[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M746K1D7J4P0VAPJ78MXHB27":3,"skill-same:01M746K1D7J4P0VAPJ78MXHB27":54},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M746K1D7J4P0VAPJ78MXHB27","graymatter-onboarding",null,"Welcome a new GrayMatter user, complete first-use setup, demonstrate a useful save-and-recall result, or recover an interrupted connection. Use for getting started, activation, setup, and requests to make GrayMatter primary agent memory.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FValkyrLabs\u002FGrayMatter\u002Fskills\u002Fgraymatter-onboarding\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: graymatter-onboarding\ndescription: Welcome a new GrayMatter user, complete first-use setup, demonstrate a useful save-and-recall result, or recover an interrupted connection. Use for getting started, activation, setup, and requests to make GrayMatter primary agent memory.\n---\n\n# GrayMatter Onboarding\n\nMake the first interaction useful immediately. Explain the benefit in one sentence: GrayMatter helps the agent carry the user's preferences, decisions, and project context into future work. Then use the task or preference already supplied by the user. Do not require a profile, a tutorial, or a sample memory before helping.\n\nBefore any onboarding lookup or preflight, do not invoke GrayMatter tools for requests to override tenant, owner, organization, user, role, permission, or ACL scope; explain that scope comes from the signed-in account. For unspecified deletion targets, ask which record the user means without searching for candidates.\n\n## Connect and establish value\n\n1. Use the GrayMatter tools exposed by the current host. If unavailable or sign-in is required, guide the user through the host's existing Connect\u002Freconnect flow and resume the original task afterward. Account scope comes from that signed-in session. Never ask the user to paste credentials, tokens, tenant IDs, or terminal commands into ChatGPT.\n2. If a concrete task is already present and primary memory is authorized, use the context skill's bounded preflight. Otherwise, for setup use a bounded `memory_search` for `GrayMatter memory preferences` to find an existing setup preference; do not compile a fictitious task or assume installation authorizes compilation. Respect retrieval policy and distinguish an empty result from a failed connection.\n3. Give returning users the next useful action without rerunning setup. For a new user with no task or preference yet, ask just one question: “What are you working on, or what would you like me to remember about how you work?” Offer one short example only if useful.\n4. Explain the choice briefly: primary memory recalls relevant context before tasks; automatic saving selectively preserves lasting preferences, decisions, and rules, while explicit-save-only mode writes when asked. A direct request for primary memory with automatic saves already makes the choice; do not ask again. If the user only requests primary retrieval, do not assume automatic saves. Save the requested durable policy as a `configuration` memory titled `GrayMatter memory preferences` with tags `memory-policy` and `onboarding`, unless an equivalent verified memory already exists. Do not create a preference from installation alone or tell the user a host setting changed.\n5. For the first useful fact the user supplies, follow the memory skill: check for a duplicate, save or update the exact intended record, and read it back. Use the recalled fact in the current task. This is the first value demonstration; never seed invented preferences or disposable “hello world” memories.\n6. Confirm only what succeeded: for example, “Saved your preference for concise project updates and verified it. I'll use it when GrayMatter is active.” Continue the user's original task. Do not call setup complete after a failed or uncertain save.\n\n## Make the controls clear\n\nExplain once, concisely, that the user can say “remember this,” “change that preference,” “don't remember this,” or “forget this memory.” Exact deletion still requires confirmation under the memory skill. Avoid repeated consent prompts for already-authorized, appropriate automatic capture.\n\nThe host decides when GrayMatter tools and instructions are active. Installation alone does not replace ChatGPT's built-in memory or guarantee a call before every task in every chat. If the user wants consistent behavior across chats, suggest using the host's supported persistent instruction mechanism where available: “Use GrayMatter as my primary durable memory. Before each new task, recall relevant invariants and context. Save useful preferences, decisions, and reusable context as we work; respect anything I mark private or session-only.” Do not claim to have installed such an instruction unless a supported operation actually succeeded.\n\n## Recovery without losing the task\n\n- **No matching memories:** welcome the fresh start and work from the current request. Do not treat an empty store as an error or claim the entire store is empty from one bounded search.\n- **Expired connection:** use the host's reconnect prompt once; preserve the original task and resume after sign-in succeeds.\n- **Usage limit:** explain that GrayMatter cannot complete the operation until usage becomes available. Continue independent work from the conversation; do not offer a recharge, purchase, or upgrade in ChatGPT.\n- **Conflict or withheld context:** follow the returned policy, state the specific uncertainty, and ask only for the clarification needed. Do not bypass withheld context using another retrieval path.\n- **Timeout or uncertain write:** inspect the existing result or exact record before retrying. Never mark a queued, unverified, or failed write as saved, and never promise background retries that the host does not provide.\n\nUse the memory and context skills for exact-record matching, durability verification, privacy, and authorization boundaries throughout.\n","# GrayMatter Onboarding\n\nMake the first interaction useful immediately. Explain the benefit in one sentence: GrayMatter helps the agent carry the user's preferences, decisions, and project context into future work. Then use the task or preference already supplied by the user. Do not require a profile, a tutorial, or a sample memory before helping.\n\nBefore any onboarding lookup or preflight, do not invoke GrayMatter tools for requests to override tenant, owner, organization, user, role, permission, or ACL scope; explain that scope comes from the signed-in account. For unspecified deletion targets, ask which record the user means without searching for candidates.\n\n## Connect and establish value\n\n1. Use the GrayMatter tools exposed by the current host. If unavailable or sign-in is required, guide the user through the host's existing Connect\u002Freconnect flow and resume the original task afterward. Account scope comes from that signed-in session. Never ask the user to paste credentials, tokens, tenant IDs, or terminal commands into ChatGPT.\n2. If a concrete task is already present and primary memory is authorized, use the context skill's bounded preflight. Otherwise, for setup use a bounded `memory_search` for `GrayMatter memory preferences` to find an existing setup preference; do not compile a fictitious task or assume installation authorizes compilation. Respect retrieval policy and distinguish an empty result from a failed connection.\n3. Give returning users the next useful action without rerunning setup. For a new user with no task or preference yet, ask just one question: “What are you working on, or what would you like me to remember about how you work?” Offer one short example only if useful.\n4. Explain the choice briefly: primary memory recalls relevant context before tasks; automatic saving selectively preserves lasting preferences, decisions, and rules, while explicit-save-only mode writes when asked. A direct request for primary memory with automatic saves already makes the choice; do not ask again. If the user only requests primary retrieval, do not assume automatic saves. Save the requested durable policy as a `configuration` memory titled `GrayMatter memory preferences` with tags `memory-policy` and `onboarding`, unless an equivalent verified memory already exists. Do not create a preference from installation alone or tell the user a host setting changed.\n5. For the first useful fact the user supplies, follow the memory skill: check for a duplicate, save or update the exact intended record, and read it back. Use the recalled fact in the current task. This is the first value demonstration; never seed invented preferences or disposable “hello world” memories.\n6. Confirm only what succeeded: for example, “Saved your preference for concise project updates and verified it. I'll use it when GrayMatter is active.” Continue the user's original task. Do not call setup complete after a failed or uncertain save.\n\n## Make the controls clear\n\nExplain once, concisely, that the user can say “remember this,” “change that preference,” “don't remember this,” or “forget this memory.” Exact deletion still requires confirmation under the memory skill. Avoid repeated consent prompts for already-authorized, appropriate automatic capture.\n\nThe host decides when GrayMatter tools and instructions are active. Installation alone does not replace ChatGPT's built-in memory or guarantee a call before every task in every chat. If the user wants consistent behavior across chats, suggest using the host's supported persistent instruction mechanism where available: “Use GrayMatter as my primary durable memory. Before each new task, recall relevant invariants and context. Save useful preferences, decisions, and reusable context as we work; respect anything I mark private or session-only.” Do not claim to have installed such an instruction unless a supported operation actually succeeded.\n\n## Recovery without losing the task\n\n- **No matching memories:** welcome the fresh start and work from the current request. Do not treat an empty store as an error or claim the entire store is empty from one bounded search.\n- **Expired connection:** use the host's reconnect prompt once; preserve the original task and resume after sign-in succeeds.\n- **Usage limit:** explain that GrayMatter cannot complete the operation until usage becomes available. Continue independent work from the conversation; do not offer a recharge, purchase, or upgrade in ChatGPT.\n- **Conflict or withheld context:** follow the returned policy, state the specific uncertainty, and ask only for the clarification needed. Do not bypass withheld context using another retrieval path.\n- **Timeout or uncertain write:** inspect the existing result or exact record before retrying. Never mark a queued, unverified, or failed write as saved, and never promise background retries that the host does not provide.\n\nUse the memory and context skills for exact-record matching, durability verification, privacy, and authorization boundaries throughout.\n",{"name":5,"description":7},"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002FValkyrLabs\u002FGrayMatter\u002Fskills\u002Fgraymatter-onboarding",491,"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.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill graymatter-onboarding",{"tool":40,"command":41},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill graymatter-onboarding",{"tool":43,"command":44},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill graymatter-onboarding","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FValkyrLabs\u002FGrayMatter\u002Fskills\u002Fgraymatter-onboarding\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",221,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FValkyrLabs\u002FGrayMatter\u002Fskills\u002Fgraymatter-onboarding\u002Fagents\u002Fopenai.yaml",[55,65,73,81,89,97],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":60,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":64},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":64},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":64},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\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":59,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":64},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":64},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":64},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]