architect-analyze
Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or…
Use when orchestrating a product lifecycle (specify/init → clarify → implement → analyze) to generate or verify PRD.md.
$ npx -y skills add tikalk/adlc-team-skills --skill factory-product --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/factory-productContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when orchestrating a product lifecycle (specify/init → clarify → implement → analyze) to generate or verify PRD.md.
name: factory-product description: Use when orchestrating a product lifecycle (specify/init → clarify → implement → analyze) to generate or verify PRD.md. disable-model-invocation: true
`factory-product` orchestrates the product-decisions lifecycle. It coordinates individual product-related skills (`product-init`, `product-specify`, `product-clarify`, `product-implement`, `product-analyze`) to maintain a consistent `PRD.md` at `docs/adlc/product/PRD.md` (the shared layout).
It operates as a **Kind-A DAG orchestrator** in alignment with the shared executor engine contract in `factory-mission/references/executor.md`.
---
**When NOT to use**:
---
`factory-product` implements a **fixed named-skill DAG** (`fixed` step resolution):
1. **`specify`** (`generate` phase) -> Invoke `product-specify` to collaboratively capture PDR drafts in `.adlc/drafts/pdr/`. 2. **`clarify`⭐** (`clarify` phase) -> Invoke `product-clarify` to run interactive quality checks and mark PDRs Accepted (human sign-off gate). 3. **`implement`** (`build` phase) -> Invoke `product-implement` to compile accepted PDRs into `docs/adlc/product/PRD.md` and promote them to `docs/adlc/memory/pdr/`. 4. **`analyze`** (`analyze` phase) -> Invoke `product-analyze` to verify PRD/PDR consistency and output a severity-ranked report.
1. **`init`** (`generate` phase) -> Invoke `product-init` to reverse-engineer draft PDRs from the existing codebase. 2. **`clarify`⭐** → **`implement`** → **`analyze`** (same as Greenfield).
1. **`analyze`** (`analyze` phase) -> Run product-analyze first to detect drift. 2. **`clarify`⭐** → **`implement`** → **`analyze`** (drift-correction cycle).
---
`factory-product` overrides the shared executor engine primitives as follows:
1. **Publish Target**: Fixed to `local`. Outputs are written to `docs/adlc/memory/pdr/` and `docs/adlc/product/PRD.md`. If tracker-integrated, a `tracker` completion summary comment is also posted. 2. **Output Types**: Steps use the following `output_type` assignments:
3. **Correction Loop**: If `analyze` returns `CRITICAL` or `HIGH` consistency errors, the executor routes back to `clarify` with the analyze marker in `reads_from`. `clarify` reads the findings from the PR/MR/issue comment bus (or local fallback). This loop is bounded by `max_corrections` (default 2); if exceeded, the orchestrator halts for human review. 4. **Supervision Default**: `hybrid`. A human gate is hard-enforced at `clarify`⭐ (for PDR approvals) and at final `PRD.md` review. 5. **Pre-flight Check**: Verifies that the `product-*` lifecycle skills are installed in the workspace before beginning Phase 0.
Agent skills that give coding agents your team's context at session start, so they stop working like strangers.
Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or…
Use when architecture work starts or a tech-stack or pattern decision emerges — injects the project ADR index…
Use when ADRs need review, gaps need filling, or ADR status must be approved as Accepted before architecture generation.
Use when accepted ADRs exist and AD.md must be produced or updated as unified architecture documentation.
Use when bootstrapping architecture documentation for a brownfield project by reverse-engineering ADRs from an existing codebase.
Use when you want guided trade-off analysis, multi-option comparison, or structured architectural decision facilitation before…