القائمة
De-risk surviving Infiquetra ideas before committing to a build. Slots after saga:ideate and before saga:brainstorm or saga:plan. Per idea: riskiest assumption, smallest build-to-learn, success metric threshold, premise check, and operator-confirmed route.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Route proposed Team Mimir profile behavior changes into target-owned Hermes dialogue after producer-owned custody classification.
Compile and review an approved Workflow Contract for Codex V2 graph, profile, write, check, reviewer, fallback, and external-action consistency without launching work.
Explicitly run an operator-approved Infiquetra Workflow Contract as a root-orchestrated Codex V2 DAG with exact profiles, runtime receipts, bounded writes, one independent review, one remediation, and one targeted recheck.
Deep-dive one chosen Infiquetra idea into a right-sized requirements document before planning.
Run a structured Infiquetra code-quality review at the work-to-PR boundary. Reads the merge-base diff, runs a built-vs-planned audit plus judgment-selected review lenses, validates findings, writes a durable review artifact, appends to the work-thread saga, and routes — without mutating code. Triggers on "review this PR", "code review", "check my diff", "pre-PR review", or a /work hand-in before shipping.
Review Infiquetra plans, requirements, and SDLC documents for implementation readiness.
| name | product-review |
| description | De-risk surviving Infiquetra ideas before committing to a build. Slots after saga:ideate and before saga:brainstorm or saga:plan. Per idea: riskiest assumption, smallest build-to-learn, success metric threshold, premise check, and operator-confirmed route. |
| argument-hint | [ideation doc path | topic | idea list] |
Use this after saga:ideate when ideas are promising but the bet is not proven enough for full
requirements or implementation planning.
Product review answers: which surviving ideas are worth building, and what is the cheapest way to learn before committing?
It writes docs/product-reviews/YYYY-MM-DD-<topic>-product-review.md. It does not write requirements,
plans, code, issues, Saga state, commits, PRs, or deployment state.
saga:ideate generates and ranks grounded candidates.saga:product-review de-risks those candidates by assumption, experiment, metric, and premise.saga:brainstorm deepens a validated idea into requirements.saga:plan can consume an experiment-ready prototype as a scoped spike.Resolve the subject from $ARGUMENTS.
docs/ideation/ artifact, read the ranked survivors and revivable cut.Offer near-miss revivals when an ideation artifact includes a cut list. Use:
python3 plugins/saga/scripts/product_review.py revival --survivors '<json>' --cut '<json>'
Review each idea one at a time:
Compute route recommendations with:
python3 plugins/saga/scripts/product_review.py route --ideas '<json>'
Confirm routes with the operator before treating them as real.
Write the product-review artifact using references/product-review-template.md.
Route onward:
saga:plan with maturity: experiment-ready;saga:brainstorm with maturity: requirements-ready;deferred-context.needs_threshold.saga/references/formatting-style.md.references/product-review-template.mdplugins/saga/scripts/product_review.pysaga/references/formatting-style.md