pattern-targeted guidance via `applyTo` frontmatter.
 - User arguments are provided as natural language input in the prompt, not through a `$ARGUMENTS` variable.
-- Frontmatter keys `context`, `agent`, and `allowed-tools` are not supported; guidance is advisory only.
+- Frontmatter keys `context: fork` and `allowed-tools` are not natively supported; guidance is advisory.
 - Reference files can be included via `#file:references/<name>.md` syntax in Copilot Chat.
+- MCP configuration lives in `.vscode/mcp.json`. MCP skill tools are available when configured.
+- Rules file relative to the mirrored skill directory: `../../rules/copilot-instructions.md` — broad and stable, not task-specific.

package/workflows/workflows/agent-environment-setup/platforms/copilot/skills/rust-best-practices/SKILL.md

@@ -81,8 +81,12 @@ No helper scripts are required for this skill right now. Keep execution in `SKIL
 
 ## Copilot Platform Notes
 
-- Skill files are stored under `.github/prompts/` (prompt files) and `.github/instructions/` (instruction files).
-- Copilot does not support subagent spawning — all skill guidance executes within the current conversation context.
+- Custom agents live under `../../agents/` relative to the mirrored skill directory and use YAML frontmatter such as `name`, `description`, `tools`, `model`, and `handoffs`.
+- Agent `handoffs` can guide workflow transitions (for example, `@planner` → `@implementer`).
+- Skill files are stored under `.github/skills/` (skill markdown) and `.github/prompts/` (prompt files).
+- Path-scoped instructions live under `../../instructions/` and provide file-pattern-targeted guidance via `applyTo` frontmatter.
 - User arguments are provided as natural language input in the prompt, not through a `$ARGUMENTS` variable.
-- Frontmatter keys `context`, `agent`, and `allowed-tools` are not supported; guidance is advisory only.
+- Frontmatter keys `context: fork` and `allowed-tools` are not natively supported; guidance is advisory.
 - Reference files can be included via `#file:references/<name>.md` syntax in Copilot Chat.
+- MCP configuration lives in `.vscode/mcp.json`. MCP skill tools are available when configured.
+- Rules file relative to the mirrored skill directory: `../../rules/copilot-instructions.md` — broad and stable, not task-specific.

package/workflows/workflows/agent-environment-setup/platforms/copilot/skills/secret-management/SKILL.md

@@ -97,8 +97,12 @@ Guide the design and implementation of robust secret and credential management s
 
 ## Copilot Platform Notes
 
-- Skill files are stored under `.github/prompts/` (prompt files) and `.github/instructions/` (instruction files).
-- Copilot does not support subagent spawning — all skill guidance executes within the current conversation context.
+- Custom agents live under `../../agents/` relative to the mirrored skill directory and use YAML frontmatter such as `name`, `description`, `tools`, `model`, and `handoffs`.
+- Agent `handoffs` can guide workflow transitions (for example, `@planner` → `@implementer`).
+- Skill files are stored under `.github/skills/` (skill markdown) and `.github/prompts/` (prompt files).
+- Path-scoped instructions live under `../../instructions/` and provide file-pattern-targeted guidance via `applyTo` frontmatter.
 - User arguments are provided as natural language input in the prompt, not through a `$ARGUMENTS` variable.
-- Frontmatter keys `context`, `agent`, and `allowed-tools` are not supported; guidance is advisory only.
+- Frontmatter keys `context: fork` and `allowed-tools` are not natively supported; guidance is advisory.
 - Reference files can be included via `#file:references/<name>.md` syntax in Copilot Chat.
+- MCP configuration lives in `.vscode/mcp.json`. MCP skill tools are available when configured.
+- Rules file relative to the mirrored skill directory: `../../rules/copilot-instructions.md` — broad and stable, not task-specific.

package/workflows/workflows/agent-environment-setup/platforms/copilot/skills/skill-creator/SKILL.md

@@ -160,8 +160,12 @@ skill-creator
 
 ## Copilot Platform Notes
 
-- Skill files are stored under `.github/prompts/` (prompt files) and `.github/instructions/` (instruction files).
-- Copilot does not support subagent spawning — all skill guidance executes within the current conversation context.
+- Custom agents live under `../../agents/` relative to the mirrored skill directory and use YAML frontmatter such as `name`, `description`, `tools`, `model`, and `handoffs`.
+- Agent `handoffs` can guide workflow transitions (for example, `@planner` → `@implementer`).
+- Skill files are stored under `.github/skills/` (skill markdown) and `.github/prompts/` (prompt files).
+- Path-scoped instructions live under `../../instructions/` and provide file-pattern-targeted guidance via `applyTo` frontmatter.
 - User arguments are provided as natural language input in the prompt, not through a `$ARGUMENTS` variable.
-- Frontmatter keys `context`, `agent`, and `allowed-tools` are not supported; guidance is advisory only.
+- Frontmatter keys `context: fork` and `allowed-tools` are not natively supported; guidance is advisory.
 - Reference files can be included via `#file:references/<name>.md` syntax in Copilot Chat.
+- MCP configuration lives in `.vscode/mcp.json`. MCP skill tools are available when configured.
+- Rules file relative to the mirrored skill directory: `../../rules/copilot-instructions.md` — broad and stable, not task-specific.

package/workflows/workflows/agent-environment-setup/platforms/copilot/skills/skill-creator/references/platform-adaptations.md

@@ -105,16 +105,30 @@ allowed-tools: [Read, Edit, Write, Bash, Grep, Glob]
 ## Adaptation Strategy
 
 ### Canonical Version (workflows/skills/)
-The canonical skill in `workflows/skills/<name>/` uses the full Pro Skill Standard format with rich frontmatter. This is the source of truth.
+The canonical skill in `workflows/skills/<name>/` is the authoring source of truth.
 
-### Claude Code Mirror
-Placed at `platforms/claude/skills/<name>/SKILL.md`. Uses full Claude frontmatter. Instructions may reference `context:fork`, `$ARGUMENTS`, and `${CLAUDE_SKILL_DIR}`.
+### Generated Platform Mirrors
+Generated mirrors are maintained for Claude Code, Copilot, Codex, Gemini CLI, and Antigravity under `platforms/<platform>/skills/<name>/SKILL.md`.
 
-### Copilot Mirror
-Placed at `platforms/copilot/skills/<name>/SKILL.md`. Same as Claude (Copilot reads Claude format). May add notes about prompt files and path-scoped instructions.
+- Claude Code mirrors can use Claude-specific frontmatter and instruction references such as `context: fork`, `$ARGUMENTS`, and `${CLAUDE_SKILL_DIR}`.
+- Copilot mirrors stay Claude-compatible where useful, but Copilot-native behavior still follows Copilot's own constraints.
+- Codex, Gemini CLI, and Antigravity mirrors usually keep minimal frontmatter and rely on platform rules plus MCP/routing behavior for the rest.
+- Do not assume one mirror transform works for every asset type. Skills, custom agents, workflow projections, prompts, and command files each have different platform constraints and must be generated through their own platform-aware pipeline.
 
-### Codex, Gemini CLI, Antigravity
-These platforms use the canonical version directly, referenced by their respective rule files. No separate mirror needed — the rule files handle routing.
+### Shared Steering + Platform Overrides
+Routing and loading behavior should not be documented independently in every platform skill.
+
+- `shared/rules/STEERING.md` is the canonical routing and skill-loading source.
+- `shared/rules/overrides/<platform>.md` adds platform-specific behavior.
+- Generated platform rule files are composed from the shared steering file plus the relevant platform override.
+
+### Non-Skill Assets
+Custom agents and workflow projections are not mirrored with the same logic as skills.
+
+- Skills are mirrored with platform-specific frontmatter and body transforms.
+- Shared agents are compiled into platform-native outputs such as Claude/Copilot markdown agents or Codex TOML agents.
+- Workflows are compiled into platform-native workflow skills, command files, or prompt files depending on the target platform.
+- Regenerate these with the platform asset generator, not by copying skill directories.
 
 ## Instruction Adaptation
 
@@ -124,5 +138,5 @@ When the canonical instructions reference platform-specific features, adapt them
 |-----------|------------|-------|--------|-------------|---------|
 | "fork to subagent" | `context: fork` | "switch posture" | "activate agent" | "use workflow" | `context: fork` |
 | "load reference" | `skill_get_reference` | "read file" | `activate_skill` | "read file" | `skill_get_reference` |
-| "use MCP tool" | `skill_validate` | N/A | `activate_skill` | N/A | N/A |
+| "use MCP tool" | `skill_validate` / `skill_get` | `skill_validate` / `skill_get` when MCP is connected | `skill_validate` / `skill_get` when MCP is connected; `activate_skill` only when using Gemini-native skill loading | `skill_validate` / `skill_get` when MCP is configured | `skill_validate` / `skill_get` when MCP is configured |
 | "run script" | `Bash` | `Bash` (may be sandboxed) | Shell | Shell | `Bash` |

package/workflows/workflows/agent-environment-setup/platforms/copilot/skills/skill-creator/references/routing-integration.md

@@ -18,15 +18,21 @@ User request
 
 ## Rule File Integration
 
-Each platform has a rule file with a skill routing matrix. When adding a new skill, update the matrix in every platform's rule file.
+Rule behavior is defined canonically in the shared steering layer, then specialized per platform by overrides and generated outputs.
+
+- Update `workflows/workflows/agent-environment-setup/shared/rules/STEERING.md` when the routing contract itself changes.
+- Update `workflows/workflows/agent-environment-setup/shared/rules/overrides/<platform>.md` only for platform-specific deviations.
+- Regenerate platform rule files after canonical edits instead of hand-editing every generated platform file.
+
+Each generated platform rule file still exposes a routing matrix or equivalent skill-routing surface, but the source of truth is the shared steering + override layer.
 
 ### Skill Routing Matrix Format
 
 ```markdown
 | Skill | Category | When to Load | Primary Agent |
 |-------|----------|--------------|---------------|
-| python-best-practices | Language | Python backend, typing, async | @backend-specialist |
-| nextjs | Framework | Next.js App Router, RSC | @frontend-specialist |
+| python-best-practices | Language | Python backend, typing, async | @implementer |
+| nextjs | Framework | Next.js App Router, RSC | @implementer |
 ```
 
 ### Matrix Fields
@@ -50,7 +56,9 @@ Each platform has a rule file with a skill routing matrix. When adding a new ski
 
 ### When to Create Mirrors
 
-Create platform-specific mirrors for Claude Code and Copilot. Other platforms use the canonical version.
+Create or regenerate platform skill mirrors for every supported platform. The authoring source remains canonical under `workflows/skills/`, but the install/runtime surfaces use generated platform mirrors.
+
+This applies to skills only. Do not reuse the skill mirror process for shared agents, workflow markdown, prompt files, or command files.
 
 ### Claude Code Mirror
 
@@ -77,7 +85,18 @@ Same format as Claude (Copilot reads Claude format). Add notes about:
 
 ### Codex / Gemini / Antigravity
 
-No mirror needed. The canonical version is used directly. Routing is handled by the platform rule file.
+These platforms also receive generated skill mirrors. Keep their frontmatter minimal and let the generated rule files plus MCP/routing behavior carry the platform-specific execution model.
+
+## Agent and Workflow Projections
+
+Shared agents and workflows must go through platform-specific generators because their output format differs by platform.
+
+- Codex agents are emitted as `.toml` native agents.
+- Claude and Copilot agents are emitted as markdown with sanitized platform frontmatter.
+- Gemini and Antigravity workflows and agent routes are emitted as TOML command files.
+- Copilot workflows are emitted as prompt files rather than skill mirrors.
+
+If a change affects custom agents, workflow prompts, or command behavior, update the shared source and rerun the platform asset generator instead of relying on `sync-skill-mirrors`.
 
 ## Agent Assignment
 
@@ -85,16 +104,16 @@ Each skill should be assigned a primary agent in the routing matrix. Choose base
 
 | Domain | Primary Agent |
 |--------|---------------|
-| Languages (Python, TS, Go, etc.) | @backend-specialist or @frontend-specialist |
-| Backend frameworks | @backend-specialist |
-| Frontend frameworks | @frontend-specialist |
-| Mobile frameworks | @mobile-developer |
-| Database/ORM | @database-architect |
-| Testing | @test-engineer |
-| Security | @security-auditor |
-| DevOps | @devops-engineer |
-| Design/Architecture | @project-planner |
-| AI/ML | @researcher |
+| Languages (Python, TS, Go, etc.) | @implementer |
+| Backend frameworks | @implementer |
+| Frontend frameworks | @implementer |
+| Mobile frameworks | @implementer |
+| Database/ORM | @planner or @implementer |
+| Testing | @tester |
+| Security | @reviewer |
+| DevOps | @implementer |
+| Design/Architecture | @planner |
+| AI/ML / research | @explorer or @planner |
 | Workflow | @orchestrator |
 | Meta | @orchestrator |
 
@@ -102,17 +121,20 @@ Each skill should be assigned a primary agent in the routing matrix. Choose base
 
 After adding a skill to the routing infrastructure:
 
-1. Run `npm run test:attributes` — validates frontmatter across all skills
-2. Run `npm run check:generated-assets` — verifies platform mirrors are in sync
-3. Verify the skill appears in `npm run generate:skills-index`
-4. Test `route_resolve` with a prompt that should match the new skill
-5. Test `skill_validate` with the new skill's name
-6. Test `skill_get` to confirm the SKILL.md loads correctly
+1. Update canonical skill content under `workflows/skills/<name>/`
+2. Update shared steering or platform overrides if the routing contract changed
+3. Run `npm run generate:all` or the narrower mirror/rule/platform-asset generation commands
+4. Run `npm run test:attributes` — validates frontmatter across all skills
+5. Run `npm run check:generated-assets` — verifies platform mirrors are in sync
+6. Verify the skill appears in `npm run generate:skills-index`
+7. Test `route_resolve` with a prompt that should match the new skill
+8. Test `skill_validate` with the new skill's name
+9. Test `skill_get` to confirm the SKILL.md loads correctly
 
 ## Common Integration Mistakes
 
-1. **Forgetting to update all 5 platform rule files** — every platform needs the skill in its routing matrix
+1. **Editing generated platform rule files directly** — change shared `STEERING.md` or a platform override, then regenerate
 2. **Mismatched names** — directory name, frontmatter name, and routing matrix name must all match
-3. **Wrong agent assignment** — assigning a frontend skill to @backend-specialist causes incorrect context loading
-4. **Missing mirror creation** — Claude and Copilot platforms need mirrors with platform-specific frontmatter
+3. **Wrong agent assignment** — assigning a testing or review skill to the wrong lean agent causes incorrect routing and validation
+4. **Using skill mirror sync for non-skill assets** — agents, prompts, and command files have their own platform-native generation path
 5. **Invalid evals.json** — JSON syntax errors cause the eval runner to skip the skill silently