[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7350QTSA0CJGZXBJG11XA24":3,"skill-same:01M7350QTSA0CJGZXBJG11XA24":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7350QTSA0CJGZXBJG11XA24","productize-runtime",null,"Explains Productize capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and extensions. Use when the user asks how to use Productize, what commands are available, how the workflow pipeline works, or how to configure a workspace. Do not use for executing workflow steps — use the specific workflow skills (create-prd, create-techspec, create-tasks, execute-task, review-round, fix-reviews, final-verify, workflow-memory) instead.","itseffi\u002Fproductize","itseffi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F15998472?v=4","01M734C5RJ7CKRTPB3FX84VZV7","Effi","01M734C5S6B7FW62ZNWYBZ9GG7",3,"MIT","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-runtime\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: productize-runtime\ndescription: Explains Productize capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and extensions. Use when the user asks how to use Productize, what commands are available, how the workflow pipeline works, or how to configure a workspace. Do not use for executing workflow steps — use the specific workflow skills (create-prd, create-techspec, create-tasks, execute-task, review-round, fix-reviews, final-verify, workflow-memory) instead.\n---\n\n# Productize Reference Guide\n\nComprehensive reference for the Productize CLI and its daemon-backed product workflow runtime.\n\n## What Is Productize\n\nProductize is a Go CLI and daemon-backed runtime for shipping products with AI agents. It keeps product work in markdown, syncs authored workflow artifacts into daemon state, supervises ACP-backed agent runs, and supports review\u002Ffix loops, reusable agents, extensions, memory, gates, and routed product skills.\n\nKey characteristics:\n\n- **Agent-agnostic.** Supports claude, codex, copilot, cursor-agent, droid, gemini, opencode, and pi as ACP runtimes.\n- **Skills-based.** Bundled Productize workflow skills and Productize product-operating skills (installed via `productize setup`) teach agents how to execute each workflow phase.\n- **Artifact-driven.** Planning and review artifacts live as markdown under `.productize\u002Ftasks\u002F\u003Cslug>\u002F`, versioned alongside the codebase.\n- **Daemon-backed runtime.** A home-scoped daemon owns run state, workspace registration, snapshots, streams, and the synced `global.db` catalog under `~\u002F.productize\u002F`.\n- **Single binary runtime.** The daemon is launched from the same binary; there are no external control planes.\n\n## Workflow Pipeline Overview\n\nThe standard development pipeline follows these phases in order. Each phase produces artifacts consumed by the next.\n\n1. **Existing Project Onboarding** -- `productize onboard existing --agent \u003Cname>` resolves the repository root, inventories existing code and documentation, generates project knowledge, installs Productize, and registers the workspace.\n2. **Setup** (new repos or manual control) -- interactive `productize setup` selects one agent target. Repeated `--agent` flags explicitly install into several targets; `--all-agents` is the only all-target shortcut.\n3. **Ideation** (optional) -- install and enable the first-party `idea-forge` extension, run `productize setup`, then use `\u002Fidea-forge` to expand a raw idea into a structured, research-backed spec at `.productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md`.\n4. **Requirements** -- `\u002Fcreate-prd` creates a business-focused Product Requirements Document at `.productize\u002Ftasks\u002F\u003Cslug>\u002F_prd.md` with ADRs.\n5. **Technical Design** -- `\u002Fcreate-techspec` translates the PRD into a technical specification at `.productize\u002Ftasks\u002F\u003Cslug>\u002F_techspec.md` with ADRs.\n6. **Task Decomposition** -- `\u002Fcreate-tasks` breaks down the PRD and TechSpec into independently implementable task files (`task_01.md`, `task_02.md`, etc.) and a master list at `_tasks.md`.\n7. **Execution** -- `productize tasks run \u003Cslug> --ide \u003Cruntime>` dispatches task files to the configured AI agent. Execution is sequential by default; `--concurrent N` enables bounded parallel execution of dependency-ready tasks.\n8. **Review** -- `\u002Freview-round` (manual AI review) or `productize reviews fetch \u003Cslug> --provider coderabbit --pr \u003CN>` (external provider) produces review issue files under `reviews-NNN\u002F`.\n9. **Remediation** -- `productize reviews fix \u003Cslug>` processes review issues, triages, fixes, and verifies each one.\n10. **Archive** -- `productize archive --name \u003Cslug>` moves fully completed workflows to `.productize\u002Ftasks\u002F_archived\u002F`, then refreshes project knowledge.\n\nRepeat phases 7-8 until the review is clean, then merge.\n\n```dot\ndigraph productize_pipeline {\n    \"productize onboard existing\" [shape=box];\n    \"\u002Fidea-forge (optional)\" [shape=box];\n    \"\u002Fcreate-prd\" [shape=box];\n    \"\u002Fcreate-techspec\" [shape=box];\n    \"\u002Fcreate-tasks\" [shape=box];\n    \"productize tasks run\" [shape=box];\n    \"Review (manual or provider)\" [shape=box];\n    \"productize reviews fix\" [shape=box];\n    \"Reviews clean?\" [shape=diamond];\n    \"productize archive\" [shape=doublecircle];\n\n    \"productize onboard existing\" -> \"\u002Fidea-forge (optional)\";\n    \"\u002Fidea-forge (optional)\" -> \"\u002Fcreate-prd\";\n    \"\u002Fcreate-prd\" -> \"\u002Fcreate-techspec\";\n    \"\u002Fcreate-techspec\" -> \"\u002Fcreate-tasks\";\n    \"\u002Fcreate-tasks\" -> \"productize tasks run\";\n    \"productize tasks run\" -> \"Review (manual or provider)\";\n    \"Review (manual or provider)\" -> \"productize reviews fix\";\n    \"productize reviews fix\" -> \"Reviews clean?\";\n    \"Reviews clean?\" -> \"Review (manual or provider)\" [label=\"no\"];\n    \"Reviews clean?\" -> \"productize archive\" [label=\"yes\"];\n}\n```\n\nFor a detailed step-by-step walkthrough of each phase, read `references\u002Fworkflow-guide.md`.\n\n## CLI Commands Quick Reference\n\n| Command | Purpose | Key Flags |\n| --- | --- | --- |\n| **Setup & Config** | | |\n| `productize onboard existing` | Integrate an existing repository, install agent assets, and register it | `--agent`, `--dry-run`, `--skip-setup`, `--skip-register`, `--format` |\n| `productize init existing` | Create or refresh only `.productize\u002Fproject\u002F` knowledge docs | `--dry-run`, `--exclude`, `--force`, `--format` |\n| `productize setup` | Install skills into one selected agent target by default | `--agent`, `--all-agents`, `--skill`, `--global`, `--copy`, `--list`, `--yes` |\n| `productize setup cleanup` | Safely remove old managed agent targets | `--keep-agent`, `--global`, `--dry-run`, `--yes`, `--format` |\n| `productize upgrade` | Update CLI to latest release | |\n| **Workflow Execution** | | |\n| `productize daemon` | Manage the home-scoped daemon lifecycle | `start`, `status`, `stop` |\n| `productize workspaces` | Inspect and manage daemon workspace registrations | `list`, `show`, `register`, `unregister`, `resolve` |\n| `productize tasks run` | Execute PRD task files through the daemon | `--name`, `--concurrent`, `--verify-command`, `--format`, `--attach`, `--stream`, `--detach`, `--task-runtime` |\n| `productize exec` | Execute an ad hoc prompt | `--agent`, `--format`, `--prompt-file`, `--persist`, `--run-id` |\n| `productize runs` | Attach, watch, and purge daemon-managed runs | `attach`, `watch`, `purge` |\n| **Review** | | |\n| `productize reviews fetch` | Fetch provider review comments | `--provider`, `--pr`, `--name`, `--round` |\n| `productize reviews fix` | Process review issue files | `--name`, `--round`, `--concurrent`, `--batch-size`, `--ide` |\n| **Utilities** | | |\n| `productize tasks validate` | Validate task file metadata | `--name`, `--tasks-dir`, `--format` |\n| `productize sync` | Reconcile workflow artifacts into daemon `global.db`, then refresh project knowledge | `--name`, `--root-dir`, `--tasks-dir` |\n| `productize archive` | Move daemon-eligible completed workflows to archive, then refresh project knowledge | `--name`, `--root-dir`, `--tasks-dir` |\n| `productize migrate` | Convert legacy artifacts to frontmatter | `--name`, `--dry-run`, `--reviews-dir` |\n| **Agent Management** | | |\n| `productize agents list` | List resolved reusable agents | |\n| `productize agents inspect` | View agent definition and defaults | `\u003Cname>` |\n| **Extensions** | | |\n| `productize ext list` | List extensions | |\n| `productize ext inspect` | View extension details | `\u003Cname>` |\n| `productize ext install` | Install an extension from a local path or GitHub repo archive | `\u003Csource>`, `--remote`, `--ref`, `--subdir` |\n| `productize ext uninstall` | Remove an extension | `\u003Cname>` |\n| `productize ext enable\u002Fdisable` | Toggle extension | `\u003Cname>` |\n| `productize ext doctor` | Diagnose extension issues | |\n\nCommon flags shared by `tasks run`, `exec`, and `reviews fix`: `--ide`, `--model`, `--reasoning-effort`, `--add-dir`, `--auto-commit`, `--dry-run`.\n\nFor complete flag documentation, read `references\u002Fcli-reference.md`.\n\n## Core Skills Summary\n\n| Skill | Trigger | When To Use | Do Not Use For |\n| --- | --- | --- | --- |\n| `create-prd` | `\u002Fcreate-prd` | Building a Product Requirements Document | TechSpec, task breakdown, coding |\n| `create-techspec` | `\u002Fcreate-techspec` | Translating PRD into technical design | PRD creation, task execution |\n| `create-tasks` | `\u002Fcreate-tasks` | Decomposing PRD+TechSpec into task files | Execution, review |\n| `execute-task` | (internal) | Executing a single PRD task (called by `productize tasks run`) | Direct invocation, review work |\n| `review-round` | `\u002Freview-round` | Performing comprehensive code review | Fetching external reviews, fixing |\n| `fix-reviews` | (internal) | Remediating review issues (called by `productize reviews fix`) | Fetching reviews, task execution |\n| `final-verify` | `\u002Ffinal-verify` | Enforcing verification before completion claims | Early planning, brainstorming |\n| `workflow-memory` | (internal) | Maintaining cross-task workflow memory | PR reviews, user preferences |\n| `productize-runtime` | `\u002Fproductize-runtime` | Learning how to use the Productize CLI runtime | Executing workflow steps |\n\n## Productize Skills Summary\n\nProductize skills are bundled alongside the Productize workflow skills. Use\n`\u002Fproductize` as the Productize router, or call namespaced skills directly when\nthe job is clear.\n\n| Skill | Trigger | When To Use |\n| --- | --- | --- |\n| `productize` | `\u002Fproductize` | Route product, strategy, growth, delivery, design, analytics, finance, launch, or AI-builder work |\n| `productize-0-1` | `\u002Fproductize-0-1` | Turn a raw product idea or new capability bet into a first shipped slice |\n| `productize-product-review` | `\u002Fproductize-product-review` | Review product scope, requirements, tradeoffs, and acceptance criteria |\n| `productize-design-review` | `\u002Fproductize-design-review` | Review UX, hierarchy, interaction quality, and visual polish |\n| `productize-eng-review` | `\u002Fproductize-eng-review` | Review architecture, implementation risk, data flow, and build readiness |\n| `productize-qa` | `\u002Fproductize-qa` | Define or review verification evidence, scenarios, evals, and regression risk |\n| `productize-release` | `\u002Fproductize-release` | Check ship readiness, rollback paths, launch blockers, and release evidence |\n\n## Optional Extension Skills\n\n| Skill | Trigger | When To Use | Install Flow |\n| --- | --- | --- | --- |\n| `idea-forge` | `\u002Fidea-forge` | Raw feature idea needs structured exploration before a PRD | `productize ext install --yes itseffi\u002Fproductize --remote github --ref \u003Ctag> --subdir extensions\u002Fidea-forge` -> `productize ext enable idea-forge` -> `productize setup` |\n\nFor detailed skill descriptions and inputs\u002Foutputs, read `references\u002Fskills-reference.md`.\n\n## Artifact Directory Structure\n\n```\n.productize\u002F\n  config.toml                          # Workspace configuration\n  project\u002F\n    context.md                          # Project context pack for future work\n    conventions.md                      # Detected commands and instruction sources\n    architecture.md                     # Repository map and promoted architecture ADRs\n    decisions.md                        # Promoted durable ADR content and shared memory\n    constraints.md                      # Durable constraints and unresolved risks\n    manual.md                           # Optional human-authored additions; never generated\n  tasks\u002F\n    \u003Cslug>\u002F                            # One directory per workflow\n      _idea.md                         # Idea spec (from idea-forge)\n      _prd.md                          # Product Requirements Document\n      _techspec.md                     # Technical Specification\n      _tasks.md                        # Master task list\n      task_01.md ... task_N.md         # Individual task files\n      adrs\u002F\n        adr-001.md ... adr-NNN.md      # Architecture Decision Records\n      reviews-NNN\u002F\n        issue_001.md ... issue_N.md    # Review issues with round metadata in frontmatter\n      memory\u002F\n        MEMORY.md                      # Shared workflow memory\n        task_01.md ... task_N.md       # Per-task memory\n    _archived\u002F\n      \u003Ctimestamp>-\u003Cslug>\u002F             # Archived completed workflows\n  agents\u002F\n    \u003Cname>\u002F                            # Workspace-scoped reusable agents\n      AGENT.md                         # Agent definition\n      mcp.json                         # Optional MCP server config\n  extensions\u002F                          # Workspace-scoped extensions\n```\n\nGlobal paths:\n- `~\u002F.productize\u002Fagents\u002F\u003Cname>\u002F` -- global reusable agents (workspace overrides global)\n- `~\u002F.productize\u002Fextensions\u002F` -- user-scoped extensions\n- `~\u002F.productize\u002Fruns\u002F\u003Crun-id>\u002F` -- daemon-managed run artifacts and persisted exec sessions\n- `~\u002F.productize\u002Fdb\u002Fglobal.db` -- daemon workspace, workflow, task, and review catalog\n\n## Project Knowledge Lifecycle\n\n`context.md`, `conventions.md`, `architecture.md`, `decisions.md`, and\n`constraints.md` are canonical generated read models. Productize owns and\nrewrites them only when they carry the `productize:project-knowledge` marker.\nKeep deliberate human-authored additions in `.productize\u002Fproject\u002Fmanual.md`.\n\n- `productize onboard existing` performs the complete first-time integration and\n  records repository Knowledge Coverage in `context.md`.\n- `productize init existing` explicitly creates or refreshes only the read models.\n- A successful `productize sync` catalogs authored workflow artifacts and then\n  refreshes project knowledge.\n- `productize archive` moves an eligible workflow first and refreshes afterward,\n  preserving durable ADR content and shared memory from archived workflows.\n\nIdea, PRD, TechSpec, task-generation, and task-execution workflows read all five\ncanonical documents when present, plus `manual.md` when present. Product-facing\nartifacts use architecture and constraints only for feasibility and boundaries.\n\nSync or archive can succeed while the derived refresh reports `degraded: true`.\nText output exposes the status, checksum, skipped paths, and warnings; JSON uses\nthe optional `project_knowledge` object with `updated`, `unchanged`, `skipped`,\n`warnings`, `source_checksum`, and `degraded`. Resolve the warnings and run\n`productize sync` again to repair stale knowledge.\n\n## Configuration\n\nWorkspace defaults live in `.productize\u002Fconfig.toml`. CLI flags always override config values.\n\n```toml\n[defaults]\nide = \"claude\"\nmodel = \"opus\"\nauto_commit = true\nreasoning_effort = \"high\"\nadd_dirs = [\"..\u002Fshared-lib\"]\n\n[tasks]\ntypes = [\"frontend\", \"backend\", \"docs\", \"test\", \"infra\", \"refactor\", \"chore\", \"bugfix\"]\n\n[tasks.run]\nconcurrent = 1\ninclude_completed = false\nverify_command = \"make verify\"\n\n[fix_reviews]\nconcurrent = 2\nbatch_size = 3\n\n[fetch_reviews]\nprovider = \"coderabbit\"\nnitpicks = false\n\n[exec]\nverbose = false\npersist = false\n```\n\nFor all fields, types, and defaults, read `references\u002Fconfig-reference.md`.\n\n## Reusable Agents and the Advisor Pattern\n\nReusable agents are standalone personas that can be invoked via `productize exec --agent \u003Cname>` or referenced by skills through `run_agent`.\n\n**Discovery order:** workspace (`.productize\u002Fagents\u002F\u003Cname>\u002F`) overrides global (`~\u002F.productize\u002Fagents\u002F\u003Cname>\u002F`).\n\n**Agent definition:** Each agent has an `AGENT.md` with YAML frontmatter (`title`, `description`) and optional `mcp.json` for MCP server configuration.\n\n**Advisor agents shipped by the optional `idea-forge` extension**:\n\n| Agent | Perspective |\n| --- | --- |\n| `pragmatic-engineer` | Execution-focused, delivery speed, maintenance burden |\n| `architect-advisor` | Long-term system coherence, boundaries, coupling |\n| `security-advocate` | Attack vectors, compliance, data protection |\n| `product-mind` | User impact, business value, opportunity cost |\n| `stress-tester` | Challenges assumptions, surfaces risks, stress-tests |\n| `the-thinker` | Cross-domain patterns, structural reframing |\n\nInstall flow: `productize ext install --yes itseffi\u002Fproductize --remote github --ref \u003Ctag> --subdir extensions\u002Fidea-forge` -> `productize ext enable idea-forge` -> `productize setup`.\n\nThe `idea-forge` skill uses these agents in an advisor debate to challenge feature scope and surface risks.\n\nManagement commands: `productize agents list`, `productize agents inspect \u003Cname>`.\n\n## Extensions\n\nExecutable plugins that extend Productize at runtime via JSON-RPC 2.0 on stdin\u002Fstdout.\n\n- **Three scopes:** bundled (shipped with Productize), user (`~\u002F.productize\u002Fextensions\u002F`), workspace (`.productize\u002Fextensions\u002F`). Workspace overrides user overrides bundled.\n- **Disabled by default.** Enable explicitly with `productize ext enable \u003Cname>` or `--extensions` flag on `exec`.\n- **Capabilities:** lifecycle observation, prompt decoration, plan injection, agent session modification, review provider registration.\n- **SDKs:** TypeScript (`@productize\u002Fextension-sdk`), Go (`sdk\u002Fextension`).\n- **Scaffolding:** `npx @productize\u002Fcreate-extension` generates extension boilerplate.\n\nManagement: `productize ext list`, `productize ext inspect \u003Cname>`, `productize ext install \u003Csource>`, `productize ext uninstall \u003Cname>`, `productize ext enable\u002Fdisable \u003Cname>`, `productize ext doctor`.\n\n## Common Patterns\n\n- For an existing repository, run `productize onboard existing --agent \u003Cname>` before PRD creation.\n- Use `productize setup` separately for new repositories or manual installation control. Select one agent unless multiple explicit targets are required.\n- Use `productize setup cleanup --keep-agent \u003Cname> --dry-run` when an older installation populated unwanted agent directories. Never delete drifted or unknown paths automatically.\n- Follow the pipeline in order: onboarding (existing repos) -> idea (optional) -> PRD -> TechSpec -> Tasks -> Execution -> Review -> Fix.\n- Configure workspace defaults in `.productize\u002Fconfig.toml` to reduce repetitive CLI flags.\n- Run `productize tasks validate --name \u003Cslug>` before `productize tasks run` to catch metadata issues early.\n- Use `productize archive` to clean up fully completed workflows and keep the tasks directory focused.\n- Use `productize exec --agent \u003Cname>` for ad hoc prompts with a specific advisor perspective.\n- Use `productize exec --persist` to save session artifacts for later resumption with `--run-id`.\n\n## Anti-Patterns\n\n- **Skipping pipeline stages.** Running `productize tasks run` without a PRD and task files produces poor results.\n- **Invoking `execute-task` directly.** Use `productize tasks run`, which handles dispatch, sequencing, memory, and tracking.\n- **Mixing workflow skills out of order.** Running `\u002Fcreate-tasks` without a PRD and TechSpec leads to shallow task decomposition.\n- **Editing task file frontmatter manually.** Use `productize migrate` or `productize tasks validate` to fix metadata issues programmatically.\n- **Confusing skills with CLI commands.** Skills (slash commands like `\u002Fcreate-prd`) run inside an agent session. CLI commands (`productize tasks run`) run in the terminal.\n- **Skipping verification.** Always use `final-verify` before claiming task completion or creating commits.\n","# Productize Reference Guide\n\nComprehensive reference for the Productize CLI and its daemon-backed product workflow runtime.\n\n## What Is Productize\n\nProductize is a Go CLI and daemon-backed runtime for shipping products with AI agents. It keeps product work in markdown, syncs authored workflow artifacts into daemon state, supervises ACP-backed agent runs, and supports review\u002Ffix loops, reusable agents, extensions, memory, gates, and routed product skills.\n\nKey characteristics:\n\n- **Agent-agnostic.** Supports claude, codex, copilot, cursor-agent, droid, gemini, opencode, and pi as ACP runtimes.\n- **Skills-based.** Bundled Productize workflow skills and Productize product-operating skills (installed via `productize setup`) teach agents how to execute each workflow phase.\n- **Artifact-driven.** Planning and review artifacts live as markdown under `.productize\u002Ftasks\u002F\u003Cslug>\u002F`, versioned alongside the codebase.\n- **Daemon-backed runtime.** A home-scoped daemon owns run state, workspace registration, snapshots, streams, and the synced `global.db` catalog under `~\u002F.productize\u002F`.\n- **Single binary runtime.** The daemon is launched from the same binary; there are no external control planes.\n\n## Workflow Pipeline Overview\n\nThe standard development pipeline follows these phases in order. Each phase produces artifacts consumed by the next.\n\n1. **Existing Project Onboarding** -- `productize onboard existing --agent \u003Cname>` resolves the repository root, inventories existing code and documentation, generates project knowledge, installs Productize, and registers the workspace.\n2. **Setup** (new repos or manual control) -- interactive `productize setup` selects one agent target. Repeated `--agent` flags explicitly install into several targets; `--all-agents` is the only all-target shortcut.\n3. **Ideation** (optional) -- install and enable the first-party `idea-forge` extension, run `productize setup`, then use `\u002Fidea-forge` to expand a raw idea into a structured, research-backed spec at `.productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md`.\n4. **Requirements** -- `\u002Fcreate-prd` creates a business-focused Product Requirements Document at `.productize\u002Ftasks\u002F\u003Cslug>\u002F_prd.md` with ADRs.\n5. **Technical Design** -- `\u002Fcreate-techspec` translates the PRD into a technical specification at `.productize\u002Ftasks\u002F\u003Cslug>\u002F_techspec.md` with ADRs.\n6. **Task Decomposition** -- `\u002Fcreate-tasks` breaks down the PRD and TechSpec into independently implementable task files (`task_01.md`, `task_02.md`, etc.) and a master list at `_tasks.md`.\n7. **Execution** -- `productize tasks run \u003Cslug> --ide \u003Cruntime>` dispatches task files to the configured AI agent. Execution is sequential by default; `--concurrent N` enables bounded parallel execution of dependency-ready tasks.\n8. **Review** -- `\u002Freview-round` (manual AI review) or `productize reviews fetch \u003Cslug> --provider coderabbit --pr \u003CN>` (external provider) produces review issue files under `reviews-NNN\u002F`.\n9. **Remediation** -- `productize reviews fix \u003Cslug>` processes review issues, triages, fixes, and verifies each one.\n10. **Archive** -- `productize archive --name \u003Cslug>` moves fully completed workflows to `.productize\u002Ftasks\u002F_archived\u002F`, then refreshes project knowledge.\n\nRepeat phases 7-8 until the review is clean, then merge.\n\n```dot\ndigraph productize_pipeline {\n    \"productize onboard existing\" [shape=box];\n    \"\u002Fidea-forge (optional)\" [shape=box];\n    \"\u002Fcreate-prd\" [shape=box];\n    \"\u002Fcreate-techspec\" [shape=box];\n    \"\u002Fcreate-tasks\" [shape=box];\n    \"productize tasks run\" [shape=box];\n    \"Review (manual or provider)\" [shape=box];\n    \"productize reviews fix\" [shape=box];\n    \"Reviews clean?\" [shape=diamond];\n    \"productize archive\" [shape=doublecircle];\n\n    \"productize onboard existing\" -> \"\u002Fidea-forge (optional)\";\n    \"\u002Fidea-forge (optional)\" -> \"\u002Fcreate-prd\";\n    \"\u002Fcreate-prd\" -> \"\u002Fcreate-techspec\";\n    \"\u002Fcreate-techspec\" -> \"\u002Fcreate-tasks\";\n    \"\u002Fcreate-tasks\" -> \"productize tasks run\";\n    \"productize tasks run\" -> \"Review (manual or provider)\";\n    \"Review (manual or provider)\" -> \"productize reviews fix\";\n    \"productize reviews fix\" -> \"Reviews clean?\";\n    \"Reviews clean?\" -> \"Review (manual or provider)\" [label=\"no\"];\n    \"Reviews clean?\" -> \"productize archive\" [label=\"yes\"];\n}\n```\n\nFor a detailed step-by-step walkthrough of each phase, read `references\u002Fworkflow-guide.md`.\n\n## CLI Commands Quick Reference\n\n| Command | Purpose | Key Flags |\n| --- | --- | --- |\n| **Setup & Config** | | |\n| `productize onboard existing` | Integrate an existing repository, install agent assets, and register it | `--agent`, `--dry-run`, `--skip-setup`, `--skip-register`, `--format` |\n| `productize init existing` | Create or refresh only `.productize\u002Fproject\u002F` knowledge docs | `--dry-run`, `--exclude`, `--force`, `--format` |\n| `productize setup` | Install skills into one selected agent target by default | `--agent`, `--all-agents`, `--skill`, `--global`, `--copy`, `--list`, `--yes` |\n| `productize setup cleanup` | Safely remove old managed agent targets | `--keep-agent`, `--global`, `--dry-run`, `--yes`, `--format` |\n| `productize upgrade` | Update CLI to latest release | |\n| **Workflow Execution** | | |\n| `productize daemon` | Manage the home-scoped daemon lifecycle | `start`, `status`, `stop` |\n| `productize workspaces` | Inspect and manage daemon workspace registrations | `list`, `show`, `register`, `unregister`, `resolve` |\n| `productize tasks run` | Execute PRD task files through the daemon | `--name`, `--concurrent`, `--verify-command`, `--format`, `--attach`, `--stream`, `--detach`, `--task-runtime` |\n| `productize exec` | Execute an ad hoc prompt | `--agent`, `--format`, `--prompt-file`, `--persist`, `--run-id` |\n| `productize runs` | Attach, watch, and purge daemon-managed runs | `attach`, `watch`, `purge` |\n| **Review** | | |\n| `productize reviews fetch` | Fetch provider review comments | `--provider`, `--pr`, `--name`, `--round` |\n| `productize reviews fix` | Process review issue files | `--name`, `--round`, `--concurrent`, `--batch-size`, `--ide` |\n| **Utilities** | | |\n| `productize tasks validate` | Validate task file metadata | `--name`, `--tasks-dir`, `--format` |\n| `productize sync` | Reconcile workflow artifacts into daemon `global.db`, then refresh project knowledge | `--name`, `--root-dir`, `--tasks-dir` |\n| `productize archive` | Move daemon-eligible completed workflows to archive, then refresh project knowledge | `--name`, `--root-dir`, `--tasks-dir` |\n| `productize migrate` | Convert legacy artifacts to frontmatter | `--name`, `--dry-run`, `--reviews-dir` |\n| **Agent Management** | | |\n| `productize agents list` | List resolved reusable agents | |\n| `productize agents inspect` | View agent definition and defaults | `\u003Cname>` |\n| **Extensions** | | |\n| `productize ext list` | List extensions | |\n| `productize ext inspect` | View extension details | `\u003Cname>` |\n| `productize ext install` | Install an extension from a local path or GitHub repo archive | `\u003Csource>`, `--remote`, `--ref`, `--subdir` |\n| `productize ext uninstall` | Remove an extension | `\u003Cname>` |\n| `productize ext enable\u002Fdisable` | Toggle extension | `\u003Cname>` |\n| `productize ext doctor` | Diagnose extension issues | |\n\nCommon flags shared by `tasks run`, `exec`, and `reviews fix`: `--ide`, `--model`, `--reasoning-effort`, `--add-dir`, `--auto-commit`, `--dry-run`.\n\nFor complete flag documentation, read `references\u002Fcli-reference.md`.\n\n## Core Skills Summary\n\n| Skill | Trigger | When To Use | Do Not Use For |\n| --- | --- | --- | --- |\n| `create-prd` | `\u002Fcreate-prd` | Building a Product Requirements Document | TechSpec, task breakdown, coding |\n| `create-techspec` | `\u002Fcreate-techspec` | Translating PRD into technical design | PRD creation, task execution |\n| `create-tasks` | `\u002Fcreate-tasks` | Decomposing PRD+TechSpec into task files | Execution, review |\n| `execute-task` | (internal) | Executing a single PRD task (called by `productize tasks run`) | Direct invocation, review work |\n| `review-round` | `\u002Freview-round` | Performing comprehensive code review | Fetching external reviews, fixing |\n| `fix-reviews` | (internal) | Remediating review issues (called by `productize reviews fix`) | Fetching reviews, task execution |\n| `final-verify` | `\u002Ffinal-verify` | Enforcing verification before completion claims | Early planning, brainstorming |\n| `workflow-memory` | (internal) | Maintaining cross-task workflow memory | PR reviews, user preferences |\n| `productize-runtime` | `\u002Fproductize-runtime` | Learning how to use the Productize CLI runtime | Executing workflow steps |\n\n## Productize Skills Summary\n\nProductize skills are bundled alongside the Productize workflow skills. Use\n`\u002Fproductize` as the Productize router, or call namespaced skills directly when\nthe job is clear.\n\n| Skill | Trigger | When To Use |\n| --- | --- | --- |\n| `productize` | `\u002Fproductize` | Route product, strategy, growth, delivery, design, analytics, finance, launch, or AI-builder work |\n| `productize-0-1` | `\u002Fproductize-0-1` | Turn a raw product idea or new capability bet into a first shipped slice |\n| `productize-product-review` | `\u002Fproductize-product-review` | Review product scope, requirements, tradeoffs, and acceptance criteria |\n| `productize-design-review` | `\u002Fproductize-design-review` | Review UX, hierarchy, interaction quality, and visual polish |\n| `productize-eng-review` | `\u002Fproductize-eng-review` | Review architecture, implementation risk, data flow, and build readiness |\n| `productize-qa` | `\u002Fproductize-qa` | Define or review verification evidence, scenarios, evals, and regression risk |\n| `productize-release` | `\u002Fproductize-release` | Check ship readiness, rollback paths, launch blockers, and release evidence |\n\n## Optional Extension Skills\n\n| Skill | Trigger | When To Use | Install Flow |\n| --- | --- | --- | --- |\n| `idea-forge` | `\u002Fidea-forge` | Raw feature idea needs structured exploration before a PRD | `productize ext install --yes itseffi\u002Fproductize --remote github --ref \u003Ctag> --subdir extensions\u002Fidea-forge` -> `productize ext enable idea-forge` -> `productize setup` |\n\nFor detailed skill descriptions and inputs\u002Foutputs, read `references\u002Fskills-reference.md`.\n\n## Artifact Directory Structure\n\n```\n.productize\u002F\n  config.toml                          # Workspace configuration\n  project\u002F\n    context.md                          # Project context pack for future work\n    conventions.md                      # Detected commands and instruction sources\n    architecture.md                     # Repository map and promoted architecture ADRs\n    decisions.md                        # Promoted durable ADR content and shared memory\n    constraints.md                      # Durable constraints and unresolved risks\n    manual.md                           # Optional human-authored additions; never generated\n  tasks\u002F\n    \u003Cslug>\u002F                            # One directory per workflow\n      _idea.md                         # Idea spec (from idea-forge)\n      _prd.md                          # Product Requirements Document\n      _techspec.md                     # Technical Specification\n      _tasks.md                        # Master task list\n      task_01.md ... task_N.md         # Individual task files\n      adrs\u002F\n        adr-001.md ... adr-NNN.md      # Architecture Decision Records\n      reviews-NNN\u002F\n        issue_001.md ... issue_N.md    # Review issues with round metadata in frontmatter\n      memory\u002F\n        MEMORY.md                      # Shared workflow memory\n        task_01.md ... task_N.md       # Per-task memory\n    _archived\u002F\n      \u003Ctimestamp>-\u003Cslug>\u002F             # Archived completed workflows\n  agents\u002F\n    \u003Cname>\u002F                            # Workspace-scoped reusable agents\n      AGENT.md                         # Agent definition\n      mcp.json                         # Optional MCP server config\n  extensions\u002F                          # Workspace-scoped extensions\n```\n\nGlobal paths:\n- `~\u002F.productize\u002Fagents\u002F\u003Cname>\u002F` -- global reusable agents (workspace overrides global)\n- `~\u002F.productize\u002Fextensions\u002F` -- user-scoped extensions\n- `~\u002F.productize\u002Fruns\u002F\u003Crun-id>\u002F` -- daemon-managed run artifacts and persisted exec sessions\n- `~\u002F.productize\u002Fdb\u002Fglobal.db` -- daemon workspace, workflow, task, and review catalog\n\n## Project Knowledge Lifecycle\n\n`context.md`, `conventions.md`, `architecture.md`, `decisions.md`, and\n`constraints.md` are canonical generated read models. Productize owns and\nrewrites them only when they carry the `productize:project-knowledge` marker.\nKeep deliberate human-authored additions in `.productize\u002Fproject\u002Fmanual.md`.\n\n- `productize onboard existing` performs the complete first-time integration and\n  records repository Knowledge Coverage in `context.md`.\n- `productize init existing` explicitly creates or refreshes only the read models.\n- A successful `productize sync` catalogs authored workflow artifacts and then\n  refreshes project knowledge.\n- `productize archive` moves an eligible workflow first and refreshes afterward,\n  preserving durable ADR content and shared memory from archived workflows.\n\nIdea, PRD, TechSpec, task-generation, and task-execution workflows read all five\ncanonical documents when present, plus `manual.md` when present. Product-facing\nartifacts use architecture and constraints only for feasibility and boundaries.\n\nSync or archive can succeed while the derived refresh reports `degraded: true`.\nText output exposes the status, checksum, skipped paths, and warnings; JSON uses\nthe optional `project_knowledge` object with `updated`, `unchanged`, `skipped`,\n`warnings`, `source_checksum`, and `degraded`. Resolve the warnings and run\n`productize sync` again to repair stale knowledge.\n\n## Configuration\n\nWorkspace defaults live in `.productize\u002Fconfig.toml`. CLI flags always override config values.\n\n```toml\n[defaults]\nide = \"claude\"\nmodel = \"opus\"\nauto_commit = true\nreasoning_effort = \"high\"\nadd_dirs = [\"..\u002Fshared-lib\"]\n\n[tasks]\ntypes = [\"frontend\", \"backend\", \"docs\", \"test\", \"infra\", \"refactor\", \"chore\", \"bugfix\"]\n\n[tasks.run]\nconcurrent = 1\ninclude_completed = false\nverify_command = \"make verify\"\n\n[fix_reviews]\nconcurrent = 2\nbatch_size = 3\n\n[fetch_reviews]\nprovider = \"coderabbit\"\nnitpicks = false\n\n[exec]\nverbose = false\npersist = false\n```\n\nFor all fields, types, and defaults, read `references\u002Fconfig-reference.md`.\n\n## Reusable Agents and the Advisor Pattern\n\nReusable agents are standalone personas that can be invoked via `productize exec --agent \u003Cname>` or referenced by skills through `run_agent`.\n\n**Discovery order:** workspace (`.productize\u002Fagents\u002F\u003Cname>\u002F`) overrides global (`~\u002F.productize\u002Fagents\u002F\u003Cname>\u002F`).\n\n**Agent definition:** Each agent has an `AGENT.md` with YAML frontmatter (`title`, `description`) and optional `mcp.json` for MCP server configuration.\n\n**Advisor agents shipped by the optional `idea-forge` extension**:\n\n| Agent | Perspective |\n| --- | --- |\n| `pragmatic-engineer` | Execution-focused, delivery speed, maintenance burden |\n| `architect-advisor` | Long-term system coherence, boundaries, coupling |\n| `security-advocate` | Attack vectors, compliance, data protection |\n| `product-mind` | User impact, business value, opportunity cost |\n| `stress-tester` | Challenges assumptions, surfaces risks, stress-tests |\n| `the-thinker` | Cross-domain patterns, structural reframing |\n\nInstall flow: `productize ext install --yes itseffi\u002Fproductize --remote github --ref \u003Ctag> --subdir extensions\u002Fidea-forge` -> `productize ext enable idea-forge` -> `productize setup`.\n\nThe `idea-forge` skill uses these agents in an advisor debate to challenge feature scope and surface risks.\n\nManagement commands: `productize agents list`, `productize agents inspect \u003Cname>`.\n\n## Extensions\n\nExecutable plugins that extend Productize at runtime via JSON-RPC 2.0 on stdin\u002Fstdout.\n\n- **Three scopes:** bundled (shipped with Productize), user (`~\u002F.productize\u002Fextensions\u002F`), workspace (`.productize\u002Fextensions\u002F`). Workspace overrides user overrides bundled.\n- **Disabled by default.** Enable explicitly with `productize ext enable \u003Cname>` or `--extensions` flag on `exec`.\n- **Capabilities:** lifecycle observation, prompt decoration, plan injection, agent session modification, review provider registration.\n- **SDKs:** TypeScript (`@productize\u002Fextension-sdk`), Go (`sdk\u002Fextension`).\n- **Scaffolding:** `npx @productize\u002Fcreate-extension` generates extension boilerplate.\n\nManagement: `productize ext list`, `productize ext inspect \u003Cname>`, `productize ext install \u003Csource>`, `productize ext uninstall \u003Cname>`, `productize ext enable\u002Fdisable \u003Cname>`, `productize ext doctor`.\n\n## Common Patterns\n\n- For an existing repository, run `productize onboard existing --agent \u003Cname>` before PRD creation.\n- Use `productize setup` separately for new repositories or manual installation control. Select one agent unless multiple explicit targets are required.\n- Use `productize setup cleanup --keep-agent \u003Cname> --dry-run` when an older installation populated unwanted agent directories. Never delete drifted or unknown paths automatically.\n- Follow the pipeline in order: onboarding (existing repos) -> idea (optional) -> PRD -> TechSpec -> Tasks -> Execution -> Review -> Fix.\n- Configure workspace defaults in `.productize\u002Fconfig.toml` to reduce repetitive CLI flags.\n- Run `productize tasks validate --name \u003Cslug>` before `productize tasks run` to catch metadata issues early.\n- Use `productize archive` to clean up fully completed workflows and keep the tasks directory focused.\n- Use `productize exec --agent \u003Cname>` for ad hoc prompts with a specific advisor perspective.\n- Use `productize exec --persist` to save session artifacts for later resumption with `--run-id`.\n\n## Anti-Patterns\n\n- **Skipping pipeline stages.** Running `productize tasks run` without a PRD and task files produces poor results.\n- **Invoking `execute-task` directly.** Use `productize tasks run`, which handles dispatch, sequencing, memory, and tracking.\n- **Mixing workflow skills out of order.** Running `\u002Fcreate-tasks` without a PRD and TechSpec leads to shallow task decomposition.\n- **Editing task file frontmatter manually.** Use `productize migrate` or `productize tasks validate` to fix metadata issues programmatically.\n- **Confusing skills with CLI commands.** Skills (slash commands like `\u002Fcreate-prd`) run inside an agent session. CLI commands (`productize tasks run`) run in the terminal.\n- **Skipping verification.** Always use `final-verify` before claiming task completion or creating commits.\n",{"name":5,"description":7},"main","f177680a573a242a81bd0a776f9681f620e6d74c","skills\u002Fproductize-runtime",0,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize","https:\u002F\u002Fgithub.com\u002Fitseffi","2026-08-07 20:07:32",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add itseffi\u002Fproductize --skill productize-runtime",{"tool":37,"command":38},"bunx","bunx skills add itseffi\u002Fproductize --skill productize-runtime",{"tool":40,"command":41},"pnpm","pnpm dlx skills add itseffi\u002Fproductize --skill productize-runtime","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-runtime\u002FSKILL.md",true,[45,51,55,59],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fcli-reference.md","REFERENCE","参考文档",16139,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-runtime\u002Freferences\u002Fcli-reference.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fconfig-reference.md",13680,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-runtime\u002Freferences\u002Fconfig-reference.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fskills-reference.md",9524,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-runtime\u002Freferences\u002Fskills-reference.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fworkflow-guide.md",11582,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-runtime\u002Freferences\u002Fworkflow-guide.md",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7357QB5M87V95F82E73V2TF","workflow-memory","Maintains workflow-scoped task memory for Productize runs using .productize\u002Ftasks\u002F\u003Cname>\u002Fmemory\u002F files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across PRD task executions. Do not use for PR review remediation, global user preferences, or programmatic event-log summarization.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-memory\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7357K97HSYEHAQTW5ZKM4CE","review-round","Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing PRD tasks, or editing source code.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Freview-round\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7357F2NZE5NSYM2SJXEGBFZ","productize","Productize root skill for building, shipping, operating, and growing AI products inside a coding harness. Routes work across thesis framing, discovery, research, positioning, finance, decision making, requirements, design, metrics, AI-builder execution, code implementation, verification, stakeholder narratives, growth, launch, operation, and learning workflows. Use when the user wants to build a product from zero, improve an existing product, or needs product work that spans multiple lifecycle stages before code, launch, operation, or growth execution.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7357B48F8MK86EQF135FJQ6","productize-wwas","Why-What-Acceptance. Use when writing backlog items in Why-What-Acceptance format, breaking features into independent valuable work, or adding strategic context to delivery items.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-wwas\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M735783CDA9MQ0SPR9X6QZSE","productize-writing-plans","Create comprehensive implementation plans with bite-sized tasks. Use when you have requirements before touching code.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-writing-plans\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M735750V5Q6WRBX1ZFGNRMEB","productize-write-spec","Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea into a structured document, scoping goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into phases.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-write-spec\u002FSKILL.md",[],[]]