[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ENFMX0YESRD9ZPTPFQAW91":3,"skill-same:01M7ENFMX0YESRD9ZPTPFQAW91":52},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7ENFMX0YESRD9ZPTPFQAW91","loom-topics",null,"Coordinate bounded work that spans multiple Turns, days, or CodexLoom Agents through a shared Topic. Use when a workstream needs one Responsible Agent, scoped Participants, a versioned current brief, waiting conditions, evidence links, or recovery after time has passed; when receiving loom_topic_context; or when Message, Needs You, Trigger, Goal, Turn, or Artifact work should remain connected without sharing Agent Threads. Do not use for a one-Turn task, a permanent Domain, or a private Agent process.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Floom-topics\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: loom-topics\ndescription: Coordinate bounded work that spans multiple Turns, days, or CodexLoom Agents through a shared Topic. Use when a workstream needs one Responsible Agent, scoped Participants, a versioned current brief, waiting conditions, evidence links, or recovery after time has passed; when receiving loom_topic_context; or when Message, Needs You, Trigger, Goal, Turn, or Artifact work should remain connected without sharing Agent Threads. Do not use for a one-Turn task, a permanent Domain, or a private Agent process.\n---\n\n# Loom Topics\n\nA Topic is a thin shared coordination record for one bounded workstream. It preserves the current brief, responsibility, waiting condition, important evidence, and causal activity while every Agent keeps its detailed work in its own Thread.\n\nA Topic is not a shared model Session, another Goal, a group chat, a task board, or a second source of truth. Provider state, code, artifacts, and Agent Threads remain authoritative for their own facts.\n\n## Decide whether a Topic is warranted\n\nUse a Topic when work has a completion boundary and at least one of these is true:\n\n- it spans multiple Turns or days;\n- it waits on external or human conditions;\n- multiple Agents need a stable shared brief;\n- the Owner needs to recover the work without reconstructing several Threads.\n\nKeep a one-Turn request in the Agent Thread. Keep permanent responsibility in the Agent Profile. Use a Goal for one Agent's long-running execution lifecycle.\n\n## Establish the coordination boundary\n\nCreate one Responsible Agent and only the Participants needed now:\n\n```bash\nloom topic create \\\n  --title \"Parall Clip release closure\" \\\n  --responsible parall-dev-lead \\\n  --purpose \"Coordinate the bounded release stage across Lead, Edge, and Platform.\" \\\n  --completion \"The responsible Agent publishes the verified release-stage result.\" \\\n  --summary \"Candidate facts are being re-verified before the next gate.\" \\\n  --participant 'parall-edge-dev::Own packaged client verification.' \\\n  --participant 'parall-platform-dev::Own deployment and environment evidence.'\n```\n\nThe Responsible Agent owns purpose, scope, Participants, versioned brief, waiting state, and final resolution. A Participant owns only its stated topic-scoped responsibility. The Owner confirms material scope, authorization, and organization changes.\n\nInspect before acting:\n\n```bash\nloom topic list --agent AGENT\nloom topic get TOPIC_ID\n```\n\n## Work through causal links\n\nThe Responsible Agent routes scoped work with the Topic ID:\n\n```bash\nloom msg PARTICIPANT --from RESPONSIBLE --topic TOPIC_ID \\\n  --subject \"Verify the current packaged candidate\" \\\n  --body \"Read current provider facts and return evidence or a blocking condition.\"\n```\n\nParticipants report to the Responsible Agent using the same Topic ID:\n\n```bash\nloom msg RESPONSIBLE --from PARTICIPANT --topic TOPIC_ID \\\n  --subject \"Re: Verify the current packaged candidate\" \\\n  --body \"Current result, limitation, and evidence IDs.\"\n```\n\nDo not send ordinary Topic work to an Agent outside the Topic. Add a Participant with a narrow responsibility first. Do not copy another Agent's full Thread into the Topic.\n\nLink only durable anchors that help recovery:\n\n```bash\nloom topic link TOPIC_ID pull-request OWNER\u002FREPO#1970 \\\n  --from RESPONSIBLE --label \"Historical contract candidate\"\nloom topic link TOPIC_ID artifact ARTIFACT_ID \\\n  --from RESPONSIBLE --label \"Packaged smoke report\"\n```\n\n`loom msg --topic`, `loom ask-user --topic`, and `loom trigger add --topic` create causal Topic activity automatically. Replies inherit the Topic. Use explicit links for external Inbox \u002F Outbox items, Artifacts, provider facts, or an existing native Goal that did not originate inside the Topic. Identify a Goal version as `\u003Cthread-id>@\u003Cgoal-created-at>` because a Thread can receive a later Goal.\n\n## Maintain the shared brief\n\nOnly the Responsible Agent updates the operational brief and publishes results:\n\n```bash\nloom topic update TOPIC_ID --from RESPONSIBLE --if-version VERSION \\\n  --summary \"Current cross-domain conclusion.\" \\\n  --state \"What is true now.\" \\\n  --next \"The first next action.\" \\\n  --limitations \"Known uncertainty.\"\n```\n\nWhen work must wait, record why, the stable reference, and what to do after wake-up:\n\n```bash\nloom topic update TOPIC_ID --from RESPONSIBLE \\\n  --waiting \"Waiting for the target PR to enter main.\" \\\n  --waiting-kind github-pr \\\n  --waiting-ref OWNER\u002FREPO#1970 \\\n  --resume-action \"Re-read main and verify the expected contract.\"\n```\n\nArm the related Trigger with `--topic TOPIC_ID`, then end the Turn. Clear waiting only after re-reading authoritative state.\n\nPublish a stage result only after integrating Participant evidence:\n\n```bash\nloom topic update TOPIC_ID --from RESPONSIBLE --if-version VERSION \\\n  --summary \"Verified stage result.\" --state \"Ready for Owner review.\" --result\nloom topic resolve TOPIC_ID --from RESPONSIBLE\n```\n\nParticipants must not mutate the shared brief or declare the Topic resolved. They return facts, limits, and proposals to the Responsible Agent.\n\n## Handle Owner input and intervention\n\n`loom topic send TOPIC_ID ...` always starts a Turn for the Responsible Agent. Scope, priority, completion, and Participant assignment changes go through that path.\n\nThe Owner may guide or interrupt an exact active Participant Turn from the Topic UI or CLI:\n\n```bash\nloom topic intervene TOPIC_ID --agent PARTICIPANT --action steer --text \"Re-check the current HEAD, not the archived candidate.\"\nloom topic intervene TOPIC_ID --agent PARTICIPANT --action interrupt --reason \"The candidate was superseded.\"\n```\n\nAn intervention is an audited process correction. It does not change Topic status, reassign work, or silently change scope. If it changes the overall plan, the Responsible Agent must update the brief and replan.\n\n## Read supplied context\n\n`\u003Cloom_topic_context>` contains a bounded current brief, your Topic responsibility, waiting state, key links, and activity delta since your last Topic delivery. Treat it as coordination context, not a replacement for current provider reads or your own Thread history. Do not poll the Topic; linked Messages and Triggers resume the right Agent.\n","# Loom Topics\n\nA Topic is a thin shared coordination record for one bounded workstream. It preserves the current brief, responsibility, waiting condition, important evidence, and causal activity while every Agent keeps its detailed work in its own Thread.\n\nA Topic is not a shared model Session, another Goal, a group chat, a task board, or a second source of truth. Provider state, code, artifacts, and Agent Threads remain authoritative for their own facts.\n\n## Decide whether a Topic is warranted\n\nUse a Topic when work has a completion boundary and at least one of these is true:\n\n- it spans multiple Turns or days;\n- it waits on external or human conditions;\n- multiple Agents need a stable shared brief;\n- the Owner needs to recover the work without reconstructing several Threads.\n\nKeep a one-Turn request in the Agent Thread. Keep permanent responsibility in the Agent Profile. Use a Goal for one Agent's long-running execution lifecycle.\n\n## Establish the coordination boundary\n\nCreate one Responsible Agent and only the Participants needed now:\n\n```bash\nloom topic create \\\n  --title \"Parall Clip release closure\" \\\n  --responsible parall-dev-lead \\\n  --purpose \"Coordinate the bounded release stage across Lead, Edge, and Platform.\" \\\n  --completion \"The responsible Agent publishes the verified release-stage result.\" \\\n  --summary \"Candidate facts are being re-verified before the next gate.\" \\\n  --participant 'parall-edge-dev::Own packaged client verification.' \\\n  --participant 'parall-platform-dev::Own deployment and environment evidence.'\n```\n\nThe Responsible Agent owns purpose, scope, Participants, versioned brief, waiting state, and final resolution. A Participant owns only its stated topic-scoped responsibility. The Owner confirms material scope, authorization, and organization changes.\n\nInspect before acting:\n\n```bash\nloom topic list --agent AGENT\nloom topic get TOPIC_ID\n```\n\n## Work through causal links\n\nThe Responsible Agent routes scoped work with the Topic ID:\n\n```bash\nloom msg PARTICIPANT --from RESPONSIBLE --topic TOPIC_ID \\\n  --subject \"Verify the current packaged candidate\" \\\n  --body \"Read current provider facts and return evidence or a blocking condition.\"\n```\n\nParticipants report to the Responsible Agent using the same Topic ID:\n\n```bash\nloom msg RESPONSIBLE --from PARTICIPANT --topic TOPIC_ID \\\n  --subject \"Re: Verify the current packaged candidate\" \\\n  --body \"Current result, limitation, and evidence IDs.\"\n```\n\nDo not send ordinary Topic work to an Agent outside the Topic. Add a Participant with a narrow responsibility first. Do not copy another Agent's full Thread into the Topic.\n\nLink only durable anchors that help recovery:\n\n```bash\nloom topic link TOPIC_ID pull-request OWNER\u002FREPO#1970 \\\n  --from RESPONSIBLE --label \"Historical contract candidate\"\nloom topic link TOPIC_ID artifact ARTIFACT_ID \\\n  --from RESPONSIBLE --label \"Packaged smoke report\"\n```\n\n`loom msg --topic`, `loom ask-user --topic`, and `loom trigger add --topic` create causal Topic activity automatically. Replies inherit the Topic. Use explicit links for external Inbox \u002F Outbox items, Artifacts, provider facts, or an existing native Goal that did not originate inside the Topic. Identify a Goal version as `\u003Cthread-id>@\u003Cgoal-created-at>` because a Thread can receive a later Goal.\n\n## Maintain the shared brief\n\nOnly the Responsible Agent updates the operational brief and publishes results:\n\n```bash\nloom topic update TOPIC_ID --from RESPONSIBLE --if-version VERSION \\\n  --summary \"Current cross-domain conclusion.\" \\\n  --state \"What is true now.\" \\\n  --next \"The first next action.\" \\\n  --limitations \"Known uncertainty.\"\n```\n\nWhen work must wait, record why, the stable reference, and what to do after wake-up:\n\n```bash\nloom topic update TOPIC_ID --from RESPONSIBLE \\\n  --waiting \"Waiting for the target PR to enter main.\" \\\n  --waiting-kind github-pr \\\n  --waiting-ref OWNER\u002FREPO#1970 \\\n  --resume-action \"Re-read main and verify the expected contract.\"\n```\n\nArm the related Trigger with `--topic TOPIC_ID`, then end the Turn. Clear waiting only after re-reading authoritative state.\n\nPublish a stage result only after integrating Participant evidence:\n\n```bash\nloom topic update TOPIC_ID --from RESPONSIBLE --if-version VERSION \\\n  --summary \"Verified stage result.\" --state \"Ready for Owner review.\" --result\nloom topic resolve TOPIC_ID --from RESPONSIBLE\n```\n\nParticipants must not mutate the shared brief or declare the Topic resolved. They return facts, limits, and proposals to the Responsible Agent.\n\n## Handle Owner input and intervention\n\n`loom topic send TOPIC_ID ...` always starts a Turn for the Responsible Agent. Scope, priority, completion, and Participant assignment changes go through that path.\n\nThe Owner may guide or interrupt an exact active Participant Turn from the Topic UI or CLI:\n\n```bash\nloom topic intervene TOPIC_ID --agent PARTICIPANT --action steer --text \"Re-check the current HEAD, not the archived candidate.\"\nloom topic intervene TOPIC_ID --agent PARTICIPANT --action interrupt --reason \"The candidate was superseded.\"\n```\n\nAn intervention is an audited process correction. It does not change Topic status, reassign work, or silently change scope. If it changes the overall plan, the Responsible Agent must update the brief and replan.\n\n## Read supplied context\n\n`\u003Cloom_topic_context>` contains a bounded current brief, your Topic responsibility, waiting state, key links, and activity delta since your last Topic delivery. Treat it as coordination context, not a replacement for current provider reads or your own Thread history. Do not poll the Topic; linked Messages and Triggers resume the right Agent.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Floom-topics",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill loom-topics",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill loom-topics",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill loom-topics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Floom-topics\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",261,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Floom-topics\u002Fagents\u002Fopenai.yaml",[53,61,66,73,80,87],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":60},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":62,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":60},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":60},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\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":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":60},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":60},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":60},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]