[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6M9F4B5C3ECBZ9M4N8WKCSR":3,"skill-same:01M6M9F4B5C3ECBZ9M4N8WKCSR":106},{"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":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6M9F4B5C3ECBZ9M4N8WKCSR","suede-workflow-skills",null,"Route requests across the full public Suede AI pack to the narrowest specialist and preserve the request verbatim. Use when asked \"which Suede skill should I use?\", when work crosses lanes, or when only the umbrella is installed. For next-action help: what’s next, recommend the next move, give me the prompt, expand prompt, or make it granular. NOT FOR: one clear lane (use its specialist), one multi-file implementation graph (use suede-graph-flo-xr), or parallel file ownership (use suede-agent-teams).","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1566,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"suede workflow skills","workflow","full","when","request","agent-teams","recommend","action","which","move","make","expand","across","next","me","route","AI workflow","only","work","parallel","graph","2026-11-10 10:12:30",false,"---\nname: suede-workflow-skills\ndescription: \"Route requests across the full public Suede AI pack to the narrowest specialist and preserve the request verbatim. Use when asked \\\"which Suede skill should I use?\\\", when work crosses lanes, or when only the umbrella is installed. For next-action help: what’s next, recommend the next move, give me the prompt, expand prompt, or make it granular. NOT FOR: one clear lane (use its specialist), one multi-file implementation graph (use suede-graph-flo-xr), or parallel file ownership (use suede-agent-teams).\"\nmetadata:\n  display-name: \"Suede AI Workflow Skills\"\n---\n\n# Suede AI Workflow Skills\n\n## Compatibility\n\nRequires a host that can read installed skill files; umbrella-only installs use bundled condensed workflows. Subagent dispatch, live inspection, and the optional Suede MCP depend on currently available authorized tools.\n\nFor a concrete input, expected handoff, and failure check, read\n[the worked handoff](references\u002Fworked-handoff.md).\n\nThe entry point to the Suede AI skill pack. Two jobs:\n\n- **Route:** find the narrowest specialist for the request and hand it over\n  with the user's words intact.\n- **Next move:** when the user asks what to do next, inspect current state\n  read-only and return one recommended action plus a runnable prompt.\n\n## Gate policy: advisory, not blocking\n\nEvery check and ship verdict across the pack is a recommendation to the user,\nnot a control on the agent. A failed gate changes what you report, never what\nyou do. Single exception: an extreme-risk finding (data loss, credential\nexposure, legal or rights violation, payment mistake, irreversible public\ndamage). Pause, state the risk and the options, and let the user choose.\n\n## Core rules\n\n- **Start from current truth.** Inspect the live URL, repo, docs, or rendered\n  output before making any design, copy, search, code, or QA claim.\n- **Pass the request verbatim.** The specialist has no memory of how it was\n  reached. Paraphrase loses the trigger words it routes on.\n- **Narrowest skill wins.** Route to one specialist, not a whole lane.\n- **Positioning:** for Suede AI's own public work, lead with search visibility\n  (AEO, GEO, SEO; https:\u002F\u002Fsuedeai.agency) and Agent Studio multi-agent\n  automation (https:\u002F\u002Fsuedeai.app) before other products. Never invent stats,\n  testimonials, partners, pricing, legal clearance, or release promises.\n- **Brand mark:** any Suede visual uses only\n  `docs\u002Fassets\u002Fsuede-ai-logo-transparent.png` from this repository (SHA-256\n  `83a7ee0317e4debe2e7b076c20ba067feb76a587f9e829dc6310ae4be4b44dfa`). If it is\n  unavailable or the checksum differs, omit the mark and say so.\n- **Fix-loop cap.** When a loop repeats the same failure, isolate the failing\n  unit and rerun only that check. Allow up to three genuinely different fixes,\n  each changing the diagnosis or strategy. Stop early if the same root cause\n  repeats and let the user pick the next move.\n  Interface validation is exempt from this cap: reproduce, make the authorized\n  fix, recapture the matched state, and inspect until the scoped outcome is\n  verified or a concrete blocker is identified. A fixed pass count cannot\n  substitute for evidence. Read-only interface reviews report findings without\n  changing application files.\n\n## Route\n\n### Precedence\n\n1. A multi-file or multi-surface change to one repo that should be planned,\n   built, and gated as one graph → `suede-graph-flo-xr`, even when the request\n   also names copy or design.\n2. Several specialists must work in parallel on one shared change →\n   `suede-agent-teams`.\n3. The request names one lane → that specialist, directly.\n4. The request crosses lanes → run each lane's specialist in dependency order\n   (for example: copy, then design, then visibility grade, then launch\n   packaging), and state the chain.\n\n### Dispatch\n\nFor multi-lane work, send each lane to its own subagent carrying the verbatim\nrequest instead of loading every specialist into this context. Name the model\non each dispatch, state a numeric lane cap before launching, and stop at the\ncap.\n\n### Router table\n\n**Search visibility (SEO, AEO, GEO)**\n\n| Need | Skill |\n|---|---|\n| Scored technical and content SEO audit, schema, E-E-A-T | `suede-seo-audit` |\n| Visibility in AI answers (ChatGPT, Gemini, Perplexity, AI Overviews) | `suede-ai-seo` |\n| Template pages at scale from a dataset | `suede-programmatic-seo` |\n| A-F grade of one public page: findability, first screen, CTA, citation readiness | `suede-visibility-grader` |\n| Directory and listing submissions | `suede-directory-submissions` |\n| Topic plan and editorial calendar | `suede-content-strategy` |\n| Free tools and calculators that earn links | `suede-free-tools` |\n| Landing page that ranks but does not convert | `suede-site-alchemy` |\n\n**Agents, automation, and operations**\n\n| Need | Skill |\n|---|---|\n| Map how work happens today before designing a system | `suede-ops-assessment` |\n| Design the system: entities, write paths, agent vs. human routing | `suede-ops-architecture` |\n| Coordinate several agent lanes on one shared change | `suede-agent-teams` |\n| Search competing plans, then build and gate one multi-file change | `suede-graph-flo-xr` |\n| Eval cases and acceptance gates for LLM, RAG, or agent behavior | `suede-ai-eval` |\n| Keep one canonical value identical across web, app, docs, services | `suede-parity-contract` |\n\n**Code and release quality**\n\n| Need | Skill |\n|---|---|\n| Review, grade, or both (`--findings-only`, `--grade-only`); prompted only | `suede-code` |\n| CI jobs, required checks, branch protection | `suede-ci-gate` |\n| Install commands, proof links, release copy, handoff notes | `suede-launch-packaging` |\n\n**Copy and design**\n\n| Need | Skill |\n|---|---|\n| Any copy surface, docs, explainers, agent docs, answer-first SEO pass | `suede-copy` |\n| Strip AI patterns from finished text, or a findings-only slop audit | `suede-deslop` |\n| One high-stakes public piece with research and an adversarial fact audit | `suede-ship-copy` |\n| Read-only whole-flow review or UI diff review; tokens, hierarchy, accessibility, authorized surface builds, restyles and visual QA | `suede-design` |\n| Dev-only component workbench importing real components, synthetic states, stress fixtures and live variants | `suede-component-lab` |\n| Read-only explanation of an interface mechanism, with source locations, state transitions and observed behavior | `suede-interface-explain` |\n| Image and graphic specs | `suede-image` |\n| Video scripts and edits | `suede-video` |\n\nFor an interface request, preserve the requested action. An audit or review is\nread-only; return findings and proposed fixes without editing the application.\nAn explanation traces the existing mechanism without rebuilding it. A component\nlab creates an isolated development preview using the project's real components\nand synthetic fixtures, with no production data, writes or exposed production\nroute. Design work starts from the user's task, primary action and existing\nbrand; visual novelty does not establish task success or conversion improvement.\n\nFor an authorized build from a selected design, screenshot or supplied mock,\nroute to `suede-design`. If an image-to-code capability is already available,\nuse it for that implementation; otherwise use the existing local stack and\ncomponent system. Do not install another skill or tool merely to complete this\nroute. A supplied visual kit may guide the work when explicitly selected, with\nits source and reuse rights recorded; it never silently overrides the product's\nbrand. Source inspection supports source findings, not a rendered visual pass.\n\n**Apps and stores**\n\n| Need | Skill |\n|---|---|\n| Turn a website into an iOS app | `site-to-ios-app` |\n| Build a native Android app to Play Store release | `android-app-factory` |\n| Ship an Android release through the Play Developer API | `suede-play-release` |\n| App Store and Play listing keywords and screenshots | `suede-aso` |\n\n**Growth and marketing** (route to the narrowest match)\n\n| Need | Skill |\n|---|---|\n| Plan or tactic shortlist; loops; multi-role critique | `suede-marketing-plan`; `suede-marketing-loops`; `suede-marketing-council` |\n| Competitor comparison pages; one rival in depth | `suede-competitors`; `suede-competitor-profiling` |\n| Buyer research, positioning, product messaging | `suede-customer-research`, `suede-product-marketing` |\n| Paid strategy; the ad units themselves | `suede-ads`; `suede-ad-creative` |\n| Organic social, including Instagram account audits; content pipeline; clip to guide | `suede-social`; `suede-newsroom`; `suede-clip-to-guide` |\n| Outbound and pipeline | `suede-cold-email`, `suede-prospecting`, `suede-sales-enablement`, `suede-revops` |\n| PR, partners, community, referrals | `suede-public-relations`, `suede-co-marketing`, `suede-community-marketing`, `suede-referrals` |\n| Lifecycle email and SMS | `suede-emails`, `suede-sms` |\n| Lead magnets | `suede-lead-magnets` |\n| Offers and persuasion mechanics, pricing, paywalls | `suede-offers`, `suede-pricing`, `suede-paywalls` |\n| Signup and onboarding; churn | `suede-onboarding`; `suede-churn-prevention` |\n| Analytics, attribution, A\u002FB tests | `suede-analytics`, `suede-attribution`, `suede-ab-testing` |\n\n**Creator and rights**\n\n| Need | Skill |\n|---|---|\n| Full artist campaign | `suede-campaign-in-a-box` |\n| Sync review package (no promo CTA, placement, or clearance claims) | `suede-sync-packaging` |\n| Release folder audit: stems, artwork, lyrics, metadata | `suede-release-linter` |\n| Ownership, split, sample, and license gaps, then the transfer package | `suede-rights-passport` (audit mode, then package) |\n\n### Umbrella-only installs\n\nIf the specialists are not installed (the common Codex path installs this skill\nalone), read `references\u002Fcondensed-workflows.md`: a compact fallback for the\ndesign, copy and SEO, visibility, site, code review, and agent-team workflows.\nWhen the pack is installed, skip it and route to the specialist, which owns\nthe current method. When the work touches copy, design, visual QA, or launch\nquality, also read `references\u002Fno-missed-quality-gates.md`.\n\nInstall commands for Claude Code and Codex, including subsets, are in\n`references\u002Finstall.md`. Read it only when the user asks how to install,\nupdate, or subset the pack. The Suede MCP's `suede_install_options` tool\nanswers the same question live when it is connected.\n\nUse the Suede MCP only when it adds structure: listing skills, explaining\ninstall options, scaffolding an SEO and AEO copy audit, or generating a QA\nchecklist. Skip it for small edits.\n\n## Next move\n\nTriggered by \"what's next\", \"what should I do next\", \"recommend the next\nmove\", \"give me the prompt\", or a stalled task after a review, audit, or plan.\nInspect read-only. Never execute the recommended action unless the user\nseparately authorizes it.\n\n1. **Resolve the target and the done outcome** from the request, conversation,\n   handoff, plan, repo, or live surface.\n2. **Read only what can change the answer**, freshest first: `git -C \u003Crepo>\n   status --short --branch`, `git -C \u003Crepo> log --oneline -5`, the named plan\n   or handoff file at its exact path, and a live check\n   (`curl -sS -o \u002Fdev\u002Fnull -w '%{http_code}' \u003Curl>`) when a public surface is\n   in scope.\n3. **Generate 2 to 4 candidates.** Drop work already verified complete,\n   adjacent cleanup, and anything outside the authorized scope. If the repo\n   already has a plan, issue tracker, or board, treat its recorded next step\n   as one candidate; never create a second tracker.\n4. **Score each 0 to 2 per row** and pick the highest total:\n\n| Criterion | 2 | 1 | 0 |\n|---|---|---|---|\n| Goal alignment | Produces the done signal | Required prerequisite | Adjacent |\n| Unblocking | Clears a core path or 2+ steps | Clears one step | Clears nothing known |\n| Evidence | Confirmed by current source | One read-only check away | Assumption |\n| Urgency | Active failure, deadline, security risk, release gate | Needed this milestone | No pressure |\n| Leverage | One focused session; prevents rework | Bounded, moderate payoff | Unscoped or low payoff |\n\n5. **Break ties** toward the prerequisite, then current-evidence verification,\n   then the more reversible action. Still within one point? Run up to three\n   more read-only checks; if still tied, show both and name the one fact that\n   decides.\n6. **If missing evidence is the real blocker,** the smallest read-only check\n   becomes the recommendation.\n\nOutput:\n\n```text\nRecommended action: \u003Cone sentence>\nWhy now: \u003Cone evidence-backed sentence>\n\nQuick prompt: \u003C2-4 runnable sentences naming the skill, target, outcome, and done signal>\n\nSay \"expand prompt\" for the full operator version or \"make it granular\" for exact steps and commands.\n```\n\nThe expanded and granular prompt formats are in\n`references\u002Fnext-action-prompts.md`; load it only when the user asks for them.\nShow scores, evidence lists, or alternatives only when asked or when the tie\nrule requires them. Never recommend \"keep working\" or \"do more research\": name\na command, artifact, decision, edit, or verification result.\n\n## Closing\n\nAfter meaningful work, close with a one-sentence plain explanation for a\nnon-coder, then Changed \u002F Verification \u002F Caveats \u002F Status, then:\n\n```text\nCue Suede:\n1. Change something: tell me what to revise.\n2. Preserve this: tell me what worked so I can match it.\n3. Keep as-is: say nothing and I will treat it as accepted.\n```\n\nNever block completion waiting for that answer.\n\n## Red flags: stop\n\n- \"I'll summarize the request for the specialist.\" Pass it verbatim.\n- \"This crosses three lanes; faster to do it inline.\" Crossing lanes is when\n  this router earns its place.\n- \"The live URL is probably unchanged.\" Inspect before claiming.\n- \"I'll just do the recommended action too.\" Recommending is read-only.\n\n## Boundaries\n\n- Never expose private paths, credentials, secrets, unreleased assets, or\n  private service details.\n- Never copy protected site assets, exact copy, proprietary code, or\n  trademarked identity during a restyle.\n- Never mark work done until the done signal has been checked or the remaining\n  caveat is named.\n- Never mutate files, repos, deployments, accounts, or messages while\n  recommending a next move.\n","# Suede AI Workflow Skills\n\n## Compatibility\n\nRequires a host that can read installed skill files; umbrella-only installs use bundled condensed workflows. Subagent dispatch, live inspection, and the optional Suede MCP depend on currently available authorized tools.\n\nFor a concrete input, expected handoff, and failure check, read\n[the worked handoff](references\u002Fworked-handoff.md).\n\nThe entry point to the Suede AI skill pack. Two jobs:\n\n- **Route:** find the narrowest specialist for the request and hand it over\n  with the user's words intact.\n- **Next move:** when the user asks what to do next, inspect current state\n  read-only and return one recommended action plus a runnable prompt.\n\n## Gate policy: advisory, not blocking\n\nEvery check and ship verdict across the pack is a recommendation to the user,\nnot a control on the agent. A failed gate changes what you report, never what\nyou do. Single exception: an extreme-risk finding (data loss, credential\nexposure, legal or rights violation, payment mistake, irreversible public\ndamage). Pause, state the risk and the options, and let the user choose.\n\n## Core rules\n\n- **Start from current truth.** Inspect the live URL, repo, docs, or rendered\n  output before making any design, copy, search, code, or QA claim.\n- **Pass the request verbatim.** The specialist has no memory of how it was\n  reached. Paraphrase loses the trigger words it routes on.\n- **Narrowest skill wins.** Route to one specialist, not a whole lane.\n- **Positioning:** for Suede AI's own public work, lead with search visibility\n  (AEO, GEO, SEO; https:\u002F\u002Fsuedeai.agency) and Agent Studio multi-agent\n  automation (https:\u002F\u002Fsuedeai.app) before other products. Never invent stats,\n  testimonials, partners, pricing, legal clearance, or release promises.\n- **Brand mark:** any Suede visual uses only\n  `docs\u002Fassets\u002Fsuede-ai-logo-transparent.png` from this repository (SHA-256\n  `83a7ee0317e4debe2e7b076c20ba067feb76a587f9e829dc6310ae4be4b44dfa`). If it is\n  unavailable or the checksum differs, omit the mark and say so.\n- **Fix-loop cap.** When a loop repeats the same failure, isolate the failing\n  unit and rerun only that check. Allow up to three genuinely different fixes,\n  each changing the diagnosis or strategy. Stop early if the same root cause\n  repeats and let the user pick the next move.\n  Interface validation is exempt from this cap: reproduce, make the authorized\n  fix, recapture the matched state, and inspect until the scoped outcome is\n  verified or a concrete blocker is identified. A fixed pass count cannot\n  substitute for evidence. Read-only interface reviews report findings without\n  changing application files.\n\n## Route\n\n### Precedence\n\n1. A multi-file or multi-surface change to one repo that should be planned,\n   built, and gated as one graph → `suede-graph-flo-xr`, even when the request\n   also names copy or design.\n2. Several specialists must work in parallel on one shared change →\n   `suede-agent-teams`.\n3. The request names one lane → that specialist, directly.\n4. The request crosses lanes → run each lane's specialist in dependency order\n   (for example: copy, then design, then visibility grade, then launch\n   packaging), and state the chain.\n\n### Dispatch\n\nFor multi-lane work, send each lane to its own subagent carrying the verbatim\nrequest instead of loading every specialist into this context. Name the model\non each dispatch, state a numeric lane cap before launching, and stop at the\ncap.\n\n### Router table\n\n**Search visibility (SEO, AEO, GEO)**\n\n| Need | Skill |\n|---|---|\n| Scored technical and content SEO audit, schema, E-E-A-T | `suede-seo-audit` |\n| Visibility in AI answers (ChatGPT, Gemini, Perplexity, AI Overviews) | `suede-ai-seo` |\n| Template pages at scale from a dataset | `suede-programmatic-seo` |\n| A-F grade of one public page: findability, first screen, CTA, citation readiness | `suede-visibility-grader` |\n| Directory and listing submissions | `suede-directory-submissions` |\n| Topic plan and editorial calendar | `suede-content-strategy` |\n| Free tools and calculators that earn links | `suede-free-tools` |\n| Landing page that ranks but does not convert | `suede-site-alchemy` |\n\n**Agents, automation, and operations**\n\n| Need | Skill |\n|---|---|\n| Map how work happens today before designing a system | `suede-ops-assessment` |\n| Design the system: entities, write paths, agent vs. human routing | `suede-ops-architecture` |\n| Coordinate several agent lanes on one shared change | `suede-agent-teams` |\n| Search competing plans, then build and gate one multi-file change | `suede-graph-flo-xr` |\n| Eval cases and acceptance gates for LLM, RAG, or agent behavior | `suede-ai-eval` |\n| Keep one canonical value identical across web, app, docs, services | `suede-parity-contract` |\n\n**Code and release quality**\n\n| Need | Skill |\n|---|---|\n| Review, grade, or both (`--findings-only`, `--grade-only`); prompted only | `suede-code` |\n| CI jobs, required checks, branch protection | `suede-ci-gate` |\n| Install commands, proof links, release copy, handoff notes | `suede-launch-packaging` |\n\n**Copy and design**\n\n| Need | Skill |\n|---|---|\n| Any copy surface, docs, explainers, agent docs, answer-first SEO pass | `suede-copy` |\n| Strip AI patterns from finished text, or a findings-only slop audit | `suede-deslop` |\n| One high-stakes public piece with research and an adversarial fact audit | `suede-ship-copy` |\n| Read-only whole-flow review or UI diff review; tokens, hierarchy, accessibility, authorized surface builds, restyles and visual QA | `suede-design` |\n| Dev-only component workbench importing real components, synthetic states, stress fixtures and live variants | `suede-component-lab` |\n| Read-only explanation of an interface mechanism, with source locations, state transitions and observed behavior | `suede-interface-explain` |\n| Image and graphic specs | `suede-image` |\n| Video scripts and edits | `suede-video` |\n\nFor an interface request, preserve the requested action. An audit or review is\nread-only; return findings and proposed fixes without editing the application.\nAn explanation traces the existing mechanism without rebuilding it. A component\nlab creates an isolated development preview using the project's real components\nand synthetic fixtures, with no production data, writes or exposed production\nroute. Design work starts from the user's task, primary action and existing\nbrand; visual novelty does not establish task success or conversion improvement.\n\nFor an authorized build from a selected design, screenshot or supplied mock,\nroute to `suede-design`. If an image-to-code capability is already available,\nuse it for that implementation; otherwise use the existing local stack and\ncomponent system. Do not install another skill or tool merely to complete this\nroute. A supplied visual kit may guide the work when explicitly selected, with\nits source and reuse rights recorded; it never silently overrides the product's\nbrand. Source inspection supports source findings, not a rendered visual pass.\n\n**Apps and stores**\n\n| Need | Skill |\n|---|---|\n| Turn a website into an iOS app | `site-to-ios-app` |\n| Build a native Android app to Play Store release | `android-app-factory` |\n| Ship an Android release through the Play Developer API | `suede-play-release` |\n| App Store and Play listing keywords and screenshots | `suede-aso` |\n\n**Growth and marketing** (route to the narrowest match)\n\n| Need | Skill |\n|---|---|\n| Plan or tactic shortlist; loops; multi-role critique | `suede-marketing-plan`; `suede-marketing-loops`; `suede-marketing-council` |\n| Competitor comparison pages; one rival in depth | `suede-competitors`; `suede-competitor-profiling` |\n| Buyer research, positioning, product messaging | `suede-customer-research`, `suede-product-marketing` |\n| Paid strategy; the ad units themselves | `suede-ads`; `suede-ad-creative` |\n| Organic social, including Instagram account audits; content pipeline; clip to guide | `suede-social`; `suede-newsroom`; `suede-clip-to-guide` |\n| Outbound and pipeline | `suede-cold-email`, `suede-prospecting`, `suede-sales-enablement`, `suede-revops` |\n| PR, partners, community, referrals | `suede-public-relations`, `suede-co-marketing`, `suede-community-marketing`, `suede-referrals` |\n| Lifecycle email and SMS | `suede-emails`, `suede-sms` |\n| Lead magnets | `suede-lead-magnets` |\n| Offers and persuasion mechanics, pricing, paywalls | `suede-offers`, `suede-pricing`, `suede-paywalls` |\n| Signup and onboarding; churn | `suede-onboarding`; `suede-churn-prevention` |\n| Analytics, attribution, A\u002FB tests | `suede-analytics`, `suede-attribution`, `suede-ab-testing` |\n\n**Creator and rights**\n\n| Need | Skill |\n|---|---|\n| Full artist campaign | `suede-campaign-in-a-box` |\n| Sync review package (no promo CTA, placement, or clearance claims) | `suede-sync-packaging` |\n| Release folder audit: stems, artwork, lyrics, metadata | `suede-release-linter` |\n| Ownership, split, sample, and license gaps, then the transfer package | `suede-rights-passport` (audit mode, then package) |\n\n### Umbrella-only installs\n\nIf the specialists are not installed (the common Codex path installs this skill\nalone), read `references\u002Fcondensed-workflows.md`: a compact fallback for the\ndesign, copy and SEO, visibility, site, code review, and agent-team workflows.\nWhen the pack is installed, skip it and route to the specialist, which owns\nthe current method. When the work touches copy, design, visual QA, or launch\nquality, also read `references\u002Fno-missed-quality-gates.md`.\n\nInstall commands for Claude Code and Codex, including subsets, are in\n`references\u002Finstall.md`. Read it only when the user asks how to install,\nupdate, or subset the pack. The Suede MCP's `suede_install_options` tool\nanswers the same question live when it is connected.\n\nUse the Suede MCP only when it adds structure: listing skills, explaining\ninstall options, scaffolding an SEO and AEO copy audit, or generating a QA\nchecklist. Skip it for small edits.\n\n## Next move\n\nTriggered by \"what's next\", \"what should I do next\", \"recommend the next\nmove\", \"give me the prompt\", or a stalled task after a review, audit, or plan.\nInspect read-only. Never execute the recommended action unless the user\nseparately authorizes it.\n\n1. **Resolve the target and the done outcome** from the request, conversation,\n   handoff, plan, repo, or live surface.\n2. **Read only what can change the answer**, freshest first: `git -C \u003Crepo>\n   status --short --branch`, `git -C \u003Crepo> log --oneline -5`, the named plan\n   or handoff file at its exact path, and a live check\n   (`curl -sS -o \u002Fdev\u002Fnull -w '%{http_code}' \u003Curl>`) when a public surface is\n   in scope.\n3. **Generate 2 to 4 candidates.** Drop work already verified complete,\n   adjacent cleanup, and anything outside the authorized scope. If the repo\n   already has a plan, issue tracker, or board, treat its recorded next step\n   as one candidate; never create a second tracker.\n4. **Score each 0 to 2 per row** and pick the highest total:\n\n| Criterion | 2 | 1 | 0 |\n|---|---|---|---|\n| Goal alignment | Produces the done signal | Required prerequisite | Adjacent |\n| Unblocking | Clears a core path or 2+ steps | Clears one step | Clears nothing known |\n| Evidence | Confirmed by current source | One read-only check away | Assumption |\n| Urgency | Active failure, deadline, security risk, release gate | Needed this milestone | No pressure |\n| Leverage | One focused session; prevents rework | Bounded, moderate payoff | Unscoped or low payoff |\n\n5. **Break ties** toward the prerequisite, then current-evidence verification,\n   then the more reversible action. Still within one point? Run up to three\n   more read-only checks; if still tied, show both and name the one fact that\n   decides.\n6. **If missing evidence is the real blocker,** the smallest read-only check\n   becomes the recommendation.\n\nOutput:\n\n```text\nRecommended action: \u003Cone sentence>\nWhy now: \u003Cone evidence-backed sentence>\n\nQuick prompt: \u003C2-4 runnable sentences naming the skill, target, outcome, and done signal>\n\nSay \"expand prompt\" for the full operator version or \"make it granular\" for exact steps and commands.\n```\n\nThe expanded and granular prompt formats are in\n`references\u002Fnext-action-prompts.md`; load it only when the user asks for them.\nShow scores, evidence lists, or alternatives only when asked or when the tie\nrule requires them. Never recommend \"keep working\" or \"do more research\": name\na command, artifact, decision, edit, or verification result.\n\n## Closing\n\nAfter meaningful work, close with a one-sentence plain explanation for a\nnon-coder, then Changed \u002F Verification \u002F Caveats \u002F Status, then:\n\n```text\nCue Suede:\n1. Change something: tell me what to revise.\n2. Preserve this: tell me what worked so I can match it.\n3. Keep as-is: say nothing and I will treat it as accepted.\n```\n\nNever block completion waiting for that answer.\n\n## Red flags: stop\n\n- \"I'll summarize the request for the specialist.\" Pass it verbatim.\n- \"This crosses three lanes; faster to do it inline.\" Crossing lanes is when\n  this router earns its place.\n- \"The live URL is probably unchanged.\" Inspect before claiming.\n- \"I'll just do the recommended action too.\" Recommending is read-only.\n\n## Boundaries\n\n- Never expose private paths, credentials, secrets, unreleased assets, or\n  private service details.\n- Never copy protected site assets, exact copy, proprietary code, or\n  trademarked identity during a restyle.\n- Never mark work done until the done signal has been checked or the remaining\n  caveat is named.\n- Never mutate files, repos, deployments, accounts, or messages while\n  recommending a next move.\n",{"name":5,"metadata":50,"description":7},{"display-name":51},"Suede AI Workflow Skills","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills",483,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-13 02:16:32",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill suede-workflow-skills",{"tool":68,"command":69},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill suede-workflow-skills",{"tool":71,"command":72},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill suede-workflow-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002FSKILL.md",true,[76,82,86,90,94,98,102],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"agents\u002Fopenai.yaml","REFERENCE","参考文档",474,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002Fagents\u002Fopenai.yaml",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"CARD.md",4408,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002FCARD.md",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fcondensed-workflows.md",13928,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002Freferences\u002Fcondensed-workflows.md",{"path":91,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Finstall.md",2490,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002Freferences\u002Finstall.md",{"path":95,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fnext-action-prompts.md",2557,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002Freferences\u002Fnext-action-prompts.md",{"path":99,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fno-missed-quality-gates.md",10094,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002Freferences\u002Fno-missed-quality-gates.md",{"path":103,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fworked-handoff.md",1667,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJasonColapietro\u002Fsuede-creator-skills\u002Fskills\u002Fsuede-workflow-skills\u002Freferences\u002Fworked-handoff.md",[107,115,122,129,155,179],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":114},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":114},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":114},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":45},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[136,137,138,139,140,141,142,143,144,145,146,27,147,148,149,150,151,152,153,154],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","you","done","reviewer","io","change","cli","merge","past",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":45},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[162,163,164,150,165,166,167,37,168,169,170,171,172,173,141,174,175,176,177,178],"deja reflect","reflect","review","with","record","github","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":192,"publishedAt":45},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[185,188,189],{"categoryNo":186,"categoryName":187,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":190,"categoryName":191,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[181,193,194,195,196,197,198,175,199,142,200,201,202,203,27,204,205,206,207,208],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]