Replace commands references with invocable skills

AGENTS.md

@@ -533,7 +533,7 @@ Skills for generating diagrams and rendering markdown content into shareable for
 
 ## Available Workflows & Skills
 
-Under the Antigravity CLI, workflows are structured as Skills instead of user-facing slash commands. When a user requests a task, the agent automatically matches it to the appropriate workflow, reads the skill's `SKILL.md` using `view_file`, and executes the corresponding orchestrator.
+Under the Antigravity CLI, workflows are structured as Skills. They can be invoked by the user using slash commands in the format `/<plugin_name>:<skill_name>` (e.g., `/agyflow:work` or `/agyflow:quick-dev`). When a user requests a task, the agent automatically matches it to the appropriate workflow, reads the skill's `SKILL.md` using `view_file`, and executes the corresponding orchestrator.
 
 All orchestrators support resuming from a specific phase via state restoration from `orchestrator-state.yml`.
 

README.md

@@ -73,29 +73,29 @@ agy plugin uninstall agyflow
 Initialize your project to auto-detect coding standards and generate project documentation. Run this inside an active `agy` session:
 
 ```bash
-/flow-init
+/agyflow:flow-init
 ```
 
 This scans your codebase and creates `.agyflow/` with standards, docs, and task folders. May take a few minutes on larger projects.
 
 If you have another project already using Agyflow, you can reuse its standards as a starting point:
 
 ```bash
-/flow-init --standards-from=/path/to/other-project
+/agyflow:flow-init --standards-from=/path/to/other-project
 ```
 
 ## First Workflow
 
 Start a workflow by running this inside an active `agy` session:
 
 ```bash
-/development Add user profile page with avatar upload
+/agyflow:development Add user profile page with avatar upload
 ```
 
 Or just discuss your task with Agent and then run:
 
 ```bash
-/development
+/agyflow:development
 ```
 
 The plugin picks up context from your conversation - no arguments needed.
@@ -110,55 +110,55 @@ The plugin picks up context from your conversation - no arguments needed.
 
 All artifacts are saved in `.agyflow/tasks/` organized by type and date.
 
-### Context-Aware Commands
+### Context-Aware Skills
 
-Every workflow command works without arguments. The plugin reads your current conversation to extract the task description and auto-detect the task type:
+Every workflow skill works without arguments. The plugin reads your current conversation to extract the task description and auto-detect the task type:
 
 ```
 You: "The login page throws a 500 error when the session expires"
-You: /development
+You: /agyflow:development
 → Auto-detects: bug fix, extracts description from conversation
 ```
 
 ```
-You: /standards-update
+You: /agyflow:standards-update
 → Scans conversation for patterns like "we always use..." or "prefer X over Y"
 ```
 
 You can always be explicit when you prefer - arguments and flags simply override the auto-detection.
 
 ## Supported Workflows
 
-| Command           | Use When                                    |
+| Skill             | Use When                                    |
 | ----------------- | ------------------------------------------- |
-| `/development`    | Features, bug fixes, enhancements           |
-| `/research`       | Research with synthesis and solution design |
-| `/performance`    | Optimizing speed or resource usage          |
-| `/migration`      | Changing technologies or patterns           |
-| `/product-design` | Product and feature design                  |
+| `/agyflow:development` | Features, bug fixes, enhancements           |
+| `/agyflow:research`    | Research with synthesis and solution design |
+| `/agyflow:performance` | Optimizing speed or resource usage          |
+| `/agyflow:migration`   | Changing technologies or patterns           |
+| `/agyflow:product-design` | Product and feature design               |
 
-Task type (feature/bug/enhancement) is auto-detected from context. Override with `--type=feature|bug|enhancement` if needed. Or use `/work` as a single entry point that routes to the right workflow.
+Task type (feature/bug/enhancement) is auto-detected from context. Override with `--type=feature|bug|enhancement` if needed. Or use `/agyflow:work` as a single entry point that routes to the right workflow.
 
-### Quick Commands
+### Quick Skills
 
 For smaller tasks that don't need a full workflow:
 
-| Command         | Use When                                                    | Artifacts                               |
+| Skill           | Use When                                                    | Artifacts                               |
 | --------------- | ----------------------------------------------------------- | --------------------------------------- |
-| `/quick-plan`   | You want a plan with standards awareness before coding      | `task.yml`, `findings.md`               |
-| `/quick-dev`    | You know what to do - just implement with standards applied | `task.yml`, `summary.md`                |
-| `/quick-bugfix` | Quick TDD-driven bug fix — write failing test, fix, verify  | `task.yml`, `findings.md`, `summary.md` |
+| `/agyflow:quick-plan` | You want a plan with standards awareness before coding      | `task.yml`, `findings.md`               |
+| `/agyflow:quick-dev`  | You know what to do - just implement with standards applied | `task.yml`, `summary.md`                |
+| `/agyflow:quick-bugfix` | Quick TDD-driven bug fix — write failing test, fix, verify  | `task.yml`, `findings.md`, `summary.md` |
 
-All quick commands create lightweight task directories under `.agyflow/tasks/quick-{type}/` with a `task.yml` for traceability.
+All quick skills create lightweight task directories under `.agyflow/tasks/quick-{type}/` with a `task.yml` for traceability.
 
 ## Standards-Aware Development
 
 This is the key differentiator. Agyflow doesn't just run workflows - it learns your project's conventions and enforces them:
 
 - **`flow-init`** scans config files, source code, and documentation to auto-detect your coding standards
 - **Continuous checking** - standards are consulted before specification, during planning, and while coding (not just at the start)
-- **`/standards-discover`** refreshes standards from your evolving codebase
-- **`/standards-update`** lets you add or refine standards manually, or sync from another project with `--from=PATH`
+- **`/agyflow:standards-discover`** refreshes standards from your evolving codebase
+- **`/agyflow:standards-update`** lets you add or refine standards manually, or sync from another project with `--from=PATH`
 
 Standards live in `.agyflow/docs/standards/` and are indexed in `.agyflow/docs/INDEX.md`.
 
@@ -173,24 +173,24 @@ Standards live in `.agyflow/docs/standards/` and are indexed in `.agyflow/docs/I
 **Chain workflows by passing a task folder.** If you've completed a research or product-design workflow and want to build on those results, pass the task folder directly:
 
 ```bash
-/development .agyflow/tasks/research/2026-01-12-oauth-research
+/agyflow:development .agyflow/tasks/research/2026-01-12-oauth-research
 ```
 
 You can also append additional instructions to narrow scope or guide the workflow:
 
 ```bash
-/development .agyflow/tasks/product-design/2026-03-10-dashboard-redesign Implement only phase 1
+/agyflow:development .agyflow/tasks/product-design/2026-03-10-dashboard-redesign Implement only phase 1
 ```
 
 ## Known Issues
 
 **Orchestrator may stall after long phases.** After context compaction (which typically happens after lengthy phases like implementation), the main agent may stop progressing automatically. If you notice it's idle, just type something like "continue" or "proceed" — it will pick up where it left off. You can also re-invoke the workflow in resume mode to reload the orchestrator state:
 
 ```bash
-/development .agyflow/tasks/development/2026-03-24-my-feature
+/agyflow:development .agyflow/tasks/development/2026-03-24-my-feature
 ```
 
 ## Learn More
 
 - [Workflow Details](docs/workflows.md) - phases, examples, and task structure for each workflow type
-- [Full Command Reference](docs/commands.md) - all workflow, review, utility, and quick commands
+- [Full Skill Reference](docs/skills.md) - all workflow, review, utility, and quick skills

agents/code-quality-pragmatist.md

@@ -41,7 +41,7 @@ The Task prompt MUST include:
 
 | Input         | Source                  | Purpose                                                                                   |
 | ------------- | ----------------------- | ----------------------------------------------------------------------------------------- |
-| `task_path`   | Orchestrator or command | Path to task directory or code to review                                                  |
+| `task_path`   | Orchestrator or skill   | Path to task directory or code to review                                                  |
 | `report_path` | Orchestrator (optional) | Where to write report (default: `verification/pragmatic-review.md` relative to task_path) |
 
 **CRITICAL**: All outputs MUST be written under `task_path`. Never write reports to project-level directories (`docs/`, `src/`, project root).

agents/code-reviewer.md

@@ -1,6 +1,6 @@
 ---
 name: code-reviewer
-description: Automated code quality, security, and performance analysis. Analyzes code for complexity, duplication, security vulnerabilities, performance issues, and best practices compliance. Can run standalone (via command) or as part of implementation verification. Provides actionable findings categorized by severity. Read-only - reports issues without fixing. Does not interact with users.
+description: Automated code quality, security, and performance analysis. Analyzes code for complexity, duplication, security vulnerabilities, performance issues, and best practices compliance. Can run standalone (via skill) or as part of implementation verification. Provides actionable findings categorized by severity. Read-only - reports issues without fixing. Does not interact with users.
 model: inherit
 color: orange
 mode: subagent
@@ -43,8 +43,8 @@ The Task prompt MUST include:
 
 | Input           | Source                  | Purpose                                                                                     |
 | --------------- | ----------------------- | ------------------------------------------------------------------------------------------- |
-| `analysis_path` | Orchestrator or command | Path to analyze (file, directory, or task path)                                             |
-| `scope`         | Orchestrator or command | `all` (default), `quality`, `security`, or `performance`                                    |
+| `analysis_path` | Orchestrator or skill   | Path to analyze (file, directory, or task path)                                             |
+| `scope`         | Orchestrator or skill   | `all` (default), `quality`, `security`, or `performance`                                    |
 | `report_path`   | Orchestrator (optional) | Where to write report (default: `verification/code-review-report.md` relative to task_path) |
 
 **CRITICAL**: All outputs MUST be written under `task_path`. Never write reports to project-level directories (`docs/`, `src/`, project root).
@@ -228,7 +228,7 @@ issue_counts:
 
 ## Integration
 
-**Invoked by**: implementation-verifier (Phase 3), standalone via `/reviews-code` command
+**Invoked by**: implementation-verifier (Phase 3), standalone via `/agyflow:reviews-code` skill
 
 **Prerequisites**:
 

agents/production-readiness-checker.md

@@ -43,8 +43,8 @@ The Task prompt MUST include:
 
 | Input           | Source                  | Purpose                                                                                              |
 | --------------- | ----------------------- | ---------------------------------------------------------------------------------------------------- |
-| `analysis_path` | Orchestrator or command | Path to analyze (task directory, feature directory, or project)                                      |
-| `target`        | Orchestrator or command | `production` (default, full rigor) or `staging` (relaxed)                                            |
+| `analysis_path` | Orchestrator or skill   | Path to analyze (task directory, feature directory, or project)                                      |
+| `target`        | Orchestrator or skill   | `production` (default, full rigor) or `staging` (relaxed)                                            |
 | `report_path`   | Orchestrator (optional) | Where to write report (default: `verification/production-readiness-report.md` relative to task_path) |
 
 **CRITICAL**: All outputs MUST be written under `task_path`. Never write reports to project-level directories (`docs/`, `src/`, project root).
@@ -268,7 +268,7 @@ issue_counts:
 
 ## Integration
 
-**Invoked by**: implementation-verifier (Phase 3), performance orchestrator (Phase 4), standalone via `/reviews-production-readiness` command
+**Invoked by**: implementation-verifier (Phase 3), performance orchestrator (Phase 4), standalone via `/agyflow:reviews-production-readiness` skill
 
 **Prerequisites**:
 

agents/project-analyzer.md

@@ -287,7 +287,7 @@ Return your analysis in the conversation response (do NOT create files):
 1. **Structured JSON block**: Machine-readable analysis for downstream phases
 2. **Markdown summary**: Human-readable overview for user review
 
-**IMPORTANT**: Do NOT write any files to disk. The flow-init command will use your returned analysis to generate proper documentation in `.agyflow/docs/`.
+**IMPORTANT**: Do NOT write any files to disk. The flow-init skill will use your returned analysis to generate proper documentation in `.agyflow/docs/`.
 
 ---
 
@@ -399,6 +399,6 @@ Before returning your analysis, verify:
 5. Identify conventions (naming, organization, documentation)
 6. Generate structured report (JSON + markdown)
 
-**Output**: Return structured analysis (JSON + markdown) in your response. Do NOT create files - the calling command handles file creation in `.agyflow/docs/`.
+**Output**: Return structured analysis (JSON + markdown) in your response. Do NOT create files - the calling skill handles file creation in `.agyflow/docs/`.
 
 **Remember**: You are an analyzer, not a modifier. Read, analyze, return results in conversation. All findings must be evidence-based.

agents/reality-assessor.md

@@ -40,7 +40,7 @@ The Task prompt MUST include:
 
 | Input                 | Source                  | Purpose                                                                                |
 | --------------------- | ----------------------- | -------------------------------------------------------------------------------------- |
-| `task_path`           | Orchestrator or command | Absolute path to task directory                                                        |
+| `task_path`           | Orchestrator or skill   | Absolute path to task directory                                                        |
 | `report_path`         | Orchestrator (optional) | Where to write report (default: `verification/reality-check.md` relative to task_path) |
 | `skip_test_execution` | Orchestrator (optional) | When `true`, read test results from file instead of running tests                      |
 | `test_results_path`   | Orchestrator (optional) | Path to test results file (when `skip_test_execution: true`)                           |

agents/task-classifier.md

@@ -381,12 +381,12 @@ Use question with relevant options
 
 ## Integration Points
 
-**With /work Command**:
+**With /agyflow:work Skill**:
 
-1. `/work` parses arguments and task description
+1. `/agyflow:work` parses arguments and task description
 2. Invokes this agent directly via Task tool
 3. Agent performs classification and returns result
-4. `/work` routes to appropriate orchestrator
+4. `/agyflow:work` routes to appropriate orchestrator
 
 **Classification Routes**: