Update to Omneky
Snapshot Oct 27, 2026 · 00:28 UTC · version 2.0.31
Collection source: downloaded plugin package.
Payment or plan references changed
Full description — Now says: credits/plan upgrade
Observed in published text. Live prices and checkout terms have not been verified by this change.
Up to 3 plugins free · no card required.
All fields and original values.
Full description
Oct 24, 2026 · 13:12 UTC
billing and credit-history reads
Oct 27, 2026 · 00:28 UTC
credits/plan upgrade
Skill instructions
Oct 24, 2026 · 13:12 UTC
billing and credit-history reads (omneky-billing). Intent keywords: weekly marketing plan, make me a plan, marketing plan, plan preview, revise plan, approve plan. Use the connected Omneky MCP server. Gate on this session's `tools/...
Oct 27, 2026 · 00:28 UTC
credits/plan upgrade (omneky-billing). Intent keywords: weekly marketing plan, make me a plan, marketing plan, plan preview, revise plan, approve plan. Use this when the user wants a weekly marketing plan created, revised, checked,...
Supporting files
Oct 24, 2026 · 13:12 UTC
[]
Oct 27, 2026 · 00:28 UTC
[{"relative_path":"references/playbook.md","size_in_bytes":4946}]
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -10,44 +10,43 @@ (omneky-competitor-analysis), A/B tests (omneky-ab-tests), first-run onboarding (omneky-onboarding), agency (omneky-agency), branded image/video creatives, - launch/connect (omneky-launch-and-connect), or billing and - credit-history reads (omneky-billing). Intent keywords: weekly - marketing plan, make me a plan, marketing plan, plan preview, - revise plan, approve plan. + launch/connect (omneky-launch-and-connect), or credits/plan + upgrade (omneky-billing). Intent keywords: weekly marketing + plan, make me a plan, marketing plan, plan preview, revise + plan, approve plan. --- # Omneky marketing plan -Use the connected Omneky MCP server. Gate on this session's `tools/list`. -If `analyze_brand` / `create_marketing_plan` / `get_marketing_plan` are -missing, say those tools are not available here and point the user to -the Omneky app. Do not invent them. Run only the tools that appear on -this session's `tools/list`. +Use this when the user wants a weekly marketing plan created, revised, +checked, or run. One job: goal intake → create → revise → poll → +preview → state the cost and proceed (no approval gate; stop only +above a cap the user named). The host runs each listed plan step. + +Gate on `analyze_brand`, `create_marketing_plan` and +`get_marketing_plan` being on `tools/list`; if missing, point to the +Omneky app. +Step detail: [playbook](references/playbook.md) (goal intake, loop, +pending polls, checks). -This skill owns goal intake / create / revise / poll / preview / -approve. The host runs each listed plan step (that is execute). <!-- host:begin name="creative-skill-routing" --> Branded stills → `omneky-image-ads`. Product video → -`omneky-product-video`. Edit / +`omneky-product-video`. Avatar / UGC → `omneky-avatar-ugc`. +Voice or video clone → `omneky-voice-and-video-clone`. Edit / resize → `omneky-edit-and-resize`. <!-- host:end --> -Handoff fields: -[handoff-contract](../_shared/references/handoff-contract.md). -Sourced ids (how to obtain / what to do if absent): -[preconditions](../_shared/references/preconditions.md). +Handoff fields: [handoff-contract](../_shared/references/handoff-contract.md). +Sourced ids (how to obtain / what to do if absent): [preconditions](../_shared/references/preconditions.md). <!-- host:begin name="scan-tools-routing" --> -Acceptance gates (for a later creative): -[creative-quality-gates](../_shared/references/creative-quality-gates.md). -Other intents: -[capability-registry](../_shared/references/capability-registry.md). -Write for: -[marketer-persona](../_shared/references/marketer-persona.md). +Acceptance gates (for a later creative): [creative-quality-gates](../_shared/references/creative-quality-gates.md). +Other intents: [capability-registry](../_shared/references/capability-registry.md). +Write for: [marketer-persona](../_shared/references/marketer-persona.md). <!-- host:end --> ## Goal -Author a weekly plan from a stated goal, preview the exact quote, get one yes, then host-run each listed step. +Author a weekly plan from a stated goal, preview the exact quote, state it, then host-run each listed step. ## Prerequisites @@ -60,13 +59,16 @@ ## Flow -Goal intake → analyze → create → revise → preview → one yes → host executes listed tools. Deliverable: plan id, checklist, quoted credits, step status, confidence. +1. Take the goal, budget, and window; ask only for what is missing. +2. `analyze_brand`, then `create_marketing_plan`. +3. Poll `get_marketing_plan` (`plan_id`) within the bounds in the playbook. +4. Revise with `revise_marketing_plan` until the user is happy. +5. `preview_marketing_plan_execution`, state the cost, and let the + host run each listed step. +6. Deliver plan id, checklist, step status, and confidence. -When the plan will feed a later creative, collect `approved_claims` -from the user or the plan's cited sources, and pass -`source_evidence` from `analyze_brand` / the approved plan scope -when the next step is plan-driven creative or launch. -Do not invent a claim. +When the plan feeds a later creative, hand over `source_evidence` and +`approved_claims` in the handoff (not as tool arguments). ## When to use @@ -78,133 +80,30 @@ - Not paid-media analysis, ROAS, or catalogue import - Not a standalone image-ad or product-video generate call - Not live spend or go-live -- Not launch/connect or billing reads +- Not launch/connect or credit-balance / plan upgrade ## Intent keywords weekly marketing plan, make me a plan, marketing plan, plan preview, revise plan -## Goal intake - -Ask once, only for what is missing, before `analyze_brand`: - -- Outcome (what "good" looks like) -- Timeframe (default **7 days**) -- Channels they care about -- Constraints (keep launches `PAUSED`, brand claims they already - approved) -- A credit or budget cap if they named one - -Do not invent a cap. Do not start create until `brand_id` is -known. - -## Loop - -1. `analyze_brand` with `brand_id` (optional `website_url`). Draft - `plan_id` / `analysis_id`, no steps. Uses Exa for evidence. -2. `create_marketing_plan` with `brand_id`, `plan_id`, and - `analysis_id`. Omit `plan_body`; the server authors the plan. Default - timeframe is **7 days**. Do not write `plan_body.steps`. Do not stop - on `plan_body_required`. If the result is pending, follow Pending - polls below, then read it with `get_marketing_plan`. Create is - draft-only: no generation, launch, or credit deduct. -3. `revise_marketing_plan` with an `instruction` (or a server-authored - `plan_body`) if the user wants changes. That starts a **pending - revision**; poll `get_marketing_plan` until applied (same bounds). - `plan_version` increments by 1 on apply, not at start. Pass - `step_updates` or `completed_step_ids` to mark host-run steps done. - Status-only mark-done does not start a pending revision. -4. `preview_marketing_plan_execution` is mandatory after create and - after every applied revise. It is read-only and has no side effects. - It returns the ordered checklist plus credit quotes from - `quote_creative_credits`. Show the credit quote as the one - approval. Re-preview after revise so the checklist matches. -5. **Approve.** One yes on **this** preview's checklist plus the - exact quoted `credits.total_credits`. That yes is the execute - gate. No yes → do not run steps. -6. **Execute.** Plans are data. Each step is - `{tool, arguments, depends_on, status}`. `tool` is a name from - this session's `tools/list`. - <!-- host:begin name="host-run-steps" --> - After that yes, call each - `step.tool` with `step.arguments` yourself. - <!-- host:end --> - Then - `revise_marketing_plan` to mark that step done. Read progress - with `get_marketing_plan` (read-only; unrun steps show `pending`). - There is no execute-plan tool on this surface. Do not invent one. - Leftover runs started outside this surface: poll - `get_marketing_plan_run` or stop them with - `cancel_marketing_plan_run`. - -## Pending polls - -Never silent-loop. Never start a second create or revise while one -may still be running. Reuse the same `plan_id`. - -1. Tell the user the plan is being written (or the revision is - applying). -2. Call `get_marketing_plan` every **10 seconds**, at most **6** times - (~60s). -3. Still pending: "Still writing the plan." -4. After 6 pending reads: stop. Offer to check back. Do not resubmit - create or revise. -5. When applied: run Plan-created checks, then preview. - -Quoted cost is compared to its **approved** value. Request arguments -never prove a saved plan or preview. - -Reply or a `get_marketing_plan` read-back already shows the fact → -say it plainly (e.g. "done"). Do not hedge. Missing detail → **one** -get. If it is still not confirmed, say so in one short plain sentence -(e.g. "I couldn't confirm the charge"). If a check fails: say which -field differed. Do not run steps on a stale preview. - -## Plan-created checks - -After create or an applied revise — before preview exists: - -- Non-empty `plan_id` — observe create/revise or `get_marketing_plan` -- Non-empty steps — observe plan_body.steps on `get_marketing_plan` -- Selected step id + one-line summary match the request — observe - those saved-plan fields, not the create arguments -- `plan_version` equals the applied version (revise +1 on apply) — - observe `get_marketing_plan` - -## Preview-approved checks - -After `preview_marketing_plan_execution`, before the host runs steps. -User approved **this** preview: - -- Ordered checklist tools are names from this session's `tools/list` -- Quoted cost equals the **approved** cost — observe preview - `credits.total_credits` (or equivalent) - -## Host-step checks - -After each listed `step.tool` call: - -- That step's `status` is `done` — observe `get_marketing_plan` after - `revise_marketing_plan` with `step_updates` / `completed_step_ids` -- Unrun steps may stay `pending` -- Charge for that step reconciles with the **approved** quoted line - when the tool is quotable - ## Failure and recovery Auth / 401 → `omneky-getting-started-and-failures` (host OAuth). -Empty reporting → empty is missing data, not zero; narrow the window. -`credit_insufficient` → nothing charged; the user can add credits in the Omneky app. -`needs_user_decision` → `request_user_decision`; never dump JSON. -Missing tool → say so; Omneky app. Do not invent it. +Empty reporting → `get_performance_summary` (`include_coverage=true`); empty is not zero. +`credit_insufficient` → nothing charged; state balance vs required +(`omneky-billing`). No payment links. +`needs_user_decision` → fill the missing detail and call again; ask in plain chat only if you cannot. Never dump JSON. +Missing tool → this session may run an older published app snapshot: look +the name up in [tool-name-fallbacks](../_shared/references/tool-name-fallbacks.md) +and call the older name if that one is on `tools/list`. If neither is +listed, say so; Omneky app. Do not invent it. Never ask for internal ids. Never silent-switch `brand_id`. <!-- host:begin name="capability-gaps-link" --> ## Gaps -This connector cannot do comment/social inbox, landing pages, -subtitle burn-in, email/SMS, organic scheduling, Meta Ad Library -competitor ads, virtual try-on, or website builder. Decline those. -See [capability-gaps](../_shared/references/capability-gaps.md). +Decline social inbox, landing pages, subtitle burn-in, email/SMS, +organic scheduling, Ad Library ads, try-on, and website builder +([capability-gaps](../_shared/references/capability-gaps.md)). <!-- host:end -->
Full technical diff · 3 changed fields
changed /description
"Create, revise, poll, preview (exact credit quote + checklist), and track an Omneky marketing plan. This skill owns the weekly-plan loop. The host runs each listed step itself. Use when the user wants a weekly marketing plan, make me a plan, plan preview, or plan progress. Do not use for paid-media analysis or catalogue (omneky-analytics-and-catalogue), competitor analysis (omneky-competitor-analysis), A/B tests (omneky-ab-tests), first-run onboarding (omneky-onboarding), agency (omneky-agency), branded image/video creatives, launch/connect (omneky-launch-and-connect), or billing and credit-history reads (omneky-billing). Intent keywords: weekly marketing plan, make me a plan, marketing plan, plan preview, revise plan, approve plan."
"Create, revise, poll, preview (exact credit quote + checklist), and track an Omneky marketing plan. This skill owns the weekly-plan loop. The host runs each listed step itself. Use when the user wants a weekly marketing plan, make me a plan, plan preview, or plan progress. Do not use for paid-media analysis or catalogue (omneky-analytics-and-catalogue), competitor analysis (omneky-competitor-analysis), A/B tests (omneky-ab-tests), first-run onboarding (omneky-onboarding), agency (omneky-agency), branded image/video creatives, launch/connect (omneky-launch-and-connect), or credits/plan upgrade (omneky-billing). Intent keywords: weekly marketing plan, make me a plan, marketing plan, plan preview, revise plan, approve plan."
changed /included_files
[]
[
{
"relative_path": "references/playbook.md",
"size_in_bytes": 4946
}
]changed /skill_md_contents
"---\nname: omneky-marketing-plan\ndescription: >-\n Create, revise, poll, preview (exact credit quote + checklist), and\n track an Omneky marketing plan. This skill owns the weekly-plan\n loop. The host runs each listed step itself. Use when the user wants\n a weekly marketing plan, make me a plan, plan preview, or plan\n progress. Do not use for paid-media analysis or catalogue\n (omneky-analytics-and-catalogue), competitor analysis\n (omneky-competitor-analysis), A/B tests (omneky-ab-tests),\n first-run onboarding (omneky-onboarding), agency\n (omneky-agency), branded image/video creatives,\n launch/connect (omneky-launch-and-connect), or billing and\n credit-history reads (omneky-billing). Intent keywords: weekly\n marketing plan, make me a plan, marketing plan, plan preview,\n revise plan, approve plan.\n---\n\n# Omneky marketing plan\n\nUse the connected Omneky MCP server. Gate on this session's `tools/list`.\nIf `analyze_brand` / `create_marketing_plan` / `get_marketing_plan` are\nmissing, say those tools are not available here and point the user to\nthe Omneky app. Do not invent them. Run only the tools that appear on\nthis session's `tools/list`.\n\nThis skill owns goal intake / create / revise / poll / preview /\napprove. The host runs each listed plan step (that is execute).\n<!-- host:begin name=\"creative-skill-routing\" -->\nBranded stills → `omneky-image-ads`. Product video →\n`omneky-product-video`. Edit /\nresize → `omneky-edit-and-resize`.\n<!-- host:end -->\n\nHandoff fields:\n[handoff-contract](../_shared/references/handoff-contract.md).\nSourced ids (how to obtain / what to do if absent):\n[preconditions](../_shared/references/preconditions.md).\n<!-- host:begin name=\"scan-tools-routing\" -->\nAcceptance gates (for a later creative):\n[creative-quality-gates](../_shared/references/creative-quality-gates.md).\nOther intents:\n[capability-registry](../_shared/references/capability-registry.md).\nWrite for:\n[marketer-persona](../_shared/references/marketer-persona.md).\n<!-- host:end -->\n\n## Goal\n\nAuthor a weekly plan from a stated goal, preview the exact quote, get one yes, then host-run each listed step.\n\n## Prerequisites\n\n| Need | Check | If missing |\n|---|---|---|\n| Brand | `list_brands` | Ask which |\n| Analysis | `analyze_brand` | Call it; draft only |\n| Plan tools | `create_marketing_plan` / `get_marketing_plan` / `revise_marketing_plan` | Say plan tools are missing |\n| Preview quote | `preview_marketing_plan_execution` | Do not run steps without this preview |\n\n## Flow\n\nGoal intake → analyze → create → revise → preview → one yes → host executes listed tools. Deliverable: plan id, checklist, quoted credits, step status, confidence.\n\nWhen the plan will feed a later creative, collect `approved_claims`\nfrom the user or the plan's cited sources, and pass\n`source_evidence` from `analyze_brand` / the approved plan scope\nwhen the next step is plan-driven creative or launch.\nDo not invent a claim.\n\n## When to use\n\n- Weekly marketing plan / \"make me a plan\"\n- Revise, preview, or mark plan-step progress\n\n## When not to use\n\n- Not paid-media analysis, ROAS, or catalogue import\n- Not a standalone image-ad or product-video generate call\n- Not live spend or go-live\n- Not launch/connect or billing reads\n\n## Intent keywords\n\nweekly marketing plan, make me a plan, marketing plan, plan preview,\nrevise plan\n\n## Goal intake\n\nAsk once, only for what is missing, before `analyze_brand`:\n\n- Outcome (what \"good\" looks like)\n- Timeframe (default **7 days**)\n- Channels they care about\n- Constraints (keep launches `PAUSED`, brand claims they already\n approved)\n- A credit or budget cap if they named one\n\nDo not invent a cap. Do not start create until `brand_id` is\nknown.\n\n## Loop\n\n1. `analyze_brand` with `brand_id` (optional `website_url`). Draft\n `plan_id` / `analysis_id`, no steps. Uses Exa for evidence.\n2. `create_marketing_plan` with `brand_id`, `plan_id`, and\n `analysis_id`. Omit `plan_body`; the server authors the plan. Default\n timeframe is **7 days**. Do not write `plan_body.steps`. Do not stop\n on `plan_body_required`. If the result is pending, follow Pending\n polls below, then read it with `get_marketing_plan`. Create is\n draft-only: no generation, launch, or credit deduct.\n3. `revise_marketing_plan` with an `instruction` (or a server-authored\n `plan_body`) if the user wants changes. That starts a **pending\n revision**; poll `get_marketing_plan` until applied (same bounds).\n `plan_version` increments by 1 on apply, not at start. Pass\n `step_updates` or `completed_step_ids` to mark host-run steps done.\n Status-only mark-done does not start a pending revision.\n4. `preview_marketing_plan_execution` is mandatory after create and\n after every applied revise. It is read-only and has no side effects.\n It returns the ordered checklist plus credit quotes from\n `quote_creative_credits`. Show the credit quote as the one\n approval. Re-preview after revise so the checklist matches.\n5. **Approve.** One yes on **this** preview's checklist plus the\n exact quoted `credits.total_credits`. That yes is the execute\n gate. No yes → do not run steps.\n6. **Execute.** Plans are data. Each step is\n `{tool, arguments, depends_on, status}`. `tool` is a name from\n this session's `tools/list`.\n <!-- host:begin name=\"host-run-steps\" -->\n After that yes, call each\n `step.tool` with `step.arguments` yourself.\n <!-- host:end -->\n Then\n `revise_marketing_plan` to mark that step done. Read progress\n with `get_marketing_plan` (read-only; unrun steps show `pending`).\n There is no execute-plan tool on this surface. Do not invent one.\n Leftover runs started outside this surface: poll\n `get_marketing_plan_run` or stop them with\n `cancel_marketing_plan_run`.\n\n## Pending polls\n\nNever silent-loop. Never start a second create or revise while one\nmay still be running. Reuse the same `plan_id`.\n\n1. Tell the user the plan is being written (or the revision is\n applying).\n2. Call `get_marketing_plan` every **10 seconds**, at most **6** times\n (~60s).\n3. Still pending: \"Still writing the plan.\"\n4. After 6 pending reads: stop. Offer to check back. Do not resubmit\n create or revise.\n5. When applied: run Plan-created checks, then preview.\n\nQuoted cost is compared to its **approved** value. Request arguments\nnever prove a saved plan or preview.\n\nReply or a `get_marketing_plan` read-back already shows the fact →\nsay it plainly (e.g. \"done\"). Do not hedge. Missing detail → **one**\nget. If it is still not confirmed, say so in one short plain sentence\n(e.g. \"I couldn't confirm the charge\"). If a check fails: say which\nfield differed. Do not run steps on a stale preview.\n\n## Plan-created checks\n\nAfter create or an applied revise — before preview exists:\n\n- Non-empty `plan_id` — observe create/revise or `get_marketing_plan`\n- Non-empty steps — observe plan_body.steps on `get_marketing_plan`\n- Selected step id + one-line summary match the request — observe\n those saved-plan fields, not the create arguments\n- `plan_version` equals the applied version (revise +1 on apply) —\n observe `get_marketing_plan`\n\n## Preview-approved checks\n\nAfter `preview_marketing_plan_execution`, before the host runs steps.\nUser approved **this** preview:\n\n- Ordered checklist tools are names from this session's `tools/list`\n- Quoted cost equals the **approved** cost — observe preview\n `credits.total_credits` (or equivalent)\n\n## Host-step checks\n\nAfter each listed `step.tool` call:\n\n- That step's `status` is `done` — observe `get_marketing_plan` after\n `revise_marketing_plan` with `step_updates` / `completed_step_ids`\n- Unrun steps may stay `pending`\n- Charge for that step reconciles with the **approved** quoted line\n when the tool is quotable\n\n## Failure and recovery\n\nAuth / 401 → `omneky-getting-started-and-failures` (host OAuth).\nEmpty reporting → empty is missing data, not zero; narrow the window.\n`credit_insufficient` → nothing charged; the user can add credits in the Omneky app.\n`needs_user_decision` → `request_user_decision`; never dump JSON.\nMissing tool → say so; Omneky app. Do not invent it.\nNever ask for internal ids. Never silent-switch `brand_id`.\n\n<!-- host:begin name=\"capability-gaps-link\" -->\n## Gaps\n\nThis connector cannot do comment/social inbox, landing pages,\nsubtitle burn-in, email/SMS, organic scheduling, Meta Ad Library\ncompetitor ads, virtual try-on, or website builder. Decline those.\nSee [capability-gaps](../_shared/references/capability-gaps.md).\n<!-- host:end -->\n""---\nname: omneky-marketing-plan\ndescription: >-\n Create, revise, poll, preview (exact credit quote + checklist), and\n track an Omneky marketing plan. This skill owns the weekly-plan\n loop. The host runs each listed step itself. Use when the user wants\n a weekly marketing plan, make me a plan, plan preview, or plan\n progress. Do not use for paid-media analysis or catalogue\n (omneky-analytics-and-catalogue), competitor analysis\n (omneky-competitor-analysis), A/B tests (omneky-ab-tests),\n first-run onboarding (omneky-onboarding), agency\n (omneky-agency), branded image/video creatives,\n launch/connect (omneky-launch-and-connect), or credits/plan\n upgrade (omneky-billing). Intent keywords: weekly marketing\n plan, make me a plan, marketing plan, plan preview, revise\n plan, approve plan.\n---\n\n# Omneky marketing plan\n\nUse this when the user wants a weekly marketing plan created, revised,\nchecked, or run. One job: goal intake → create → revise → poll →\npreview → state the cost and proceed (no approval gate; stop only\nabove a cap the user named). The host runs each listed plan step.\n\nGate on `analyze_brand`, `create_marketing_plan` and\n`get_marketing_plan` being on `tools/list`; if missing, point to the\nOmneky app.\nStep detail: [playbook](references/playbook.md) (goal intake, loop,\npending polls, checks).\n\n<!-- host:begin name=\"creative-skill-routing\" -->\nBranded stills → `omneky-image-ads`. Product video →\n`omneky-product-video`. Avatar / UGC → `omneky-avatar-ugc`.\nVoice or video clone → `omneky-voice-and-video-clone`. Edit /\nresize → `omneky-edit-and-resize`.\n<!-- host:end -->\n\nHandoff fields: [handoff-contract](../_shared/references/handoff-contract.md).\nSourced ids (how to obtain / what to do if absent): [preconditions](../_shared/references/preconditions.md).\n<!-- host:begin name=\"scan-tools-routing\" -->\nAcceptance gates (for a later creative): [creative-quality-gates](../_shared/references/creative-quality-gates.md).\nOther intents: [capability-registry](../_shared/references/capability-registry.md).\nWrite for: [marketer-persona](../_shared/references/marketer-persona.md).\n<!-- host:end -->\n\n## Goal\n\nAuthor a weekly plan from a stated goal, preview the exact quote, state it, then host-run each listed step.\n\n## Prerequisites\n\n| Need | Check | If missing |\n|---|---|---|\n| Brand | `list_brands` | Ask which |\n| Analysis | `analyze_brand` | Call it; draft only |\n| Plan tools | `create_marketing_plan` / `get_marketing_plan` / `revise_marketing_plan` | Say plan tools are missing |\n| Preview quote | `preview_marketing_plan_execution` | Do not run steps without this preview |\n\n## Flow\n\n1. Take the goal, budget, and window; ask only for what is missing.\n2. `analyze_brand`, then `create_marketing_plan`.\n3. Poll `get_marketing_plan` (`plan_id`) within the bounds in the playbook.\n4. Revise with `revise_marketing_plan` until the user is happy.\n5. `preview_marketing_plan_execution`, state the cost, and let the\n host run each listed step.\n6. Deliver plan id, checklist, step status, and confidence.\n\nWhen the plan feeds a later creative, hand over `source_evidence` and\n`approved_claims` in the handoff (not as tool arguments).\n\n## When to use\n\n- Weekly marketing plan / \"make me a plan\"\n- Revise, preview, or mark plan-step progress\n\n## When not to use\n\n- Not paid-media analysis, ROAS, or catalogue import\n- Not a standalone image-ad or product-video generate call\n- Not live spend or go-live\n- Not launch/connect or credit-balance / plan upgrade\n\n## Intent keywords\n\nweekly marketing plan, make me a plan, marketing plan, plan preview,\nrevise plan\n\n## Failure and recovery\n\nAuth / 401 → `omneky-getting-started-and-failures` (host OAuth).\nEmpty reporting → `get_performance_summary` (`include_coverage=true`); empty is not zero.\n`credit_insufficient` → nothing charged; state balance vs required\n(`omneky-billing`). No payment links.\n`needs_user_decision` → fill the missing detail and call again; ask in plain chat only if you cannot. Never dump JSON.\nMissing tool → this session may run an older published app snapshot: look\nthe name up in [tool-name-fallbacks](../_shared/references/tool-name-fallbacks.md)\nand call the older name if that one is on `tools/list`. If neither is\nlisted, say so; Omneky app. Do not invent it.\nNever ask for internal ids. Never silent-switch `brand_id`.\n\n<!-- host:begin name=\"capability-gaps-link\" -->\n## Gaps\n\nDecline social inbox, landing pages, subtitle burn-in, email/SMS,\norganic scheduling, Ad Library ads, try-on, and website builder\n([capability-gaps](../_shared/references/capability-gaps.md)).\n<!-- host:end -->\n"
Full snapshot data
{
"description": "Create, revise, poll, preview (exact credit quote + checklist), and track an Omneky marketing plan. This skill owns the weekly-plan loop. The host runs each listed step itself. Use when the user wants a weekly marketing plan, make me a plan, plan preview, or plan progress. Do not use for paid-media analysis or catalogue (omneky-analytics-and-catalogue), competitor analysis (omneky-competitor-analysis), A/B tests (omneky-ab-tests), first-run onboarding (omneky-onboarding), agency (omneky-agency), branded image/video creatives, launch/connect (omneky-launch-and-connect), or credits/plan upgrade (omneky-billing). Intent keywords: weekly marketing plan, make me a plan, marketing plan, plan preview, revise plan, approve plan.",
"included_files": [
{
"relative_path": "references/playbook.md",
"size_in_bytes": 4946
}
],
"name": "omneky-marketing-plan",
"skill_md_contents": "---\nname: omneky-marketing-plan\ndescription: >-\n Create, revise, poll, preview (exact credit quote + checklist), and\n track an Omneky marketing plan. This skill owns the weekly-plan\n loop. The host runs each listed step itself. Use when the user wants\n a weekly marketing plan, make me a plan, plan preview, or plan\n progress. Do not use for paid-media analysis or catalogue\n (omneky-analytics-and-catalogue), competitor analysis\n (omneky-competitor-analysis), A/B tests (omneky-ab-tests),\n first-run onboarding (omneky-onboarding), agency\n (omneky-agency), branded image/video creatives,\n launch/connect (omneky-launch-and-connect), or credits/plan\n upgrade (omneky-billing). Intent keywords: weekly marketing\n plan, make me a plan, marketing plan, plan preview, revise\n plan, approve plan.\n---\n\n# Omneky marketing plan\n\nUse this when the user wants a weekly marketing plan created, revised,\nchecked, or run. One job: goal intake → create → revise → poll →\npreview → state the cost and proceed (no approval gate; stop only\nabove a cap the user named). The host runs each listed plan step.\n\nGate on `analyze_brand`, `create_marketing_plan` and\n`get_marketing_plan` being on `tools/list`; if missing, point to the\nOmneky app.\nStep detail: [playbook](references/playbook.md) (goal intake, loop,\npending polls, checks).\n\n<!-- host:begin name=\"creative-skill-routing\" -->\nBranded stills → `omneky-image-ads`. Product video →\n`omneky-product-video`. Avatar / UGC → `omneky-avatar-ugc`.\nVoice or video clone → `omneky-voice-and-video-clone`. Edit /\nresize → `omneky-edit-and-resize`.\n<!-- host:end -->\n\nHandoff fields: [handoff-contract](../_shared/references/handoff-contract.md).\nSourced ids (how to obtain / what to do if absent): [preconditions](../_shared/references/preconditions.md).\n<!-- host:begin name=\"scan-tools-routing\" -->\nAcceptance gates (for a later creative): [creative-quality-gates](../_shared/references/creative-quality-gates.md).\nOther intents: [capability-registry](../_shared/references/capability-registry.md).\nWrite for: [marketer-persona](../_shared/references/marketer-persona.md).\n<!-- host:end -->\n\n## Goal\n\nAuthor a weekly plan from a stated goal, preview the exact quote, state it, then host-run each listed step.\n\n## Prerequisites\n\n| Need | Check | If missing |\n|---|---|---|\n| Brand | `list_brands` | Ask which |\n| Analysis | `analyze_brand` | Call it; draft only |\n| Plan tools | `create_marketing_plan` / `get_marketing_plan` / `revise_marketing_plan` | Say plan tools are missing |\n| Preview quote | `preview_marketing_plan_execution` | Do not run steps without this preview |\n\n## Flow\n\n1. Take the goal, budget, and window; ask only for what is missing.\n2. `analyze_brand`, then `create_marketing_plan`.\n3. Poll `get_marketing_plan` (`plan_id`) within the bounds in the playbook.\n4. Revise with `revise_marketing_plan` until the user is happy.\n5. `preview_marketing_plan_execution`, state the cost, and let the\n host run each listed step.\n6. Deliver plan id, checklist, step status, and confidence.\n\nWhen the plan feeds a later creative, hand over `source_evidence` and\n`approved_claims` in the handoff (not as tool arguments).\n\n## When to use\n\n- Weekly marketing plan / \"make me a plan\"\n- Revise, preview, or mark plan-step progress\n\n## When not to use\n\n- Not paid-media analysis, ROAS, or catalogue import\n- Not a standalone image-ad or product-video generate call\n- Not live spend or go-live\n- Not launch/connect or credit-balance / plan upgrade\n\n## Intent keywords\n\nweekly marketing plan, make me a plan, marketing plan, plan preview,\nrevise plan\n\n## Failure and recovery\n\nAuth / 401 → `omneky-getting-started-and-failures` (host OAuth).\nEmpty reporting → `get_performance_summary` (`include_coverage=true`); empty is not zero.\n`credit_insufficient` → nothing charged; state balance vs required\n(`omneky-billing`). No payment links.\n`needs_user_decision` → fill the missing detail and call again; ask in plain chat only if you cannot. Never dump JSON.\nMissing tool → this session may run an older published app snapshot: look\nthe name up in [tool-name-fallbacks](../_shared/references/tool-name-fallbacks.md)\nand call the older name if that one is on `tools/list`. If neither is\nlisted, say so; Omneky app. Do not invent it.\nNever ask for internal ids. Never silent-switch `brand_id`.\n\n<!-- host:begin name=\"capability-gaps-link\" -->\n## Gaps\n\nDecline social inbox, landing pages, subtitle burn-in, email/SMS,\norganic scheduling, Ad Library ads, try-on, and website builder\n([capability-gaps](../_shared/references/capability-gaps.md)).\n<!-- host:end -->\n"
}SHA-256 of public snapshot: 0f655e547dfea0cf3d4eb7057d5429a5111ab4654023bc931875565daa87b4ab