[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MGR387ATHRQG6X321GRH7P":3,"skill-same:01M6MGR387ATHRQG6X321GRH7P":74},{"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":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6MGR387ATHRQG6X321GRH7P","deepseek-minimal-anchor",null,"DeepSeek mini-router working contract. When the active model is a DeepSeek model (deepseek-v4-pro or deepseek-v4-flash), READ this skill and follow its working contract automatically before the first tool call. Also use when the user asks for minimal mode, less chatter, the anchored working contract, task-aware reasoning modes, or to verify whether the anchor engaged.","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\u002Fhccccc01333\u002Fcodex-deepseek-mini-router\u002Fplugins\u002Fdeepseek-minimal-anchor\u002Fskills\u002Fminimal-anchor\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"deepseek minimal anchor","minimal","anchor","deepseek","call","when","modes","for","mode","chatter","contract","active","reasoning","task","router","use","read","model","tool","verify","first","2026-11-10 10:12:30",false,"---\nname: deepseek-minimal-anchor\ndescription: DeepSeek mini-router working contract. When the active model is a DeepSeek model (deepseek-v4-pro or deepseek-v4-flash), READ this skill and follow its working contract automatically before the first tool call. Also use when the user asks for minimal mode, less chatter, the anchored working contract, task-aware reasoning modes, or to verify whether the anchor engaged.\n---\n\n# DeepSeek Mini-Router (working contract)\n\nThis contract applies automatically when the active model is a DeepSeek model\n(`deepseek-v4-pro` \u002F `deepseek-v4-flash`). Do not wait for the user to ask:\nadopt the mode below before the first tool call. For non-DeepSeek models this\nskill is inert.\n\n## Mode selection (first user message)\n\nPick one mode from the model and lock it for the session; do not flip\nmid-session:\n\n- `pro` - always for `deepseek-v4-pro`: **Minimal anchor**. The injected\n  contract is exactly the official Minimal system prompt: `You are a helpful\n  software engineer assistant.` Keep it to that one sentence; Pro gets no\n  per-turn guidance.\n- `flash` - always for `deepseek-v4-flash`: **decide & verify router** -\n  decide the task type (build or fix) in one step, keep reasoning concise, end\n  each reasoning block with a decision or an information need, run a concrete\n  check after writing code, and retry once on failure (no environment checks).\n- Env-forced `spec` \u002F `react` modes remain experimental escape hatches\n  (`DEEPSEEK_MINIMAL_ANCHOR_MODE`), not the default Pro path.\n\n## Working contract\n\n- Keep diagnosis and progress in internal reasoning. Make visible replies only\n  when the work is finished or you genuinely need input.\n- `pro`: stay on the one-sentence Minimal anchor; do not add extra contracts.\n- `flash`: decide the task type (build or fix) in one step and act; keep\n  reasoning concise and end each reasoning block with a decision or an\n  information need; after writing code run a concrete check; if it fails, read\n  the complete error, fix the cause, and retry once - do not loop or re-confirm\n  the environment (`echo`, `whoami`, `uname`, `pwd`).\n- When a check or build fails, read the complete error - including its middle\n  sections - before retrying; fix the cause, not the symptom.\n- Verify each change with the relevant checks before declaring completion.\n- Finish with a short summary: what changed, what you verified, what risks\n  remain.\n\n## Per-turn guidance\n\n- Simple tasks: fast convergence - verify through tool calls, keep narration\n  internal, finish with the changed \u002F verified \u002F risks summary.\n- Complex tasks (long messages or architecture keywords: `architecture`,\n  `module`, `integrat`, `distributed`, `pipeline`, `database`, `架构`, `模块`,\n  `集成`, `分布式`): also think deeply about architecture, edge cases, and\n  integration points; do not spend reasoning on the environment or tooling;\n  end each reasoning block with a decision or an information need.\n\n## Verification and channel notice\n\n- The audit trail lives in `~\u002F.codex\u002Fdeepseek-minimal-anchor-reports\u002F`\n  (`hook-log.jsonl`, `session-modes.json`).\n- Hooks inject this same contract as developer context on desktop and CLI once\n  trusted (stronger). Trust is hash-keyed: after a plugin update, re-trust the\n  current hook definition, then start a new thread.\n- If a session has no hook entries (hooks not trusted yet, or a build without\n  hook support), this skill is the active channel - follow the contract anyway.\n- If the user asks whether the mini-router is active, answer from the audit\n  trail: report the locked mode and source, or state that the hook channel is\n  off and the skill channel is carrying the mode.\n- Once per session, if this session clearly has no hook entries, briefly tell\n  the user which channel is active (one or two sentences), so \"installed but\n  silently off\" cannot happen.\n\n## Honest limitations\n\n- Skill-level anchoring is directive, not enforced developer context; hook\n  injection (CLI) has higher priority when both exist.\n- Wording is a trajectory fingerprint, not a capability proof; measured gains\n  so far: Flash router 10\u002F12 vs Flash baseline 8\u002F12 on a 6-task BigCodeBench\n  subset (n=2), Pro router matches baseline and avoids static-spec losses.\n","# DeepSeek Mini-Router (working contract)\n\nThis contract applies automatically when the active model is a DeepSeek model\n(`deepseek-v4-pro` \u002F `deepseek-v4-flash`). Do not wait for the user to ask:\nadopt the mode below before the first tool call. For non-DeepSeek models this\nskill is inert.\n\n## Mode selection (first user message)\n\nPick one mode from the model and lock it for the session; do not flip\nmid-session:\n\n- `pro` - always for `deepseek-v4-pro`: **Minimal anchor**. The injected\n  contract is exactly the official Minimal system prompt: `You are a helpful\n  software engineer assistant.` Keep it to that one sentence; Pro gets no\n  per-turn guidance.\n- `flash` - always for `deepseek-v4-flash`: **decide & verify router** -\n  decide the task type (build or fix) in one step, keep reasoning concise, end\n  each reasoning block with a decision or an information need, run a concrete\n  check after writing code, and retry once on failure (no environment checks).\n- Env-forced `spec` \u002F `react` modes remain experimental escape hatches\n  (`DEEPSEEK_MINIMAL_ANCHOR_MODE`), not the default Pro path.\n\n## Working contract\n\n- Keep diagnosis and progress in internal reasoning. Make visible replies only\n  when the work is finished or you genuinely need input.\n- `pro`: stay on the one-sentence Minimal anchor; do not add extra contracts.\n- `flash`: decide the task type (build or fix) in one step and act; keep\n  reasoning concise and end each reasoning block with a decision or an\n  information need; after writing code run a concrete check; if it fails, read\n  the complete error, fix the cause, and retry once - do not loop or re-confirm\n  the environment (`echo`, `whoami`, `uname`, `pwd`).\n- When a check or build fails, read the complete error - including its middle\n  sections - before retrying; fix the cause, not the symptom.\n- Verify each change with the relevant checks before declaring completion.\n- Finish with a short summary: what changed, what you verified, what risks\n  remain.\n\n## Per-turn guidance\n\n- Simple tasks: fast convergence - verify through tool calls, keep narration\n  internal, finish with the changed \u002F verified \u002F risks summary.\n- Complex tasks (long messages or architecture keywords: `architecture`,\n  `module`, `integrat`, `distributed`, `pipeline`, `database`, `架构`, `模块`,\n  `集成`, `分布式`): also think deeply about architecture, edge cases, and\n  integration points; do not spend reasoning on the environment or tooling;\n  end each reasoning block with a decision or an information need.\n\n## Verification and channel notice\n\n- The audit trail lives in `~\u002F.codex\u002Fdeepseek-minimal-anchor-reports\u002F`\n  (`hook-log.jsonl`, `session-modes.json`).\n- Hooks inject this same contract as developer context on desktop and CLI once\n  trusted (stronger). Trust is hash-keyed: after a plugin update, re-trust the\n  current hook definition, then start a new thread.\n- If a session has no hook entries (hooks not trusted yet, or a build without\n  hook support), this skill is the active channel - follow the contract anyway.\n- If the user asks whether the mini-router is active, answer from the audit\n  trail: report the locked mode and source, or state that the hook channel is\n  off and the skill channel is carrying the mode.\n- Once per session, if this session clearly has no hook entries, briefly tell\n  the user which channel is active (one or two sentences), so \"installed but\n  silently off\" cannot happen.\n\n## Honest limitations\n\n- Skill-level anchoring is directive, not enforced developer context; hook\n  injection (CLI) has higher priority when both exist.\n- Wording is a trajectory fingerprint, not a capability proof; measured gains\n  so far: Flash router 10\u002F12 vs Flash baseline 8\u002F12 on a 6-task BigCodeBench\n  subset (n=2), Pro router matches baseline and avoids static-spec losses.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fhccccc01333\u002Fcodex-deepseek-mini-router\u002Fplugins\u002Fdeepseek-minimal-anchor\u002Fskills\u002Fminimal-anchor",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":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill deepseek-minimal-anchor",{"tool":66,"command":67},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill deepseek-minimal-anchor",{"tool":69,"command":70},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill deepseek-minimal-anchor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fhccccc01333\u002Fcodex-deepseek-mini-router\u002Fplugins\u002Fdeepseek-minimal-anchor\u002Fskills\u002Fminimal-anchor\u002FSKILL.md",true,[],[75,85,93,101,109,117],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":84},"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":84},"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":84},"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":84},"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":84},"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":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":84},"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",[],[]]