factory-product
SkillDev toolsLets your agent run a guided product requirements process that drafts, reviews, and keeps PRD.md consistent.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the factory-product skill
About this skill
Use when orchestrating a product lifecycle (specify/init → clarify → implement → analyze) to generate or verify PRD.md.
What this skill tells your AI
The instructions your AI receives, as published by tikalk/adlc-team-skills in skills/factory/factory-product/SKILL.md and read by ahel’s review.
What this skill does
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 the project root.
It operates as a Kind-A DAG orchestrator in alignment with the shared executor engine contract in factory-mission/references/executor.md.
When to use
- You want to bootstrap, refine, or analyze a product's requirements and decisions (PDRs) end-to-end.
- You want a guided, accept-gated, and verified product definition process with a resume checkpoint.
When NOT to use:
- For software implementation task execution (use
factory-missioninstead). - For architecture decision records (use
factory-architectinstead).
Lifecycle DAG & Step Resolution
factory-product implements a fixed named-skill DAG (fixed step resolution):
Greenfield Route (default on empty project)
specify(generatephase) -> Invokeproduct-specifyto collaboratively capture PDR drafts in.adlc/drafts/pdr/.clarify⭐ (clarifyphase) -> Invokeproduct-clarifyto run interactive quality checks and mark PDRs Accepted (human sign-off gate).implement(buildphase) -> Invokeproduct-implementto compile accepted PDRs intoPRD.mdand promote them to.adlc/memory/pdr/.analyze(analyzephase) -> Invokeproduct-analyzeto verify PRD/PDR consistency and output a severity-ranked report.
Brownfield Route (default if code exists but no PDRs)
init(generatephase) -> Invokeproduct-initto reverse-engineer draft PDRs from the existing codebase.clarify⭐ →implement→analyze(same as Greenfield).
Refresh Route (default if PRD.md and memory PDRs already exist)
analyze(analyzephase) -> Run product-analyze first to detect drift.clarify⭐ →implement→analyze(drift-correction cycle).
Shared Executor Overrides
factory-product overrides the shared executor engine primitives as follows:
- Publish Target: Fixed to
local. Outputs are written to.adlc/memory/pdr/andPRD.md. If tracker-integrated, atrackercompletion summary comment is also posted. - Output Types: Steps use the following
output_typeassignments:specify/init→draft(PDR drafts stay in.adlc/drafts/pdr/, not published to comment bus)clarify⭐ →decision(accepted/rejected PDR list published to comment bus)implement→artifact-ref(PRD.md path reference published, content stays on disk)analyze→findings(severity-ranked consistency report published to comment bus)
- Correction Loop: If
analyzereturnsCRITICALorHIGHconsistency errors, the executor routes back toclarifywith the analyze marker inreads_from.clarifyreads the findings from the PR/MR/issue comment bus (or local fallback). This loop is bounded bymax_corrections(default 2); if exceeded, the orchestrator halts for human review. - Supervision Default:
hybrid. A human gate is hard-enforced atclarify⭐ (for PDR approvals) and at finalPRD.mdreview. - Pre-flight Check: Verifies that the
product-*lifecycle skills are installed in the workspace before beginning Phase 0.
Signals
- GitHub stars
- 137
- Forks
- 1
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
factory-product- Source
- github.com/tikalk/adlc-team-skills