Menu
Produces a ROADMAP.md (sequenced product bets with rationale + an explicit deferred set) from an attested product brief/strategy; primes the editorial + compliance gates. Use after the brief/PRD to sequence what to build when.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Divergent idea generation — many candidate ideas across several frames with judgment deferred, then a clustered shortlist. Use to open a solution space wide, or /brainstorm. Not for developing one idea (ideate) or picking one (propose).
Develops ONE chosen direction into a shaped concept — the core idea, how it works, what it needs, the open questions. Use to deepen a single idea, or /ideate. Not for generating many (brainstorm) or deciding among them (propose).
Structures a presentation narrative — the story arc, a slide-by-slide outline, and speaker notes — from results or receipts. Use to shape a talk or deck, or /present. Not for prose reports (report) or rendering visuals (asset).
Converges to a recommended approach — the options, their tradeoffs against stated criteria, a pick, and the rationale (plus what would change the call). Use to decide among approaches, or /propose. Not for generating options (brainstorm) or deep-diving one (ideate).
Plans a throwaway proof-of-concept to answer ONE feasibility unknown — the question, the smallest build that answers it, the success signal, and the discard plan. Use to de-risk before committing, or /prototype. Not for the real build (executor) or deciding (propose).
Produces a REDTEAM-FINDINGS.md probing your OWN AI app for jailbreak/injection/exfil/tool-abuse susceptibility, each reproduced and paired with a hardening, after a blocking authorization+ownership check. Use to red-team an owned AI system defensively.
| name | roadmap |
| description | Produces a ROADMAP.md (sequenced product bets with rationale + an explicit deferred set) from an attested product brief/strategy; primes the editorial + compliance gates. Use after the brief/PRD to sequence what to build when. |
The sequencing producer of the product domain — it turns an attested PRODUCT-BRIEF.md (the why/who)
and, when present, the prioritization output (the ranked what) into a ROADMAP.md (the what, in what
order, and why): sequenced bets, each with a rationale tied to the success metric, and an explicit
"deferred / not now" set. The bar is that the sequence has a stated logic (dependency / value / risk /
learning) and commitments are not overstated — horizons are confidence-tagged bets, not guaranteed
dates. Verified by Attestation: a named owner attests the sequencing is sound and owns the call; a
roadmap cannot be tested or measured at decision time. roadmap runs after strategy/prioritization, not
instead of them.
Does: resolve the roadmap sub_target, read the attested brief (and prioritization if present), and write a
ROADMAP.md of sequenced bets + per-bet rationale + dependencies + horizons + an explicit deferred set,
grounded in the brief's success metric; write a roadmap receipt. Does not: decide the problem/persona/
success metric (that is product-brief), rank the backlog under a framework (that is prioritization),
build the bets (the target domain's executor does), issue the gate verdict (the editorial/compliance gates
do — this primes them), or promise dates as guarantees (horizons are bets with confidence).
PRODUCT-BRIEF.md (and no strategy) yet — run product-brief first; a roadmap with
no problem/success contract sequences bets toward nothing.prioritization; a
roadmap sequences the chosen bets, it does not score them.ROADMAP.md still fits and nothing changed — editing it beats rewriting a commitment
stakeholders are tracking.roadmap.| Situation | Reference |
|---|---|
| The ROADMAP.md contract template | references/roadmap-template.md |
| Per-sub_target must-declares · overlay · vocabulary | ../acceptance/sub-targets.md · ../acceptance/overlay.md · ../vocabulary.md |
| The upstream product contract | the attested PRODUCT-BRIEF.md (+ prioritization output if present) |
PRODUCT-BRIEF.md (problem, persona, success metric, non-goals) — the anchoring contract.../vocabulary.md, ../acceptance/) + state/intake.json.PRODUCT-BRIEF.md; if absent, stop and route to product-brief (ordering:
strategy before the roadmap). Carry the success metric forward as the frame every bet is judged against.record_type: alert), never stated as a guarantee (the compliance gate).ROADMAP.md from references/roadmap-template.md; name the attestation owner.A gate failure is fixed before lock, not waived — these mirror the editorial/compliance gates.
product/ROADMAP.md if that dir exists) — persistence:
Spec-Anchored. Sequenced bets · per-bet rationale tied to the success metric · stated sequencing logic
· dependencies · horizons (confidence-tagged) · explicit deferred set · attestation owner.<workspace>/receipts/roadmap-receipt-<ts>.json): base schema + sub_target, bets,
sequencing_logic, horizons, deferred, roadmap_path, attested_by, gate_checks. persistence:
Spec-Anchored.product-brief first; do not sequence bets toward an unstated goal.Done when: a ROADMAP.md exists anchored to an attested brief, with sequenced bets each carrying a
rationale tied to the success metric, a stated sequencing logic, confidence-tagged horizons, an explicit
deferred set, and a named attestation owner; a roadmap receipt records the gate checks.
Not done if: there is no product brief; a bet lacks a rationale or a tie to the metric; the sequence has no stated logic; horizons are dated guarantees; the deferred set is missing; or commitments were stated as fact rather than flagged.
Next step: prioritization if the bets still need ranking under a framework; the target domain's
executor builds each bet (verified by that domain's mode); the named owner attests the roadmap (Attestation).
roadmap sequences bets
toward that attested metric. Always run product-brief first.roadmap sequences the
chosen bets into horizons; prioritization scores, roadmap sequences. Complementary.