WabbleSpec-V7

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.

Produces a PENTEST-PLAN.md then PENTEST-FINDINGS.md for your OWN app's attack surface (each finding reproduced, non-destructive, with remediation) after a blocking authorization+ownership check. Use to test an owned app's attack surface defensively.

Produces a SAST-FINDINGS.md (static security + secret findings over your OWN code, each reproduced, with remediation) after a blocking authorization+ownership check. Use to statically scan owned code for vulnerabilities and secrets, defensively.

Finalizes a completed execution: delivery receipt, version bump, changelog. Use when every wave has passed, or /archive. Not before verification is green.

Cross-module architectural Q&A over memory — why / blast-radius / what-changed. Use to ask why something is the way it is, or /graph-query. Not for external research (research) or live status (status).

Offline memory analysis — gaps, clusters, staleness, dedup over the drawer corpus. Use to mine memory between sessions, or /memory-mine. Not for live search (memory-search) or automatic decay.

Produces a COPY.md (UI microcopy — labels, errors, empty states, tooltips, onboarding — each with surface, action, a 3-5 word voice, and a character budget); primes the editorial + accessibility gates. Use to write in-product microcopy from the brief.

Produces a DEPLOY-PLAN.md (artifact, environment, health check, rollback, cutover) so the eventual ship is observable and reversible; primes the testing + security + observability gates. Use to plan a deployment before executing it.

Produces an INCIDENT.md (symptom + timeline + evidence-grounded diagnosis + remediation with observed restoration + blameless postmortem + follow-ups); primes the observability + security + compliance gates. Use to record and learn from an incident.

Produces a LONG-FORM.md (a blog/article/landing/case-study/tutorial declaring content type, audience, goal, hook, outline, CTA) written outline-first with no padding and substantiated claims; primes the editorial + accessibility gates. Use to write a long-form piece from the brief.

Produces a MARKET-RESEARCH.md (synthesized user/market evidence supporting a specific product decision — method, sample, evidence-tied findings); primes the ai + compliance + accessibility gates. Use to turn evidence into a decision before the brief.

Produces a PRIORITIZATION.md (a ranked backlog under one stated framework — RICE/value-effort/WSJF — with per-item scores and an explicit cut line); primes the editorial + ai gates. Use to rank candidate items before sequencing a roadmap.

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.

Produces a RUNBOOK.md (a repeatable operational procedure — trigger, numbered steps each with an observable verification, escalation) that is reversible throughout; primes the engineering + observability gates. Use to document an operational procedure as a safe, checkable SOP.

Wave execution engine: runs the locked wave plan wave by wave, gated and receipted. Use when a reviewed wave plan is ready, /execute, or resuming. Not for writing or validating the plan.

Per-wave verification gate: spec compliance, then the wave's declared I4 mode. Use after a wave completes, or /verify. Not for fixing (executor) or pre-wave checks (guard).

Produces a PRD.md (scope, user stories, testable acceptance criteria, edge cases, out-of-scope) from an attested product brief; primes the editorial + accessibility + ai gates. Use after the product brief to spec what to build.

Produces a product contract - PRODUCT-BRIEF.md (problem, persona, success metric, non-goals) - before any solution; primes the editorial + accessibility gates. Use before speccing or building a product.

Standalone counter-case against an artifact (weaknesses, missed alternatives, failure modes), isolated from its author. Use to challenge a high-impact/low-confidence artifact. Not for verdicts.

Structured root-cause analysis (5-whys / fishbone / fault-tree) for a confirmed problem. Use when a failure's cause is unknown, or /analyze. Not for the executor's in-wave REVISE debug or unconfirmed bugs.

Token-driven visual-asset producer (icons/banners/logos/data-viz/slides) on DESIGN.md tokens + the aesthetic gate. Use to generate a visual asset when a design system exists. Not for non-visual.

Thin scheduler over the kernel: runs waves on the unblocked frontier, queues ambiguities, halts only for irreversible actions. Use for multi-wave guided/autonomous runs, or /autopilot.

C4 architecture diagrams (Context / Container / Component / Code) as Mermaid from the codebase. Use to document architecture, or /c4. Not for codebase discovery (explore) or stakeholder reports (report).

Produces a content contract - BRIEF.md (audience, goal, message, voice, structure) - before drafting; primes the editorial gate. Use before writing any content deliverable.

Breaks a locked task card into an ordered, independently-verifiable wave plan (checkpoints + rollback). Use after the card locks, or /decompose. Not for writing the card or running waves.

Produces a design contract (DESIGN.md + DTCG tokens) by querying the seeded design KB, write-back on a miss. Use before the first UI wave or when visuals drift; primes the aesthetic gate.

Multi-persona review of a planning artifact (coherence/feasibility/scope/adversarial) -> P0-P3 findings before lock. Use to review a task card, wave plan, or spec, or /document-review.

Produces a <DOMAIN>-BRIEF.md priming a pack's gates before a non-content, non-visual domain build. Use before that build; not for content (content-brief) or visuals (design-brief).

Graph-first codebase discovery → project-map.md. Use at session start on an unfamiliar project, or /explore. Not for root-cause analysis (analyze) or deriving a spec (reverse-document).

Feature-flag lifecycle — create, roll out (gated), audit, retire. Use to manage a feature flag, or /flag. Not for deploys (deploy) or infra config (ops domain).

Authority declaration for framework self-build (target=Framework): owns the framework surface so guard passes framework writes, never product (I11). Use on a target=Framework wave.

Spec-grounded verdict: scores an output against the adversary counter-case and the spec. Use after adversary, or when a verdict is needed. Not for generating the counter-case (adversary).

Pre-wave validator: schema, scope, invariants, authority, command-risk before any wave runs; cannot be bypassed. Use before each wave. Not for fixing (it blocks) or post-wave checks.

Hypothesis validation — is a suspected issue real? Classify TP/FP/INCONCLUSIVE/GAP. Use to confirm or refute a hypothesis, or /hunt. Not for finding the cause (analyze) or challenging a solution (adversary).

Entry gate: identifies the build domain (any domain, not just software) + complexity before other modules. Use at session start, on a domain change, or /intake.