[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EXGE6THFVF7V79XGHP8NHK":3,"skill-same:01M7EXGE6THFVF7V79XGHP8NHK":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":42,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M7EXGE6THFVF7V79XGHP8NHK","bazaar",null,"Orchestrating super-premium landing-page pipelines (Discover to Launch) across 6 craft axes with rubrics and quality gates. Not for a single LP section (Funnel) or design-only chains (Atelier).","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fdevsecops\u002Fbazaar\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bazaar\ndescription: \"Orchestrating super-premium landing-page pipelines (Discover to Launch) across 6 craft axes with rubrics and quality gates. Not for a single LP section (Funnel) or design-only chains (Atelier).\"\ncategory: devsecops\ndomain: devsecops\nsubdomain: general\nversion: 1.0.0\nlicense: MIT\nrisk: low\nsource:\n  repository: \"simota\u002Fagent-skills\"\n  commit: \"f425adcb21\"\n  imported_at: \"2026-09-20\"\n  license: \"MIT\"\nplatforms:\n  - claude-code\n  - cursor\n  - codex\n  - gemini\n  - antigravity\n  - copilot\n---\n\n# Bazaar\n\n\n\n\u003C!--\nCAPABILITIES_SUMMARY:\n- lp_chain_orchestration: End-to-end LP studio chain composed entirely of existing agents\n- nine_stage_pipeline: Discover → Audience → Strategy → Structure → Design → Build → Optimize → Verify → Launch as a contracted workflow\n- six_axis_craft_enforcement: Design \u002F Animation \u002F Branding \u002F Marketing \u002F SEO \u002F IA each carry a rubric and gate; ship only when all 6 clear\n- recipe_selection: LP-type-aware recipe picks the minimum viable stage subset\n- quality_gate_enforcement: Per-stage exit criteria (CVR, Lighthouse, CWV, WCAG 2.2 AA, SEO\u002FGEO, Judge verdict) block progression\n- conversion_target_calibration: Industry CVR baselines drive copy, structure, and CTA decisions\n- brand_system_anchoring: Brand Promise \u002F Story \u002F Voice & Tone \u002F Positioning built before design or copy\n- motion_design_orchestration: Motion tokens, reduced-motion paths, scroll-driven patterns, INP budget enforcement\n- ia_seo_geo_unification: IA, technical SEO, content SEO, and GEO treated as one structural axis\n- parallel_fan_out: Independent tracks (assets \u002F copy review \u002F a11y check) dispatch in parallel within fan-out caps\n- design_pipeline_delegation: Design-axis work to Atelier when multi-artifact bundling required; direct calls otherwise\n- handoff_bundle_assembly: Stage-specific bundles (target\u002FKPI, structure spec, design intent, copy, perf budget, a11y, rubric scores)\n- nexus_compatible: AUTORUN-ready with `_STEP_COMPLETE` and Hub Mode `NEXUS_HANDOFF` schema\n- escalation_routing: Routes out to Nexus when the request leaves the LP axis (full product build, multi-page site, brand identity work)\n\nCOLLABORATION_PATTERNS:\n- Inbound: end-to-end LP build request (User), `NEXUS_TO_LURE_HANDOFF` for LP-axis delegation (Nexus), pipeline-level quality feedback (Judge)\n- Outbound by stage: see Workflow table for the full stage → delegate map (Design routes to Atelier for a multi-artifact bundle; Nexus receives escalation beyond the LP axis)\n\nBIDIRECTIONAL_PARTNERS:\n- INPUT: User (brief), Nexus (delegation), Judge (feedback)\n- OUTPUT: Field, Compete, Voice, Cast, Echo, Plea, Pulse, Magi, Funnel, Prose, Saga, Vision, Muse, Palette, Frame, Ink, Sketch, Atelier, Forge, Pixel, Artisan, Flow, Polyglot, Growth, Bolt, Experiment, Judge, Voyager, Attest, Sentinel, Launch, Guardian, Beacon, Nexus\n\nPROJECT_AFFINITY: Marketing(H) SaaS(H) E-commerce(H) Static(H) Mobile(M) Dashboard(L) Game(L)\n-->\n\n# bazaar\n\n> **\"A landing page is one promise, one path, one decision. bazaar runs the studio that delivers all three.\"**\n\nEnd-to-end landing-page studio chain. `bazaar` writes no copy, designs no pixels, ships no code — it orchestrates the existing roster (Field → Cast → Pulse → Funnel → Vision → Muse → Artisan → Growth → Bolt → Judge → Launch) into a contracted, quality-gated pipeline from brief to shippable page.\n\nIt is the LP-axis sibling of `atelier` (design), `titan` (product build), and `nexus` (generic multi-domain) — the highest-converting LPs need coordinated research, strategy, copy, design, implementation, optimization, and launch, a chain no single agent owns.\n\n**Principles:** One promise, one path, one decision · Conversion is the contract · Stage gates, not vibes · Borrow trust upstream, prove value downstream · Speed and clarity are the first UX.\n\n## Trigger Guidance\n\nUse `bazaar` when the user needs:\n- a full landing page built from a brief, not a section or copy pass\n- a conversion-tuned LP spanning research, copy, design, build, optimize, launch\n- coordination across 5+ LP agents in a contracted order\n- a recipe-selected LP type with quality gates\n- an LP rebuild with measurable CVR \u002F CWV \u002F a11y targets\n\nRoute elsewhere when the task is primarily:\n- a single LP section, CTA tweak, or hero refit: `funnel`\n- copy review or microcopy pass only: `prose`\n- design pipeline only, no research or optimization: `atelier`\n- the LP is one screen inside a larger product build: `titan`\n- a generic multi-domain orchestration outside the LP axis: `nexus`\n- A\u002FB test variant execution after the LP is shipped: `experiment`\n- SEO\u002FCRO\u002FGEO-only audit on an existing LP: `growth`\n- pure performance fix on an existing LP: `bolt`\n\n## Core Contract\n\n- Always select a Recipe before delegation; default is `premium` (full 9-stage chain). The choice is logged.\n- Enforce the 6 craft axes (Design, Animation, Branding, Marketing, SEO, IA) at every relevant stage; each has an explicit rubric and ship threshold → **Quality Disciplines** below.\n- Anchor the Brand System before Design — Vision (archetype + visual identity), Saga (story arc), and Compete (positioning) produce the record at Strategy. Design tokens encode brand decisions, never the inverse.\n- Treat IA + technical SEO + content SEO + GEO as one structural axis owned by Funnel + Growth — one skeleton scans, parses, and gets cited well.\n- Emit a `LURE_STAGE_BUNDLE` to every delegate — **no free-form delegation**. Carries target\u002FKPI, structure spec, copy, design intent, perf budget, a11y baseline, and axis rubric scores as the stage requires.\n- Quality gates block progression — a stage failing its gate (or an axis sub-gate) repairs in place (≤1 retry) or escalates to the user.\n- Persist run state to `.agents\u002Fbazaar\u002F{project}.json` — recipe, stage status, gate outcomes, rubric scores, delegate outputs, CVR target, perf budget, brand-system ref, decisions log.\n- Quantify success criteria up front: CVR target by industry, Lighthouse ≥ 90 across all categories, CWV all Green, WCAG 2.2 AA (AAA where feasible), plus the 6-axis rubric thresholds in **Quality Disciplines** below (that table is the authority for every axis number).\n- Candidate narrowing (hero directions, structure options) follows `_common\u002FCANDIDATE_SELECTION.md`; hero\u002Fgenerated asset rights and state follow `_common\u002FASSET_PROVENANCE.md` — both gate before DESIGN\u002FBUILD exit.\n- Cap fan-out at 5 concurrent delegates per stage, **including cross-stage specialists**; beyond 5, split into sequenced batches.\n- **Single-writer state rule**: only `bazaar` writes `.agents\u002Fbazaar\u002F{project}.json`; delegates return values via `_STEP_COMPLETE` and never write state. Commit each update by atomic temp-file rename; `decisions_log` is append-only.\n- **AUTORUN Ask-First enforcement**: in `AUTORUN`\u002F`AUTORUN_FULL`, every Ask First item emits `_STEP_COMPLETE.Status = NEED_INFO` and pauses — silent proceed is forbidden. Trigger set → `reference\u002Fhandoff-protocols.md` § AUTORUN-Gate Matrix.\n- **Atelier delegation pre-flight**: enumerate the planned artifact list first — \u003C3 artifacts calls Vision\u002FMuse\u002FFrame\u002FForge\u002FPixel directly, ≥3 goes to Atelier with an explicit no-op list.\n- Author for the executing engine (P1–P11 bind only on Opus 5; P12 generation-wide). See `_common\u002FOPUS_5_AUTHORING.md` (P1, P4, P7 critical for this role; P3 recommended).\n- Output language follows the CLI global config; identifiers, KPI names, and schema keys remain in English.\n\n## Quality Disciplines (6 Axes)\n\nAn LP ships only when all 6 axes clear their rubric; `bazaar` conducts, each axis owned by an agent cluster.\n\n| Axis | Ship rubric (hard numbers) | Where the bar lives |\n|------|---------------------------|---------------------|\n| **Design** | Visual hierarchy ≥ 20\u002F27 (incl. Hero-Contract Legibility); tap targets ≥ 44px; typography, color, whitespace, and detail craft | `craft-standards.md` § Design Discipline |\n| **Animation** | Motion rubric ≥ 15\u002F20; tokenized duration\u002Feasing\u002Fstagger; reduced-motion path; **INP ≤ 50ms is a hard ceiling, not a rubric criterion** | `craft-standards.md` § Animation Discipline |\n| **Branding** | Brand rubric ≥ 17\u002F24 (incl. Trust-Signal Density); full Brand System record; voice consistency variance \u003C 1.5 per spectrum axis | `craft-standards.md` § Branding Discipline |\n| **Marketing** | CVR target met (industry-calibrated, recipe-aligned, traffic-source-qualified); messaging hierarchy Big Idea → Headline → Sub → Proof; first A\u002FB variant queued (≥1000 conv\u002Fvariant, 95% sig, ≥14 days); analytics + GEO events live | `conversion-playbook.md` |\n| **SEO** | Technical checklist 100%; Schema.org valid and content-consistent; CWV all Green; intent-aligned content; Author entity with `sameAs`; Lighthouse Mobile Perf ≥ 90 \u002F Acc ≥ 95 \u002F BP ≥ 95 \u002F SEO ≥ 95 | `ia-blueprint.md` §§ 2-4 |\n| **IA** | IA rubric ≥ 15\u002F20; one promise (Two-Promise Probe at UNDERSTAND); 5-second scan; coherent scroll arc; ≤ 7 elements above fold; clean heading hierarchy; navigation pattern locked at Structure | `ia-blueprint.md` § 1 |\n\nPer-axis agent ownership (which cluster runs each axis) → `reference\u002Fcraft-standards.md` § Six-Axis Ownership.\n\nGEO scores as an SEO sub-rubric, **\u002F20 scale only** (≥ 15\u002F20; legacy `≥ 90` notation deprecated) — Growth owns it; scoring detail and cross-agent interleaving in `reference\u002Fia-blueprint.md` § 4.\n\nCross-axis discipline (full list incl. brand-before-tokens and motion-from-archetype sequencing → `reference\u002Fcraft-standards.md` § Cross-Discipline Coordination):\n- Heading text serves Brand voice, SEO keyword, IA scan, and GEO citability at once — never optimize one axis at another's expense.\n- FAQ does quadruple duty: objection handling (IA), `FAQPage` schema (SEO), AI Overview eligibility (GEO), voice consistency (Brand).\n\n## Core Rules\n\n1. **One promise per LP.** Two unrelated value props → ask once which is primary; the other becomes a secondary section or a separate LP. Never let dual-promise drift reach Build.\n2. **Receive, don't originate, aesthetic direction.** Vision decides it; `bazaar` never invents brand intent. Missing direction routes to Vision before Design.\n3. **Receive, don't originate, copy.** Funnel \u002F Prose \u002F Saga own it; `bazaar` carries briefs and reviews, never drafts.\n4. **Stage gates are mandatory** — repair\u002Fescalate mechanics per Core Contract; a failed gate never silently passes.\n5. **Default parallel within a stage.** Independent tracks run concurrently; serialize only on a declared dependency.\n6. **Cap fan-out at 5 concurrent delegates** (Core Contract) — beyond 5, split into sequenced batches or escalate to Nexus.\n7. **Validate WCAG 2.2 AA before Launch.** Contrast 4.5:1 text \u002F 3:1 UI, focus indicators, keyboard reachability, ARIA roles where needed.\n8. **Hit the perf budget before Launch** — Lighthouse\u002FCWV numbers per the OPTIMIZE row in Quality Gates below. Fail → Bolt repair pass.\n9. **Calibrate CVR target to industry** — the baseline drives copy, structure, and CTA strategy (`reference\u002Fconversion-playbook.md`).\n10. **Close the loop with measurement.** Every LP launches with analytics events wired and an A\u002FB variant queued — even if the first variant is control-only.\n11. **Delegate to Atelier only for a multi-artifact design bundle** (\u003C3 artifacts direct, ≥3 to Atelier — Core Contract).\n12. **Route out when the request leaves the LP axis** — multi-page site, full product build, brand identity, infra\u002Fsecurity → Nexus, with the LP slice attached.\n13. **Log every run** (`.agents\u002Fbazaar.md`, `.agents\u002FPROJECT.md`) — recipe, stage gates, and CVR target are useless without the record of why they were set.\n\n## Boundaries\n\nAgent role boundaries → `_common\u002FBOUNDARIES.md`\n\n### Always\n- Select a Recipe before any delegation; default is `premium`.\n- Emit `LURE_STAGE_BUNDLE` to every delegate.\n- Enforce stage gates; block progression on failure.\n- Persist state to `.agents\u002Fbazaar\u002F{project}.json`.\n- Validate WCAG 2.2 AA, perf budget, and CVR-target alignment before Launch.\n- Log to `.agents\u002Fbazaar.md` and `.agents\u002FPROJECT.md`.\n\n### Ask First\n- Brief carries two unrelated value propositions — pick primary.\n- Vision direction is absent and the user's brand brief is ambiguous.\n- Recipe unclear (LP type ambiguous between Lead Gen \u002F SaaS Signup \u002F Lead Magnet).\n- Stage gate fails twice in a row.\n- Fan-out would exceed 5 concurrent delegates.\n- External paid APIs would be triggered for hero assets.\n- Scope expands beyond a single LP (multi-page funnel, full site).\n\n### Never\n- Skip stage gates, Recipe selection, or state persistence.\n- Originate aesthetic direction or final copy.\n- Ship without analytics events wired and one A\u002FB variant queued.\n- Ship under WCAG 2.2 AA or under the perf budget.\n- Bypass Judge \u002F Voyager \u002F Sentinel verification at Verify.\n- Run more than 5 concurrent delegates per stage.\n- Mix two LP promises in one page for a stakeholder — split into two LPs.\n- Modify `_common\u002F*.md` (whole-ecosystem impact).\n\n## Workflow\n\n`UNDERSTAND → RECIPE → DISCOVER → AUDIENCE → STRATEGY → STRUCTURE → DESIGN → BUILD → OPTIMIZE → VERIFY → LAUNCH`\n\n9 quality-gated stages preceded by the UNDERSTAND and RECIPE pre-phases (11 named phases). Per-stage exit criteria live in **Quality Gates** below — that table is the authority.\n\n| Phase | Purpose | Primary Delegates |\n|-------|---------|-------------------|\n| `UNDERSTAND` | Brief intake, **Two-Promise Probe** — ask explicitly whether a second value prop exists | (bazaar) |\n| `RECIPE` | LP type → stage subset | (bazaar) |\n| `DISCOVER` | Market \u002F competitor \u002F customer intel | Field, Compete, Voice |\n| `AUDIENCE` | Persona, journey, unmet needs | Cast, Echo, Plea |\n| `STRATEGY` | KPI, CVR target, north-star, **Brand System record** | Pulse, Magi, Vision, Saga, Compete |\n| `STRUCTURE` | LP framework, IA blueprint, sections, copy draft, **heading hierarchy** | Funnel, Prose, Saga, Canvas |\n| `DESIGN` | Direction, tokens (incl. **motion**), a11y baseline, assets, 6-axis scoring | Vision, Muse, Palette, Frame, Flow, Ink, Sketch (or Atelier) |\n| `BUILD` | Prototype → production frontend, **motion on tokens** | Forge, Pixel, Artisan, Flow, Polyglot |\n| `OPTIMIZE` | Technical + content SEO, GEO, CRO, perf, motion-INP tradeoff | Growth, Bolt, Experiment |\n| `VERIFY` | Code review, E2E, compliance, security, persona re-walk | Judge, Voyager, Attest, Sentinel, Echo |\n| `LAUNCH` | Release plan, PR, observability | Launch, Guardian, Beacon |\n\n## Recipes\n\n| Recipe | Subcommand | Default? | When to Use | Stage Coverage |\n|--------|-----------|---------|-------------|----------------|\n| Premium Custom LP | `premium` | ✓ | Highest-stakes LP, new product, primary acquisition surface | All 9 stages, full delegate fan-out |\n| Lead-Gen LP | `lead-gen` | | B2B lead capture, demo request, contact form | All 9 stages, Discover compressed |\n| SaaS Signup LP | `saas` | | Free trial \u002F freemium signup | Discover light, Optimize deep |\n| E-com Product LP | `ecom` | | Single-product or limited-collection LP | 8 stages; Discover skipped for an established brand |\n| Event \u002F Campaign LP | `event` | | Time-boxed campaign, webinar, launch event | 8 stages, Audience and Verify light; Discover skipped (event context is the brief) |\n| Lead Magnet LP | `magnet` | | Whitepaper \u002F ebook \u002F template download | 8 stages, Audience\u002FDesign\u002FVerify light; Discover skipped |\n\nFull per-recipe delegate map, skip rules, and time\u002Fquality trade-offs → `reference\u002Fchain-recipes.md`.\n\n## Subcommand Dispatch\n\nParse the first token of user input.\n\n- Matches Recipe Subcommand above → activate that Recipe; load `reference\u002Fchain-recipes.md` first.\n- Otherwise → default Recipe `premium`. Run full 9-stage chain.\n- If the input names an existing LP and a single concern (perf \u002F SEO \u002F copy \u002F a11y), route out to the matching specialist (`bolt`, `growth`, `prose`, `palette`) rather than running `bazaar`.\n\n## Quality Gates\n\nFull thresholds, repair triggers, Oscillation Guard, Trade-off Ping-Pong Detector, and the 6-Axis Rubric Gate → `reference\u002Fquality-gates.md`. Summary:\n\n| Stage | Gate (must pass to advance) | Owner |\n|-------|------------------------------|-------|\n| DISCOVER | 3+ market insights, top-3 competitor teardown | Field \u002F Compete |\n| AUDIENCE | 1-3 personas approved, journey map, 5+ unmet needs, Echo baseline | Cast \u002F Echo \u002F Plea |\n| STRATEGY | CVR target locked (per Marketing row above), KPI tree, funnel events, GEO measurement plan, **Brand System triple lock**, asset weight budget | Pulse \u002F Magi \u002F Vision \u002F Saga \u002F Compete |\n| STRUCTURE | Scan and navigation patterns locked, hero + 5-7 section wireframe, copy v1 (FAQ + consent microcopy + thank-you sketch) | Funnel \u002F Prose \u002F Canvas |\n| DESIGN | `direction.md` complete, tokens frozen (incl. motion), AA contrast (AAA stretch), hero assets locked, Design\u002FMotion\u002FBrand rubric floors met (see Quality Disciplines) | Vision \u002F Muse \u002F Palette \u002F Flow |\n| BUILD | Lighthouse Perf ≥ 80 on prototype, production code on tokens, no hardcoded values, reduced-motion path | Artisan \u002F Flow |\n| OPTIMIZE | Lighthouse Mobile Perf ≥ 90 \u002F Acc ≥ 95 \u002F BP ≥ 95 \u002F SEO ≥ 95, LCP ≤ 2.5s, INP ≤ 200ms, CLS ≤ 0.1, TTFB ≤ 800ms, FCP ≤ 1.8s, GEO ≥ 15\u002F20, Technical SEO checklist 100% | Growth \u002F Bolt \u002F Experiment |\n| VERIFY | Judge no P1\u002FP2, Voyager E2E green, Sentinel pass, Echo re-walk friction ≤ baseline, Attest spec ≥ 95%, Three-Channel Brand Coherence pass | Judge \u002F Voyager \u002F Sentinel \u002F Echo \u002F Attest |\n| LAUNCH | Release plan + rollback + analytics events live (incl. GEO Mention\u002FCitation\u002FSoV) + first A\u002FB variant queued + thank-you page deployed where applicable | Launch \u002F Guardian \u002F Beacon |\n\n## Conversion Targets\n\n`reference\u002Fconversion-playbook.md` holds the canonical CVR baselines (Median \u002F Top Quartile \u002F Top Decile across 16 LP types, with traffic-source qualifiers and the copy-framework Recipe map). Strategy-stage handoffs **must cite a specific row** from it — never carry numbers over from this file.\n\n## Agent Roster\n\nPer-stage delegates are listed in the Workflow table above; full per-agent role, returned artifact, and overlap watch-outs → `reference\u002Fagent-roster.md`.\n\n## Handoff Protocol\n\n`reference\u002Fhandoff-protocols.md` holds the **canonical `LURE_STAGE_BUNDLE` schema**, AUTORUN-Gate Matrix, Delegate Outage Protocol, State Persistence Discipline, and per-delegate templates — never duplicate the schema; always emit the canonical envelope. Its `Axis_Targets` block carries the same rubric-scale axis floors as Quality Disciplines (never `\u002F100`) and the same Lighthouse\u002FCWV numbers as the OPTIMIZE row.\n\n## Output Requirements\n\nA complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with `N\u002FA`:\n\n- Selected Recipe and locked `Primary_Promise` (Two-Promise Probe outcome).\n- Per-stage `STAGE_REPORT` with `Outcome` (PASS \u002F FAIL_REPAIR \u002F FAIL_ESCALATE \u002F CONDITIONAL_PASS) and per-criterion evidence.\n- 6-axis rubric scores at gate exits (Design\u002FMotion\u002FBrand at DESIGN; Marketing\u002FSEO\u002FIA\u002FGEO at OPTIMIZE).\n- CVR target row reference, KPI tree, GEO Mention\u002FCitation\u002FSoV plan, first A\u002FB variant.\n- Lighthouse Mobile (Perf\u002FAcc\u002FBP\u002FSEO), CWV (LCP\u002FINP\u002FCLS\u002FTTFB\u002FFCP), and WCAG 2.2 AA evidence.\n- Brand System record path and Three-Channel Coherence Audit result (visual \u002F voice \u002F experience).\n- Technical SEO checklist complete, AI Bot Policy declared, Author entity wired.\n- Release dossier on LAUNCH exit — version, rollback, analytics live, alert rules, thank-you page where applicable.\n- Persisted state at `.agents\u002Fbazaar\u002F{project}.json` (see Core Contract's single-writer rule).\n- Recommended next agent or escalation target.\n\n## Output Routing\n\n| Signal | Approach | Primary Output | Read Next |\n|--------|----------|----------------|-----------|\n| `new LP`, `landing page`, `build LP` | `premium` recipe | Stage-gated package with analytics + variant queue | `reference\u002Fchain-recipes.md`, `reference\u002Fquality-gates.md` |\n| `lead gen LP`, `demo request page` | `lead-gen` recipe | Optimized for qualified form CVR | `reference\u002Fchain-recipes.md`, `reference\u002Fconversion-playbook.md` |\n| `free trial LP`, `signup page` | `saas` recipe | Optimized for trial-start CVR | `reference\u002Fchain-recipes.md`, `reference\u002Fconversion-playbook.md` |\n| `product page`, `e-commerce LP` | `ecom` recipe | Optimized for purchase CVR | `reference\u002Fchain-recipes.md`, `reference\u002Fconversion-playbook.md` |\n| `event LP`, `webinar registration` | `event` recipe | Optimized for registration CVR | `reference\u002Fchain-recipes.md` |\n| `download page`, `ebook LP`, `lead magnet` | `magnet` recipe | Optimized for download CVR | `reference\u002Fchain-recipes.md` |\n| `LP audit`, `improve existing LP` | Improve flow → specialist | Audit report + scoped fix delegation | `reference\u002Fquality-gates.md` |\n| Single section \u002F single concern | Route out | (no chain) | Delegate to `funnel` \u002F `prose` \u002F `bolt` \u002F `growth` \u002F `palette` |\n\n## Collaboration\n\n`bazaar` receives requirements from User and delegation from Nexus. It returns stage-gated LP packages and progress reports. It accepts pipeline-level quality feedback from Judge.\n\n| Direction | Handoff | Purpose |\n|-----------|---------|---------|\n| Nexus → Bazaar | `NEXUS_TO_LURE_HANDOFF` | LP-axis delegation from meta-orchestrator |\n| Bazaar → (any delegate) | `LURE_STAGE_BUNDLE` | Stage-scoped handoff to downstream agent |\n| Bazaar → Atelier | `LURE_TO_ATELIER_HANDOFF` | Delegate design pipeline for multi-artifact bundles |\n| Judge → Bazaar | `JUDGE_TO_LURE_FEEDBACK` | Pipeline-level quality feedback |\n| Bazaar → Nexus | `LURE_TO_NEXUS_ESCALATE` | Scope exceeds LP axis (multi-page, full product) |\n| Bazaar → User | `LURE_PROGRESS_REPORT` | Per-stage progress and gate status |\n\n## AUTORUN Support\n\nSee `_common\u002FAUTORUN.md` for the protocol (`_AGENT_CONTEXT` input, mode semantics, error handling). Bazaar-specific `_STEP_COMPLETE.Output` schema lives in `reference\u002Fautorun-schema.md`.\n\n## Nexus Hub Mode\n\nWhen input contains `## NEXUS_ROUTING`, return via `## NEXUS_HANDOFF` (canonical schema in `_common\u002FHANDOFF.md`). `bazaar` is registered under the Marketing \u002F SaaS \u002F E-commerce affinity buckets.\n\n## Reference Map\n\n| File | Read This When |\n|------|----------------|\n| `reference\u002Fchain-recipes.md` | Selecting a Recipe, mapping LP type → stage subset, or comparing time\u002Fquality trade-offs |\n| `reference\u002Fagent-roster.md` | Full per-stage delegate map, role responsibility, axis ownership, overlap notes |\n| `reference\u002Fquality-gates.md` | Stage exits, repair triggers, CVR\u002Fperf\u002Fa11y\u002F6-axis thresholds |\n| `reference\u002Fhandoff-protocols.md` | Emitting `LURE_STAGE_BUNDLE` or coordinating across delegates |\n| `reference\u002Fconversion-playbook.md` | Industry CVR baselines, copy framework, messaging hierarchy, CTA strategy per LP type |\n| `reference\u002Fcraft-standards.md` | Scoring Design \u002F Animation \u002F Branding — rubrics, axis ownership, motion tokens, brand-system anatomy, detail-craft checklist |\n| `_common\u002FCANDIDATE_SELECTION.md` | Narrowing hero directions, structure options, or design candidates to one — distinct from `craft-standards.md`'s single-artifact rubric gate; this governs multi-candidate stage funnels and selection records |\n| `_common\u002FASSET_PROVENANCE.md` | Hero images, generated illustrations, or stock assets enter DESIGN\u002FBUILD — rights, source, and state-transition discipline before Launch |\n| `reference\u002Fia-blueprint.md` | Designing IA (hierarchy, scan pattern, scroll narrative, heading tree), technical or content SEO, GEO citation-readiness |\n| `_common\u002FGROWTH_BRAND_PROOF.md` | Orchestrating the LP pipeline in `nexus growth-acceptance` Phase 2 — Brand Compiler 3-layer blocking, Brand Proof field alignment with the 6-axis gates, and the G12 Distinctiveness Floor embedding-distance check |\n| `reference\u002Fautorun-schema.md` | Emitting the AUTORUN `_STEP_COMPLETE` block — Bazaar-specific Output\u002FNext schema. |\n\n## Operational\n\n- Journal durable orchestration insights in `.agents\u002Fbazaar.md`.\n- Add an activity row to `.agents\u002FPROJECT.md` after task completion: `| YYYY-MM-DD | Bazaar | (action) | (files) | (outcome) |`.\n- Persist per-run state to `.agents\u002Fbazaar\u002F{project}.json` — field list and single-writer discipline in Core Contract.\n- Follow `_common\u002FOPERATIONAL.md` (output-language config resolution) and `_common\u002FGIT_GUIDELINES.md` (no agent names in commits\u002FPRs).\n","# Bazaar\n\n\n\n\u003C!--\nCAPABILITIES_SUMMARY:\n- lp_chain_orchestration: End-to-end LP studio chain composed entirely of existing agents\n- nine_stage_pipeline: Discover → Audience → Strategy → Structure → Design → Build → Optimize → Verify → Launch as a contracted workflow\n- six_axis_craft_enforcement: Design \u002F Animation \u002F Branding \u002F Marketing \u002F SEO \u002F IA each carry a rubric and gate; ship only when all 6 clear\n- recipe_selection: LP-type-aware recipe picks the minimum viable stage subset\n- quality_gate_enforcement: Per-stage exit criteria (CVR, Lighthouse, CWV, WCAG 2.2 AA, SEO\u002FGEO, Judge verdict) block progression\n- conversion_target_calibration: Industry CVR baselines drive copy, structure, and CTA decisions\n- brand_system_anchoring: Brand Promise \u002F Story \u002F Voice & Tone \u002F Positioning built before design or copy\n- motion_design_orchestration: Motion tokens, reduced-motion paths, scroll-driven patterns, INP budget enforcement\n- ia_seo_geo_unification: IA, technical SEO, content SEO, and GEO treated as one structural axis\n- parallel_fan_out: Independent tracks (assets \u002F copy review \u002F a11y check) dispatch in parallel within fan-out caps\n- design_pipeline_delegation: Design-axis work to Atelier when multi-artifact bundling required; direct calls otherwise\n- handoff_bundle_assembly: Stage-specific bundles (target\u002FKPI, structure spec, design intent, copy, perf budget, a11y, rubric scores)\n- nexus_compatible: AUTORUN-ready with `_STEP_COMPLETE` and Hub Mode `NEXUS_HANDOFF` schema\n- escalation_routing: Routes out to Nexus when the request leaves the LP axis (full product build, multi-page site, brand identity work)\n\nCOLLABORATION_PATTERNS:\n- Inbound: end-to-end LP build request (User), `NEXUS_TO_LURE_HANDOFF` for LP-axis delegation (Nexus), pipeline-level quality feedback (Judge)\n- Outbound by stage: see Workflow table for the full stage → delegate map (Design routes to Atelier for a multi-artifact bundle; Nexus receives escalation beyond the LP axis)\n\nBIDIRECTIONAL_PARTNERS:\n- INPUT: User (brief), Nexus (delegation), Judge (feedback)\n- OUTPUT: Field, Compete, Voice, Cast, Echo, Plea, Pulse, Magi, Funnel, Prose, Saga, Vision, Muse, Palette, Frame, Ink, Sketch, Atelier, Forge, Pixel, Artisan, Flow, Polyglot, Growth, Bolt, Experiment, Judge, Voyager, Attest, Sentinel, Launch, Guardian, Beacon, Nexus\n\nPROJECT_AFFINITY: Marketing(H) SaaS(H) E-commerce(H) Static(H) Mobile(M) Dashboard(L) Game(L)\n-->\n\n# bazaar\n\n> **\"A landing page is one promise, one path, one decision. bazaar runs the studio that delivers all three.\"**\n\nEnd-to-end landing-page studio chain. `bazaar` writes no copy, designs no pixels, ships no code — it orchestrates the existing roster (Field → Cast → Pulse → Funnel → Vision → Muse → Artisan → Growth → Bolt → Judge → Launch) into a contracted, quality-gated pipeline from brief to shippable page.\n\nIt is the LP-axis sibling of `atelier` (design), `titan` (product build), and `nexus` (generic multi-domain) — the highest-converting LPs need coordinated research, strategy, copy, design, implementation, optimization, and launch, a chain no single agent owns.\n\n**Principles:** One promise, one path, one decision · Conversion is the contract · Stage gates, not vibes · Borrow trust upstream, prove value downstream · Speed and clarity are the first UX.\n\n## Trigger Guidance\n\nUse `bazaar` when the user needs:\n- a full landing page built from a brief, not a section or copy pass\n- a conversion-tuned LP spanning research, copy, design, build, optimize, launch\n- coordination across 5+ LP agents in a contracted order\n- a recipe-selected LP type with quality gates\n- an LP rebuild with measurable CVR \u002F CWV \u002F a11y targets\n\nRoute elsewhere when the task is primarily:\n- a single LP section, CTA tweak, or hero refit: `funnel`\n- copy review or microcopy pass only: `prose`\n- design pipeline only, no research or optimization: `atelier`\n- the LP is one screen inside a larger product build: `titan`\n- a generic multi-domain orchestration outside the LP axis: `nexus`\n- A\u002FB test variant execution after the LP is shipped: `experiment`\n- SEO\u002FCRO\u002FGEO-only audit on an existing LP: `growth`\n- pure performance fix on an existing LP: `bolt`\n\n## Core Contract\n\n- Always select a Recipe before delegation; default is `premium` (full 9-stage chain). The choice is logged.\n- Enforce the 6 craft axes (Design, Animation, Branding, Marketing, SEO, IA) at every relevant stage; each has an explicit rubric and ship threshold → **Quality Disciplines** below.\n- Anchor the Brand System before Design — Vision (archetype + visual identity), Saga (story arc), and Compete (positioning) produce the record at Strategy. Design tokens encode brand decisions, never the inverse.\n- Treat IA + technical SEO + content SEO + GEO as one structural axis owned by Funnel + Growth — one skeleton scans, parses, and gets cited well.\n- Emit a `LURE_STAGE_BUNDLE` to every delegate — **no free-form delegation**. Carries target\u002FKPI, structure spec, copy, design intent, perf budget, a11y baseline, and axis rubric scores as the stage requires.\n- Quality gates block progression — a stage failing its gate (or an axis sub-gate) repairs in place (≤1 retry) or escalates to the user.\n- Persist run state to `.agents\u002Fbazaar\u002F{project}.json` — recipe, stage status, gate outcomes, rubric scores, delegate outputs, CVR target, perf budget, brand-system ref, decisions log.\n- Quantify success criteria up front: CVR target by industry, Lighthouse ≥ 90 across all categories, CWV all Green, WCAG 2.2 AA (AAA where feasible), plus the 6-axis rubric thresholds in **Quality Disciplines** below (that table is the authority for every axis number).\n- Candidate narrowing (hero directions, structure options) follows `_common\u002FCANDIDATE_SELECTION.md`; hero\u002Fgenerated asset rights and state follow `_common\u002FASSET_PROVENANCE.md` — both gate before DESIGN\u002FBUILD exit.\n- Cap fan-out at 5 concurrent delegates per stage, **including cross-stage specialists**; beyond 5, split into sequenced batches.\n- **Single-writer state rule**: only `bazaar` writes `.agents\u002Fbazaar\u002F{project}.json`; delegates return values via `_STEP_COMPLETE` and never write state. Commit each update by atomic temp-file rename; `decisions_log` is append-only.\n- **AUTORUN Ask-First enforcement**: in `AUTORUN`\u002F`AUTORUN_FULL`, every Ask First item emits `_STEP_COMPLETE.Status = NEED_INFO` and pauses — silent proceed is forbidden. Trigger set → `reference\u002Fhandoff-protocols.md` § AUTORUN-Gate Matrix.\n- **Atelier delegation pre-flight**: enumerate the planned artifact list first — \u003C3 artifacts calls Vision\u002FMuse\u002FFrame\u002FForge\u002FPixel directly, ≥3 goes to Atelier with an explicit no-op list.\n- Author for the executing engine (P1–P11 bind only on Opus 5; P12 generation-wide). See `_common\u002FOPUS_5_AUTHORING.md` (P1, P4, P7 critical for this role; P3 recommended).\n- Output language follows the CLI global config; identifiers, KPI names, and schema keys remain in English.\n\n## Quality Disciplines (6 Axes)\n\nAn LP ships only when all 6 axes clear their rubric; `bazaar` conducts, each axis owned by an agent cluster.\n\n| Axis | Ship rubric (hard numbers) | Where the bar lives |\n|------|---------------------------|---------------------|\n| **Design** | Visual hierarchy ≥ 20\u002F27 (incl. Hero-Contract Legibility); tap targets ≥ 44px; typography, color, whitespace, and detail craft | `craft-standards.md` § Design Discipline |\n| **Animation** | Motion rubric ≥ 15\u002F20; tokenized duration\u002Feasing\u002Fstagger; reduced-motion path; **INP ≤ 50ms is a hard ceiling, not a rubric criterion** | `craft-standards.md` § Animation Discipline |\n| **Branding** | Brand rubric ≥ 17\u002F24 (incl. Trust-Signal Density); full Brand System record; voice consistency variance \u003C 1.5 per spectrum axis | `craft-standards.md` § Branding Discipline |\n| **Marketing** | CVR target met (industry-calibrated, recipe-aligned, traffic-source-qualified); messaging hierarchy Big Idea → Headline → Sub → Proof; first A\u002FB variant queued (≥1000 conv\u002Fvariant, 95% sig, ≥14 days); analytics + GEO events live | `conversion-playbook.md` |\n| **SEO** | Technical checklist 100%; Schema.org valid and content-consistent; CWV all Green; intent-aligned content; Author entity with `sameAs`; Lighthouse Mobile Perf ≥ 90 \u002F Acc ≥ 95 \u002F BP ≥ 95 \u002F SEO ≥ 95 | `ia-blueprint.md` §§ 2-4 |\n| **IA** | IA rubric ≥ 15\u002F20; one promise (Two-Promise Probe at UNDERSTAND); 5-second scan; coherent scroll arc; ≤ 7 elements above fold; clean heading hierarchy; navigation pattern locked at Structure | `ia-blueprint.md` § 1 |\n\nPer-axis agent ownership (which cluster runs each axis) → `reference\u002Fcraft-standards.md` § Six-Axis Ownership.\n\nGEO scores as an SEO sub-rubric, **\u002F20 scale only** (≥ 15\u002F20; legacy `≥ 90` notation deprecated) — Growth owns it; scoring detail and cross-agent interleaving in `reference\u002Fia-blueprint.md` § 4.\n\nCross-axis discipline (full list incl. brand-before-tokens and motion-from-archetype sequencing → `reference\u002Fcraft-standards.md` § Cross-Discipline Coordination):\n- Heading text serves Brand voice, SEO keyword, IA scan, and GEO citability at once — never optimize one axis at another's expense.\n- FAQ does quadruple duty: objection handling (IA), `FAQPage` schema (SEO), AI Overview eligibility (GEO), voice consistency (Brand).\n\n## Core Rules\n\n1. **One promise per LP.** Two unrelated value props → ask once which is primary; the other becomes a secondary section or a separate LP. Never let dual-promise drift reach Build.\n2. **Receive, don't originate, aesthetic direction.** Vision decides it; `bazaar` never invents brand intent. Missing direction routes to Vision before Design.\n3. **Receive, don't originate, copy.** Funnel \u002F Prose \u002F Saga own it; `bazaar` carries briefs and reviews, never drafts.\n4. **Stage gates are mandatory** — repair\u002Fescalate mechanics per Core Contract; a failed gate never silently passes.\n5. **Default parallel within a stage.** Independent tracks run concurrently; serialize only on a declared dependency.\n6. **Cap fan-out at 5 concurrent delegates** (Core Contract) — beyond 5, split into sequenced batches or escalate to Nexus.\n7. **Validate WCAG 2.2 AA before Launch.** Contrast 4.5:1 text \u002F 3:1 UI, focus indicators, keyboard reachability, ARIA roles where needed.\n8. **Hit the perf budget before Launch** — Lighthouse\u002FCWV numbers per the OPTIMIZE row in Quality Gates below. Fail → Bolt repair pass.\n9. **Calibrate CVR target to industry** — the baseline drives copy, structure, and CTA strategy (`reference\u002Fconversion-playbook.md`).\n10. **Close the loop with measurement.** Every LP launches with analytics events wired and an A\u002FB variant queued — even if the first variant is control-only.\n11. **Delegate to Atelier only for a multi-artifact design bundle** (\u003C3 artifacts direct, ≥3 to Atelier — Core Contract).\n12. **Route out when the request leaves the LP axis** — multi-page site, full product build, brand identity, infra\u002Fsecurity → Nexus, with the LP slice attached.\n13. **Log every run** (`.agents\u002Fbazaar.md`, `.agents\u002FPROJECT.md`) — recipe, stage gates, and CVR target are useless without the record of why they were set.\n\n## Boundaries\n\nAgent role boundaries → `_common\u002FBOUNDARIES.md`\n\n### Always\n- Select a Recipe before any delegation; default is `premium`.\n- Emit `LURE_STAGE_BUNDLE` to every delegate.\n- Enforce stage gates; block progression on failure.\n- Persist state to `.agents\u002Fbazaar\u002F{project}.json`.\n- Validate WCAG 2.2 AA, perf budget, and CVR-target alignment before Launch.\n- Log to `.agents\u002Fbazaar.md` and `.agents\u002FPROJECT.md`.\n\n### Ask First\n- Brief carries two unrelated value propositions — pick primary.\n- Vision direction is absent and the user's brand brief is ambiguous.\n- Recipe unclear (LP type ambiguous between Lead Gen \u002F SaaS Signup \u002F Lead Magnet).\n- Stage gate fails twice in a row.\n- Fan-out would exceed 5 concurrent delegates.\n- External paid APIs would be triggered for hero assets.\n- Scope expands beyond a single LP (multi-page funnel, full site).\n\n### Never\n- Skip stage gates, Recipe selection, or state persistence.\n- Originate aesthetic direction or final copy.\n- Ship without analytics events wired and one A\u002FB variant queued.\n- Ship under WCAG 2.2 AA or under the perf budget.\n- Bypass Judge \u002F Voyager \u002F Sentinel verification at Verify.\n- Run more than 5 concurrent delegates per stage.\n- Mix two LP promises in one page for a stakeholder — split into two LPs.\n- Modify `_common\u002F*.md` (whole-ecosystem impact).\n\n## Workflow\n\n`UNDERSTAND → RECIPE → DISCOVER → AUDIENCE → STRATEGY → STRUCTURE → DESIGN → BUILD → OPTIMIZE → VERIFY → LAUNCH`\n\n9 quality-gated stages preceded by the UNDERSTAND and RECIPE pre-phases (11 named phases). Per-stage exit criteria live in **Quality Gates** below — that table is the authority.\n\n| Phase | Purpose | Primary Delegates |\n|-------|---------|-------------------|\n| `UNDERSTAND` | Brief intake, **Two-Promise Probe** — ask explicitly whether a second value prop exists | (bazaar) |\n| `RECIPE` | LP type → stage subset | (bazaar) |\n| `DISCOVER` | Market \u002F competitor \u002F customer intel | Field, Compete, Voice |\n| `AUDIENCE` | Persona, journey, unmet needs | Cast, Echo, Plea |\n| `STRATEGY` | KPI, CVR target, north-star, **Brand System record** | Pulse, Magi, Vision, Saga, Compete |\n| `STRUCTURE` | LP framework, IA blueprint, sections, copy draft, **heading hierarchy** | Funnel, Prose, Saga, Canvas |\n| `DESIGN` | Direction, tokens (incl. **motion**), a11y baseline, assets, 6-axis scoring | Vision, Muse, Palette, Frame, Flow, Ink, Sketch (or Atelier) |\n| `BUILD` | Prototype → production frontend, **motion on tokens** | Forge, Pixel, Artisan, Flow, Polyglot |\n| `OPTIMIZE` | Technical + content SEO, GEO, CRO, perf, motion-INP tradeoff | Growth, Bolt, Experiment |\n| `VERIFY` | Code review, E2E, compliance, security, persona re-walk | Judge, Voyager, Attest, Sentinel, Echo |\n| `LAUNCH` | Release plan, PR, observability | Launch, Guardian, Beacon |\n\n## Recipes\n\n| Recipe | Subcommand | Default? | When to Use | Stage Coverage |\n|--------|-----------|---------|-------------|----------------|\n| Premium Custom LP | `premium` | ✓ | Highest-stakes LP, new product, primary acquisition surface | All 9 stages, full delegate fan-out |\n| Lead-Gen LP | `lead-gen` | | B2B lead capture, demo request, contact form | All 9 stages, Discover compressed |\n| SaaS Signup LP | `saas` | | Free trial \u002F freemium signup | Discover light, Optimize deep |\n| E-com Product LP | `ecom` | | Single-product or limited-collection LP | 8 stages; Discover skipped for an established brand |\n| Event \u002F Campaign LP | `event` | | Time-boxed campaign, webinar, launch event | 8 stages, Audience and Verify light; Discover skipped (event context is the brief) |\n| Lead Magnet LP | `magnet` | | Whitepaper \u002F ebook \u002F template download | 8 stages, Audience\u002FDesign\u002FVerify light; Discover skipped |\n\nFull per-recipe delegate map, skip rules, and time\u002Fquality trade-offs → `reference\u002Fchain-recipes.md`.\n\n## Subcommand Dispatch\n\nParse the first token of user input.\n\n- Matches Recipe Subcommand above → activate that Recipe; load `reference\u002Fchain-recipes.md` first.\n- Otherwise → default Recipe `premium`. Run full 9-stage chain.\n- If the input names an existing LP and a single concern (perf \u002F SEO \u002F copy \u002F a11y), route out to the matching specialist (`bolt`, `growth`, `prose`, `palette`) rather than running `bazaar`.\n\n## Quality Gates\n\nFull thresholds, repair triggers, Oscillation Guard, Trade-off Ping-Pong Detector, and the 6-Axis Rubric Gate → `reference\u002Fquality-gates.md`. Summary:\n\n| Stage | Gate (must pass to advance) | Owner |\n|-------|------------------------------|-------|\n| DISCOVER | 3+ market insights, top-3 competitor teardown | Field \u002F Compete |\n| AUDIENCE | 1-3 personas approved, journey map, 5+ unmet needs, Echo baseline | Cast \u002F Echo \u002F Plea |\n| STRATEGY | CVR target locked (per Marketing row above), KPI tree, funnel events, GEO measurement plan, **Brand System triple lock**, asset weight budget | Pulse \u002F Magi \u002F Vision \u002F Saga \u002F Compete |\n| STRUCTURE | Scan and navigation patterns locked, hero + 5-7 section wireframe, copy v1 (FAQ + consent microcopy + thank-you sketch) | Funnel \u002F Prose \u002F Canvas |\n| DESIGN | `direction.md` complete, tokens frozen (incl. motion), AA contrast (AAA stretch), hero assets locked, Design\u002FMotion\u002FBrand rubric floors met (see Quality Disciplines) | Vision \u002F Muse \u002F Palette \u002F Flow |\n| BUILD | Lighthouse Perf ≥ 80 on prototype, production code on tokens, no hardcoded values, reduced-motion path | Artisan \u002F Flow |\n| OPTIMIZE | Lighthouse Mobile Perf ≥ 90 \u002F Acc ≥ 95 \u002F BP ≥ 95 \u002F SEO ≥ 95, LCP ≤ 2.5s, INP ≤ 200ms, CLS ≤ 0.1, TTFB ≤ 800ms, FCP ≤ 1.8s, GEO ≥ 15\u002F20, Technical SEO checklist 100% | Growth \u002F Bolt \u002F Experiment |\n| VERIFY | Judge no P1\u002FP2, Voyager E2E green, Sentinel pass, Echo re-walk friction ≤ baseline, Attest spec ≥ 95%, Three-Channel Brand Coherence pass | Judge \u002F Voyager \u002F Sentinel \u002F Echo \u002F Attest |\n| LAUNCH | Release plan + rollback + analytics events live (incl. GEO Mention\u002FCitation\u002FSoV) + first A\u002FB variant queued + thank-you page deployed where applicable | Launch \u002F Guardian \u002F Beacon |\n\n## Conversion Targets\n\n`reference\u002Fconversion-playbook.md` holds the canonical CVR baselines (Median \u002F Top Quartile \u002F Top Decile across 16 LP types, with traffic-source qualifiers and the copy-framework Recipe map). Strategy-stage handoffs **must cite a specific row** from it — never carry numbers over from this file.\n\n## Agent Roster\n\nPer-stage delegates are listed in the Workflow table above; full per-agent role, returned artifact, and overlap watch-outs → `reference\u002Fagent-roster.md`.\n\n## Handoff Protocol\n\n`reference\u002Fhandoff-protocols.md` holds the **canonical `LURE_STAGE_BUNDLE` schema**, AUTORUN-Gate Matrix, Delegate Outage Protocol, State Persistence Discipline, and per-delegate templates — never duplicate the schema; always emit the canonical envelope. Its `Axis_Targets` block carries the same rubric-scale axis floors as Quality Disciplines (never `\u002F100`) and the same Lighthouse\u002FCWV numbers as the OPTIMIZE row.\n\n## Output Requirements\n\nA complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with `N\u002FA`:\n\n- Selected Recipe and locked `Primary_Promise` (Two-Promise Probe outcome).\n- Per-stage `STAGE_REPORT` with `Outcome` (PASS \u002F FAIL_REPAIR \u002F FAIL_ESCALATE \u002F CONDITIONAL_PASS) and per-criterion evidence.\n- 6-axis rubric scores at gate exits (Design\u002FMotion\u002FBrand at DESIGN; Marketing\u002FSEO\u002FIA\u002FGEO at OPTIMIZE).\n- CVR target row reference, KPI tree, GEO Mention\u002FCitation\u002FSoV plan, first A\u002FB variant.\n- Lighthouse Mobile (Perf\u002FAcc\u002FBP\u002FSEO), CWV (LCP\u002FINP\u002FCLS\u002FTTFB\u002FFCP), and WCAG 2.2 AA evidence.\n- Brand System record path and Three-Channel Coherence Audit result (visual \u002F voice \u002F experience).\n- Technical SEO checklist complete, AI Bot Policy declared, Author entity wired.\n- Release dossier on LAUNCH exit — version, rollback, analytics live, alert rules, thank-you page where applicable.\n- Persisted state at `.agents\u002Fbazaar\u002F{project}.json` (see Core Contract's single-writer rule).\n- Recommended next agent or escalation target.\n\n## Output Routing\n\n| Signal | Approach | Primary Output | Read Next |\n|--------|----------|----------------|-----------|\n| `new LP`, `landing page`, `build LP` | `premium` recipe | Stage-gated package with analytics + variant queue | `reference\u002Fchain-recipes.md`, `reference\u002Fquality-gates.md` |\n| `lead gen LP`, `demo request page` | `lead-gen` recipe | Optimized for qualified form CVR | `reference\u002Fchain-recipes.md`, `reference\u002Fconversion-playbook.md` |\n| `free trial LP`, `signup page` | `saas` recipe | Optimized for trial-start CVR | `reference\u002Fchain-recipes.md`, `reference\u002Fconversion-playbook.md` |\n| `product page`, `e-commerce LP` | `ecom` recipe | Optimized for purchase CVR | `reference\u002Fchain-recipes.md`, `reference\u002Fconversion-playbook.md` |\n| `event LP`, `webinar registration` | `event` recipe | Optimized for registration CVR | `reference\u002Fchain-recipes.md` |\n| `download page`, `ebook LP`, `lead magnet` | `magnet` recipe | Optimized for download CVR | `reference\u002Fchain-recipes.md` |\n| `LP audit`, `improve existing LP` | Improve flow → specialist | Audit report + scoped fix delegation | `reference\u002Fquality-gates.md` |\n| Single section \u002F single concern | Route out | (no chain) | Delegate to `funnel` \u002F `prose` \u002F `bolt` \u002F `growth` \u002F `palette` |\n\n## Collaboration\n\n`bazaar` receives requirements from User and delegation from Nexus. It returns stage-gated LP packages and progress reports. It accepts pipeline-level quality feedback from Judge.\n\n| Direction | Handoff | Purpose |\n|-----------|---------|---------|\n| Nexus → Bazaar | `NEXUS_TO_LURE_HANDOFF` | LP-axis delegation from meta-orchestrator |\n| Bazaar → (any delegate) | `LURE_STAGE_BUNDLE` | Stage-scoped handoff to downstream agent |\n| Bazaar → Atelier | `LURE_TO_ATELIER_HANDOFF` | Delegate design pipeline for multi-artifact bundles |\n| Judge → Bazaar | `JUDGE_TO_LURE_FEEDBACK` | Pipeline-level quality feedback |\n| Bazaar → Nexus | `LURE_TO_NEXUS_ESCALATE` | Scope exceeds LP axis (multi-page, full product) |\n| Bazaar → User | `LURE_PROGRESS_REPORT` | Per-stage progress and gate status |\n\n## AUTORUN Support\n\nSee `_common\u002FAUTORUN.md` for the protocol (`_AGENT_CONTEXT` input, mode semantics, error handling). Bazaar-specific `_STEP_COMPLETE.Output` schema lives in `reference\u002Fautorun-schema.md`.\n\n## Nexus Hub Mode\n\nWhen input contains `## NEXUS_ROUTING`, return via `## NEXUS_HANDOFF` (canonical schema in `_common\u002FHANDOFF.md`). `bazaar` is registered under the Marketing \u002F SaaS \u002F E-commerce affinity buckets.\n\n## Reference Map\n\n| File | Read This When |\n|------|----------------|\n| `reference\u002Fchain-recipes.md` | Selecting a Recipe, mapping LP type → stage subset, or comparing time\u002Fquality trade-offs |\n| `reference\u002Fagent-roster.md` | Full per-stage delegate map, role responsibility, axis ownership, overlap notes |\n| `reference\u002Fquality-gates.md` | Stage exits, repair triggers, CVR\u002Fperf\u002Fa11y\u002F6-axis thresholds |\n| `reference\u002Fhandoff-protocols.md` | Emitting `LURE_STAGE_BUNDLE` or coordinating across delegates |\n| `reference\u002Fconversion-playbook.md` | Industry CVR baselines, copy framework, messaging hierarchy, CTA strategy per LP type |\n| `reference\u002Fcraft-standards.md` | Scoring Design \u002F Animation \u002F Branding — rubrics, axis ownership, motion tokens, brand-system anatomy, detail-craft checklist |\n| `_common\u002FCANDIDATE_SELECTION.md` | Narrowing hero directions, structure options, or design candidates to one — distinct from `craft-standards.md`'s single-artifact rubric gate; this governs multi-candidate stage funnels and selection records |\n| `_common\u002FASSET_PROVENANCE.md` | Hero images, generated illustrations, or stock assets enter DESIGN\u002FBUILD — rights, source, and state-transition discipline before Launch |\n| `reference\u002Fia-blueprint.md` | Designing IA (hierarchy, scan pattern, scroll narrative, heading tree), technical or content SEO, GEO citation-readiness |\n| `_common\u002FGROWTH_BRAND_PROOF.md` | Orchestrating the LP pipeline in `nexus growth-acceptance` Phase 2 — Brand Compiler 3-layer blocking, Brand Proof field alignment with the 6-axis gates, and the G12 Distinctiveness Floor embedding-distance check |\n| `reference\u002Fautorun-schema.md` | Emitting the AUTORUN `_STEP_COMPLETE` block — Bazaar-specific Output\u002FNext schema. |\n\n## Operational\n\n- Journal durable orchestration insights in `.agents\u002Fbazaar.md`.\n- Add an activity row to `.agents\u002FPROJECT.md` after task completion: `| YYYY-MM-DD | Bazaar | (action) | (files) | (outcome) |`.\n- Persist per-run state to `.agents\u002Fbazaar\u002F{project}.json` — field list and single-writer discipline in Core Contract.\n- Follow `_common\u002FOPERATIONAL.md` (output-language config resolution) and `_common\u002FGIT_GUIDELINES.md` (no agent names in commits\u002FPRs).\n",{"name":5,"risk":24,"domain":25,"source":26,"license":15,"version":30,"category":25,"platforms":31,"subdomain":38,"description":7},"low","devsecops",{"commit":27,"license":15,"repository":28,"imported_at":29},"f425adcb21","simota\u002Fagent-skills","2026-09-20","1.0.0",[32,33,34,35,36,37],"claude-code","cursor","codex","gemini","antigravity","copilot","general","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fdevsecops\u002Fbazaar","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bazaar",{"tool":51,"command":52},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bazaar",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bazaar","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fdevsecops\u002Fbazaar\u002FSKILL.md",true,[59],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"ARCHIVED_2026-08-19.md","REFERENCE","参考文档",556,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fdevsecops\u002Fbazaar\u002FARCHIVED_2026-08-19.md",[66,74,81,88,95,102],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":73},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":73},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":73},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":73},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":73},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":73},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]