owflow 0.2.0 → 0.4.2

package/dist/commands/research-design.md

@@ -0,0 +1,33 @@
+---
+name: owflow:research-design
+description: Research skill — optional step. Asks for your design preferences, creates the high-level architecture design together with its decision log, and refines the diagrams. Invoking this step means you chose to design.
+argument-hint: "[task-path-or-identifier]"
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:research-design skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "research-design"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+
+- Analyze the task before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow step by using /owflow:research-design.
+Invoke the skill now and let it execute the step, update orchestrator state,
+and present results with next-step suggestions.
+
+---
+
+## About This Workflow
+
+Part of the research workflow. See `skills/research-design/SKILL.md` for complete step documentation.
+
+Entry points:
+
+- `/owflow:research <description | task-path>` — start or resume a research task (assisted mode)
+- `/owflow:goal-research <description>` — run all steps in one loop (orchestrated mode)

package/dist/commands/research-finalize.md

@@ -0,0 +1,33 @@
+---
+name: owflow:research-finalize
+description: Research skill — terminal step. Inventories all research outputs (the research report always, brainstorm and design artifacts when they exist), presents the workflow results, and gets your confirmation that the research is correct. Marks the task complete.
+argument-hint: "[task-path-or-identifier]"
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:research-finalize skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "research-finalize"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+
+- Analyze the task before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow step by using /owflow:research-finalize.
+Invoke the skill now and let it execute the step, update orchestrator state,
+and present results with next-step suggestions.
+
+---
+
+## About This Workflow
+
+Terminal step of the research workflow. Inventory of outputs, results box, confirmation; then assisted mode suggests development handoff. See `skills/research-finalize/SKILL.md` for complete step documentation.
+
+Entry points:
+
+- `/owflow:research <description | task-path>` — start or resume a research task (assisted mode)
+- `/owflow:goal-research <description>` — run all steps in one loop (orchestrated mode)

package/dist/commands/research-fork.md

@@ -0,0 +1,40 @@
+---
+name: owflow:research-fork
+description: 'Utility command for the research workflow — fork an existing research task into a new one that diverges at a chosen completed step (the copied state is trimmed so the fork continues from that step onwards; the source stays untouched). Pass just the task path: the skill reads the source, then asks intent, fork point, and name with suggestions derived from that research.'
+argument-hint: "<task-path-or-identifier> [\"<what this fork should explore>\"] [--from=<slug>] [--name=\"...\"]"
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:research-fork skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "research-fork"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+
+- Analyze the task before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow step by using /owflow:research-fork.
+Invoke the skill now and let it copy the task, update orchestrator state,
+and present the fork summary.
+
+---
+
+## About This Workflow
+
+Utility skill of the research workflow — NOT a pipeline step. Copies a research task directory wholesale into a new task that diverges from the previous run at a chosen fork point (`--from=<slug>`); the copied state is trimmed to continue from the fork point onwards. See `skills/research-fork/SKILL.md` for complete documentation.
+
+Usage:
+
+- `/owflow:research-fork <task-path>` — bare path; the skill asks the remaining questions
+- `/owflow:research-fork <task-path> "explore the cost angle"` — the quoted text answers the intent question
+- `--from=<step-slug>` / `--name="<short name>"` — skip the matching question entirely
+
+Related entry points:
+
+- `/owflow:research <description | task-path>` — start or resume a research task (assisted mode)
+- `/owflow:goal-research <description>` — run all steps in one loop (orchestrated mode)
+- After forking: `/owflow:research <fork-path>` resumes the fork at the first step after the fork point.

package/dist/commands/research-gather.md

@@ -0,0 +1,33 @@
+---
+name: owflow:research-gather
+description: Research skill — reads the plan's Gathering Strategy and launches the parallel information-gatherer agent fan in ONE message, then merges per-category findings. Ends the gathering step of the research workflow (findings-gathered) and continues with research-synthesize.
+argument-hint: "[task-path-or-identifier]"
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:research-gather skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "research-gather"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+
+- Analyze the task before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow step by using /owflow:research-gather.
+Invoke the skill now and let it execute the step, update orchestrator state,
+and present results with next-step suggestions.
+
+---
+
+## About This Workflow
+
+Part of the research workflow. See `skills/research-gather/SKILL.md` for complete step documentation.
+
+Entry points:
+
+- `/owflow:research <description | task-path>` — start or resume a research task (assisted mode)
+- `/owflow:goal-research <description>` — run all steps in one loop (orchestrated mode)

package/dist/commands/research-plan.md

@@ -0,0 +1,37 @@
+---
+name: owflow:research-plan
+description: Research skill — creates the research brief, delegates methodology selection and planning to the research-planner agent, and writes the research plan with a parsable Gathering Strategy. First work phase of the research workflow; continues with research-gather.
+argument-hint: "[task-path-or-identifier | \"description\"]"
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:research-plan skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "research-plan"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+
+- Analyze the task before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow step by using /owflow:research-plan.
+Invoke the skill now and let it execute the step, update orchestrator state,
+and present results with next-step suggestions.
+
+---
+
+## About This Workflow
+
+Part of the research workflow. See `skills/research-plan/SKILL.md` for complete step documentation.
+
+Entry points:
+
+- `/owflow:research <description | task-path>` — start or resume a research task (assisted mode)
+- `/owflow:goal-research <description>` — run all steps in one loop (orchestrated mode)
+
+Quick lane:
+
+- `/owflow:research-quick "<description>"` — condensed research task: bootstraps a standard research task and then fuses brief, plan, gather, and synthesis into one pass — continuable with any research subskill

package/dist/commands/research-quick.md

@@ -0,0 +1,37 @@
+---
+name: owflow:research-quick
+description: Research skill — the quick lane. Bootstraps a standard research task and fuses brief, plan + sources, gather, and synthesis into one condensed pass — the only place where the planner delegation, the gatherer fan, and the synthesizer delegation are condensable. Produces the same standard artifacts and state as the full lane; continuable by any research subskill at full fidelity.
+argument-hint: "[task-path-or-identifier | \"description\"]"
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:research-quick skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "research-quick"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+
+- Analyze the task before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow step by using /owflow:research-quick.
+Invoke the skill now and let it execute the step, update orchestrator state,
+and present results with next-step suggestions.
+
+---
+
+## About This Workflow
+
+Part of the research workflow. See `skills/research-quick/SKILL.md` for complete step documentation.
+
+Entry points:
+
+- `/owflow:research <description | task-path>` — start or resume a research task (assisted mode)
+- `/owflow:goal-research <description>` — run all steps in one loop (orchestrated mode)
+
+Quick lane:
+
+- `/owflow:research-quick "<description>"` — condensed research task: bootstraps a standard research task and then fuses brief, plan, gather, and synthesis into one pass — continuable with any research subskill

package/dist/commands/research-synthesize.md

@@ -0,0 +1,33 @@
+---
+name: owflow:research-synthesize
+description: Research skill — delegates synthesis and evidence-based reporting to the research-synthesizer agent, producing the synthesis document and the comprehensive research report with per-finding confidence. Closes the research foundation (synthesis-complete) at the boundary with the optional chain (user choice).
+argument-hint: "[task-path-or-identifier]"
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:research-synthesize skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "research-synthesize"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+
+- Analyze the task before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow step by using /owflow:research-synthesize.
+Invoke the skill now and let it execute the step, update orchestrator state,
+and present results with next-step suggestions.
+
+---
+
+## About This Workflow
+
+Part of the research workflow. See `skills/research-synthesize/SKILL.md` for complete step documentation.
+
+Entry points:
+
+- `/owflow:research <description | task-path>` — start or resume a research task (assisted mode)
+- `/owflow:goal-research <description>` — run all steps in one loop (orchestrated mode)

package/dist/commands/research.md

@@ -1,37 +1,55 @@
----
-name: research
-description: Orchestrates comprehensive research workflows from question definition through findings documentation. Handles technical, requirements, literature, and mixed research types with adaptive methodology, multi-source gathering, pattern synthesis, and evidence-based reporting. Supports standalone research tasks and embedded research phase in other workflows.
-argument-hint: [task description]
-generated-from-skill: true
----
-
-CRITICAL INSTRUCTION: You MUST invoke the research skill immediately as your FIRST action.
-
-Use the Skill tool with these exact parameters:
-name: "research"
-prompt: "$ARGUMENTS"
-
-DO NOT:
-
-- Analyze the task before invoking the skill
-- Decide the task is "straightforward" and skip the skill
-- Substitute your own approach or workflow
-- Execute any part of the workflow yourself
-
-WHY: The user explicitly chose this workflow by using /research.
-Invoke the skill now and let it orchestrate the complete workflow.
-
----
-
-## About This Workflow
-
-Orchestrates comprehensive research workflows from question definition through findings documentation. Handles technical, requirements, literature, and mixed research types with adaptive methodology, multi-source gathering, pattern synthesis, and evidence-based reporting. Supports standalone research tasks and embedded research phase in other workflows.
-
-The skill handles:
-
-- Task directory creation and state management
-- Phase execution with interactive gates
-- Subagent delegation for specialized work
-- Pause/resume capability
-
-See `skills/research/SKILL.md` for complete workflow documentation.
+---
+name: owflow:research
+description: Research workflow dispatcher. Initializes/resumes research tasks, derives the next step from state, and hands off to the matching /owflow:research-* subskill. Handles comprehensive research and analysis — technical, requirements, literature, and mixed research types with adaptive methodology, multi-source gathering, pattern synthesis, and evidence-based artifact outputs (findings documentation). Supports standalone research tasks and embedded research phases feeding development workflows.
+argument-hint: "[task description | task-path] [--from=<slug>] [--type=<type>]"
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:research skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "research"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+
+- Analyze the task before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow by using /owflow:research.
+Invoke the skill now and let it dispatch the matching research step.
+
+---
+
+## About This Workflow
+
+Research workflow **dispatcher** (assisted mode). The skill handles:
+
+- Task initialization/resume and state management (`orchestrator-state.yml`)
+- Research context intake and `--type` flag handling
+- Deriving the next pending step from state (descriptive slugs, NOT phase numbers)
+- Handing off to the matching `/owflow:research-*` subskill, then stopping
+
+Run `/owflow:goal-research` instead for autonomous mode (all subskills in one session with gates).
+
+Quick lane: starts only via `/owflow:research-quick "<description>"` — a condensed research task that fuses brief, plan, gather, and synthesis into one pass, continuable by any research subskill.
+
+Forking: `/owflow:research-fork <task-path> ["<what this fork should explore>"] [--from=<slug>]` copies a research task to a new task diverging at a chosen completed step (directory copied verbatim, `completed_phases` trimmed) — original task untouched. A bare task path is enough: the skill asks for the intent, fork point, and name with suggestions taken from that research.
+
+Entry points:
+
+- `/owflow:research <description>` — start or resume a research task (assisted mode)
+- `/owflow:goal-research <description>` — run all steps in one loop (orchestrated mode)
+
+Steps (each works on the shared task directory):
+
+- `/owflow:research-plan <description | task-path>` — brief, methodology & plan
+- `/owflow:research-gather <task-path>` — parallel findings fan
+- `/owflow:research-synthesize <task-path>` — synthesis & research report
+- `/owflow:research-brainstorm <task-path>` — solution alternatives (optional, user's choice)
+- `/owflow:research-converge <task-path>` — per-area decisions (after brainstorming)
+- `/owflow:research-design <task-path>` — high-level design (optional, user's choice)
+- `/owflow:research-finalize <task-path>` — completion & handoff
+
+See `skills/research/SKILL.md` for the routing table and `skills/research-*/SKILL.md` for step documentation.

package/dist/commands/reviews-code.md

@@ -1,5 +1,5 @@
 ---
-name: reviews-code
+name: owflow:reviews-code
 description: Run automated code quality, security, and performance analysis on your code
 ---
 
@@ -54,19 +54,19 @@ The code-reviewer subagent will:
 **Example 1**: Review specific task
 
 ```
-User: /reviews-code .owflow/tasks/development/2025-10-24-auth/
+User: /owflow:reviews-code .owflow/tasks/development/2025-10-24-auth/
 ```
 
 **Example 2**: Review with specific scope
 
 ```
-User: /reviews-code src/api/ --scope=security
+User: /owflow:reviews-code src/api/ --scope=security
 ```
 
 **Example 3**: Review entire project
 
 ```
-User: /reviews-code src/
+User: /owflow:reviews-code src/
 ```
 
 ## What to Expect

package/dist/commands/reviews-pragmatic.md

@@ -1,5 +1,5 @@
 ---
-name: reviews-pragmatic
+name: owflow:reviews-pragmatic
 description: Run pragmatic code review to detect over-engineering and ensure code matches project scale
 ---
 
@@ -60,19 +60,19 @@ The code-quality-pragmatist agent will:
 **Example 1**: Review specific feature
 
 ```
-User: /reviews-pragmatic .owflow/tasks/development/2025-11-17-user-management/
+User: /owflow:reviews-pragmatic .owflow/tasks/development/2025-11-17-user-management/
 ```
 
 **Example 2**: Review source directory
 
 ```
-User: /reviews-pragmatic src/features/payments/
+User: /owflow:reviews-pragmatic src/features/payments/
 ```
 
 **Example 3**: Review specific file
 
 ```
-User: /reviews-pragmatic src/services/cache-service.ts
+User: /owflow:reviews-pragmatic src/services/cache-service.ts
 ```
 
 ## What to Expect

package/dist/commands/reviews-production-readiness.md

@@ -1,5 +1,5 @@
 ---
-name: reviews-production-readiness
+name: owflow:reviews-production-readiness
 description: Verify production deployment readiness with comprehensive checks
 ---
 
@@ -55,19 +55,19 @@ The production-readiness-checker subagent will:
 **Example 1**: Check specific task for production
 
 ```
-User: /reviews-production-readiness .owflow/tasks/development/2025-10-24-payment-api/
+User: /owflow:reviews-production-readiness .owflow/tasks/development/2025-10-24-payment-api/
 ```
 
 **Example 2**: Check feature for staging
 
 ```
-User: /reviews-production-readiness src/features/notifications/ --target=staging
+User: /owflow:reviews-production-readiness src/features/notifications/ --target=staging
 ```
 
 **Example 3**: Comprehensive project check
 
 ```
-User: /reviews-production-readiness .
+User: /owflow:reviews-production-readiness .
 ```
 
 ## What to Expect

package/dist/commands/reviews-reality-check.md

@@ -1,5 +1,5 @@
 ---
-name: reviews-reality-check
+name: owflow:reviews-reality-check
 description: Comprehensive reality assessment of completed work to verify it actually works and is production-ready
 ---
 
@@ -68,19 +68,19 @@ The reality-assessor agent will:
 **Example 1**: Reality check before deployment
 
 ```
-User: /reviews-reality-check .owflow/tasks/development/2025-11-17-payment-processing/
+User: /owflow:reviews-reality-check .owflow/tasks/development/2025-11-17-payment-processing/
 ```
 
 **Example 2**: Verify claimed completion
 
 ```
-User: /reviews-reality-check .owflow/tasks/development/2025-11-17-login-timeout/
+User: /owflow:reviews-reality-check .owflow/tasks/development/2025-11-17-login-timeout/
 ```
 
 **Example 3**: Production readiness check
 
 ```
-User: /reviews-reality-check .owflow/tasks/development/2025-11-17-user-dashboard/ --production
+User: /owflow:reviews-reality-check .owflow/tasks/development/2025-11-17-user-dashboard/ --production
 ```
 
 ## What to Expect

package/dist/commands/reviews-spec-audit.md

@@ -1,5 +1,5 @@
 ---
-name: reviews-spec-audit
+name: owflow:reviews-spec-audit
 description: Independent specification audit to verify completeness and clarity before implementation
 ---
 
@@ -73,19 +73,19 @@ The spec-auditor agent will:
 **Example 1**: Pre-implementation spec audit
 
 ```
-User: /reviews-spec-audit .owflow/tasks/development/2025-11-17-user-auth/implementation/spec.md
+User: /owflow:reviews-spec-audit .owflow/tasks/development/2025-11-17-user-auth/implementation/spec.md
 ```
 
 **Example 2**: Post-implementation audit
 
 ```
-User: /reviews-spec-audit .owflow/tasks/development/2025-11-17-user-auth/ --post-implementation
+User: /owflow:reviews-spec-audit .owflow/tasks/development/2025-11-17-user-auth/ --post-implementation
 ```
 
 **Example 3**: Audit with clarification focus
 
 ```
-User: /reviews-spec-audit spec.md --focus=ambiguity
+User: /owflow:reviews-spec-audit spec.md --focus=ambiguity
 ```
 
 ## What to Expect

package/dist/commands/rule-reviewer.md

@@ -0,0 +1,38 @@
+---
+name: owflow:rule-reviewer
+description: Score an AI rules file on 5 axes and produce concrete actionable fixes
+---
+
+CRITICAL INSTRUCTION: You MUST invoke the owflow:rule-reviewer skill immediately as your FIRST action.
+
+Use the Skill tool with these exact parameters:
+name: "rule-reviewer"
+prompt: "$ARGUMENTS"
+
+DO NOT:
+- Analyze the file before invoking the skill
+- Decide the task is "straightforward" and skip the skill
+- Substitute your own approach or workflow
+- Execute any part of the workflow yourself
+
+WHY: The user explicitly chose this workflow by using /owflow:rule-reviewer.
+Invoke the skill now and let it orchestrate the complete workflow.
+
+---
+
+## About This Workflow
+
+Score an AI rules file (AGENTS.md, CLAUDE.md, .cursor/rules/*.mdc, .windsurfrules,
+.github/copilot-instructions.md, or any rule-for-AI markdown) on 5 axes and return
+concrete actionable fixes. The skill is read-only by default — it produces a scorecard.
+The only edit it may apply is a section reorder, and only with explicit user approval.
+
+## Examples
+
+```
+/owflow:rule-reviewer AGENTS.md
+/owflow:rule-reviewer .cursor/rules/api.mdc
+/owflow:rule-reviewer src/api/AGENTS.md
+```
+
+See `skills/rule-reviewer/SKILL.md` for complete workflow documentation.

package/dist/commands/standards-discover.md

@@ -1,11 +1,10 @@
 ---
-name: standards-discover
+name: owflow:standards-discover
 description: Discover coding standards from project configuration files, code patterns, documentation, and external sources (PRs, CI/CD)
 argument-hint: [task description]
-generated-from-skill: true
 ---
 
-CRITICAL INSTRUCTION: You MUST invoke the standards-discover skill immediately as your FIRST action.
+CRITICAL INSTRUCTION: You MUST invoke the owflow:standards-discover skill immediately as your FIRST action.
 
 Use the Skill tool with these exact parameters:
 name: "standards-discover"
@@ -18,7 +17,7 @@ DO NOT:
 - Substitute your own approach or workflow
 - Execute any part of the workflow yourself
 
-WHY: The user explicitly chose this workflow by using /standards-discover.
+WHY: The user explicitly chose this workflow by using /owflow:standards-discover.
 Invoke the skill now and let it orchestrate the complete workflow.
 
 ---

package/dist/commands/standards-update.md

@@ -1,11 +1,10 @@
 ---
-name: standards-update
+name: owflow:standards-update
 description: Update or create project standards from conversation context or explicit description
 argument-hint: "[description of standard/convention] [--from=PATH]"
-generated-from-skill: true
 ---
 
-CRITICAL INSTRUCTION: You MUST invoke the standards-update skill immediately as your FIRST action.
+CRITICAL INSTRUCTION: You MUST invoke the owflow:standards-update skill immediately as your FIRST action.
 
 Use the Skill tool with these exact parameters:
 name: "standards-update"
@@ -18,7 +17,7 @@ DO NOT:
 - Substitute your own approach or workflow
 - Execute any part of the workflow yourself
 
-WHY: The user explicitly chose this workflow by using /standards-update.
+WHY: The user explicitly chose this workflow by using /owflow:standards-update.
 Invoke the skill now and let it orchestrate the complete workflow.
 
 ---