[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78D6WGT3WA2ACTABNTPYSY3":3,"skill-same:01M78D6WGT3WA2ACTABNTPYSY3":57},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M78D6WGT3WA2ACTABNTPYSY3","delegated-intelligence",null,"Delegate independent work through bounded briefs, owned outputs and checked handbacks. Use when real workers help; keep small or tightly coupled work direct.","JRichlen\u002Fagent-plugins","JRichlen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9574264?v=4","01M78D3QWDTGRFSC2A9XADS6GM","Jordan Richlen","01M78D3QX3W2ZQEEACQHKDX3HW",1,"MIT","https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdelegated-intelligence\u002Fskills\u002Fdelegated-intelligence\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: delegated-intelligence\ndescription: >-\n  Delegate independent work through bounded briefs, owned outputs and checked handbacks. Use when real workers help; keep small or tightly coupled work direct.\nlicense: MIT\ncompatibility: >-\n  PORTABILITY: prose and files; real dispatch requires a worker tool.\n  Without one, work directly and label any sequential pass honestly.\n  Independent verification cannot be simulated by changing roles in one pass.\n---\n\n# Delegate work\n\nThis service owns dispatch, briefs, output ownership, integration and recovery\nfor a selected unit of work. It does not take over the assistant's identity or\nown the project plan. Shared authority, interaction and task-state rules live in\n[the operating contract](..\u002F..\u002Fcontext\u002FOPERATING.md), generated from the\nrepository's canonical core. Do not edit that packaged copy.\n\n## Invariant\n\nEvery dispatched job has a bounded, self-contained brief and an output owner.\nA returned report is checked against artifacts and acceptance evidence before\nthe work is relied upon. No assignment ends with unaccounted workers.\n\n## Entry and exit\n\nUse when the task benefits from independent work or an additional qualified\nworker, the inputs and permitted effects can be bounded, and a real worker\ntool is available. Keep small or tightly coupled work direct when a brief and\nintegration would cost more than the work.\n\nExit after every assignment is reconciled as returned, verified, blocked or\nstopped under the core state contract. Return evidence, gaps and the next action\nto the calling method. Do not leave a coordination persona, background observer,\ndashboard requirement or schedule active after that unit ends.\n\n## Assign\n\n1. Reuse the current task\u002Fproject record. Wayfinder owns persistent plans;\n   [context-handoff](..\u002F..\u002F..\u002Fcontext-handoff\u002Fskills\u002Fcontext-handoff\u002FSKILL.md)\n   owns phase-boundary continuation. Do not create another planning board.\n2. Write the [delegation brief](references\u002Ftemplates.md) before dispatch:\n   objective, source context, scope, configured model\u002Feffort, tools and effects,\n   operational allowance, output path\u002Fowner, return cap, acceptance and stop\n   conditions. Workers return blockers to the main assistant.\n3. Allocate against the whole cycle: coordinator, workers, review, retries,\n   duplicated context and handoffs. Reserve room for integration. State unknown\n   monetary cost rather than inventing it; an estimate is not an enforced cap.\n   Preserve configured provider\u002Fmodel choices.\n4. Give workers only the tools needed for the assignment. Workers never receive\n   agent-spawning or session-control tools, including scheduling, messaging and\n   connectors that send or spend. The main assistant performs those actions\n   under the core authority contract.\n5. Fan out independent assignments with disjoint output ownership. Shared inputs\n   are read-only; do not launch downstream work before its dependencies exist.\n   Assign one integrator for shared\u002Fderived files.\n\n## Hand back and integrate\n\nWorkers write partial artifacts as useful work lands and return a short brief\nwith source\u002Fevidence pointers. Do not flood the main context with raw transcripts.\nThe worker reports `returned`; it cannot declare the coordinator's check complete.\n\nInspect the actual output: existence, non-empty content, expected change and a\ndiff for unrelated edits. Then check the acceptance condition. A complete file\nor a worker's confidence does not establish semantic correctness. Use\n[verify-before-claim](..\u002F..\u002F..\u002Fverify-before-claim\u002Fskills\u002Fverify-before-claim\u002FSKILL.md)\nfor evidence behind a completion claim; use an independent check only when\nrequired and actually available.\n\nUpdate the existing record with the core state and evidence. Share material\nchanges, blockers and needed decisions from that record. Attribute reported\nfindings and distinguish them from checks performed directly.\n\n## Recover or stop\n\nRead [recovery](references\u002Frecovery.md) when output is missing, invalid, stale\nor interrupted. Preserve valid outputs; invalidate downstream work only when\nit consumed an invalid dependency. Include the previous failure in a retry brief.\n\n[stop-rule](..\u002F..\u002F..\u002Fstop-rule\u002Fskills\u002Fstop-rule\u002FSKILL.md) owns retry accounting,\nbounds and stop reports. This service supplies no second retry quota. A user\nstop takes precedence over recovery: stop dispatching, account for in-flight\nactions and uncertain outcomes, preserve results, and return control.\n\nLearning proposals belong to recurrence-detector and existing decision records.\nThis service does not schedule follow-ups or adopt instruction changes.\n","# Delegate work\n\nThis service owns dispatch, briefs, output ownership, integration and recovery\nfor a selected unit of work. It does not take over the assistant's identity or\nown the project plan. Shared authority, interaction and task-state rules live in\n[the operating contract](..\u002F..\u002Fcontext\u002FOPERATING.md), generated from the\nrepository's canonical core. Do not edit that packaged copy.\n\n## Invariant\n\nEvery dispatched job has a bounded, self-contained brief and an output owner.\nA returned report is checked against artifacts and acceptance evidence before\nthe work is relied upon. No assignment ends with unaccounted workers.\n\n## Entry and exit\n\nUse when the task benefits from independent work or an additional qualified\nworker, the inputs and permitted effects can be bounded, and a real worker\ntool is available. Keep small or tightly coupled work direct when a brief and\nintegration would cost more than the work.\n\nExit after every assignment is reconciled as returned, verified, blocked or\nstopped under the core state contract. Return evidence, gaps and the next action\nto the calling method. Do not leave a coordination persona, background observer,\ndashboard requirement or schedule active after that unit ends.\n\n## Assign\n\n1. Reuse the current task\u002Fproject record. Wayfinder owns persistent plans;\n   [context-handoff](..\u002F..\u002F..\u002Fcontext-handoff\u002Fskills\u002Fcontext-handoff\u002FSKILL.md)\n   owns phase-boundary continuation. Do not create another planning board.\n2. Write the [delegation brief](references\u002Ftemplates.md) before dispatch:\n   objective, source context, scope, configured model\u002Feffort, tools and effects,\n   operational allowance, output path\u002Fowner, return cap, acceptance and stop\n   conditions. Workers return blockers to the main assistant.\n3. Allocate against the whole cycle: coordinator, workers, review, retries,\n   duplicated context and handoffs. Reserve room for integration. State unknown\n   monetary cost rather than inventing it; an estimate is not an enforced cap.\n   Preserve configured provider\u002Fmodel choices.\n4. Give workers only the tools needed for the assignment. Workers never receive\n   agent-spawning or session-control tools, including scheduling, messaging and\n   connectors that send or spend. The main assistant performs those actions\n   under the core authority contract.\n5. Fan out independent assignments with disjoint output ownership. Shared inputs\n   are read-only; do not launch downstream work before its dependencies exist.\n   Assign one integrator for shared\u002Fderived files.\n\n## Hand back and integrate\n\nWorkers write partial artifacts as useful work lands and return a short brief\nwith source\u002Fevidence pointers. Do not flood the main context with raw transcripts.\nThe worker reports `returned`; it cannot declare the coordinator's check complete.\n\nInspect the actual output: existence, non-empty content, expected change and a\ndiff for unrelated edits. Then check the acceptance condition. A complete file\nor a worker's confidence does not establish semantic correctness. Use\n[verify-before-claim](..\u002F..\u002F..\u002Fverify-before-claim\u002Fskills\u002Fverify-before-claim\u002FSKILL.md)\nfor evidence behind a completion claim; use an independent check only when\nrequired and actually available.\n\nUpdate the existing record with the core state and evidence. Share material\nchanges, blockers and needed decisions from that record. Attribute reported\nfindings and distinguish them from checks performed directly.\n\n## Recover or stop\n\nRead [recovery](references\u002Frecovery.md) when output is missing, invalid, stale\nor interrupted. Preserve valid outputs; invalidate downstream work only when\nit consumed an invalid dependency. Include the previous failure in a retry brief.\n\n[stop-rule](..\u002F..\u002F..\u002Fstop-rule\u002Fskills\u002Fstop-rule\u002FSKILL.md) owns retry accounting,\nbounds and stop reports. This service supplies no second retry quota. A user\nstop takes precedence over recovery: stop dispatching, account for in-flight\nactions and uncertain outcomes, preserve results, and return control.\n\nLearning proposals belong to recurrence-detector and existing decision records.\nThis service does not schedule follow-ups or adopt instruction changes.\n",{"name":5,"license":15,"description":7,"compatibility":24},"PORTABILITY: prose and files; real dispatch requires a worker tool. Without one, work directly and label any sequential pass honestly. Independent verification cannot be simulated by changing roles in one pass.","main","929887017aa19a575de99be4e3f9b78d0d7ad48d","plugins\u002Fdelegated-intelligence\u002Fskills\u002Fdelegated-intelligence",0,"https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins","https:\u002F\u002Fgithub.com\u002FJRichlen","Solutions Architect","2026-11-12 14:00:54",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add JRichlen\u002Fagent-plugins --skill delegated-intelligence",{"tool":39,"command":40},"bunx","bunx skills add JRichlen\u002Fagent-plugins --skill delegated-intelligence",{"tool":42,"command":43},"pnpm","pnpm dlx skills add JRichlen\u002Fagent-plugins --skill delegated-intelligence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdelegated-intelligence\u002Fskills\u002Fdelegated-intelligence\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Frecovery.md","REFERENCE","参考文档",1762,"https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdelegated-intelligence\u002Fskills\u002Fdelegated-intelligence\u002Freferences\u002Frecovery.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftemplates.md",2406,"https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdelegated-intelligence\u002Fskills\u002Fdelegated-intelligence\u002Freferences\u002Ftemplates.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M78DCJ7N0S5GVNPR0849HPRA","wayfinder","Chart a multi-session effort as a labeled map of typed decision tickets (grilling \u002F prototype \u002F research \u002F task) with explicit dependencies and an open frontier agents self-assign into. Plans; never executes. Use this skill whenever the user is working with wayfinder, and on phrases like \"chart this effort\", \"break this into tickets\", \"what's the frontier\", \"plan across sessions\", or \"map out the dependencies for this work\".","https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fwayfinder\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M78DCB8APFG6B3G7D34WZ2H9","wave-research","Staged, adversarial research that tries to break a thesis before believing it: waves, checkpoints, falsifiable sub-claims, rival hypotheses, an ACH matrix, source-incentive tags and a verified final thesis. Also carries Workflow templates for a one-pass research-and-verify fan-out. Use to stress-test or vet a contested claim; not for quick lookups.","https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fwave-research\u002Fskills\u002Fwave-research\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M78DC30012WTD0B2T21ZFVFG","second-opinion","Offer-only validation pipeline for a verdict or recommendation. Use when the user asks to validate, verify, fact-check, or get a second opinion on a claim or recommendation — \"are you sure\", \"double-check this\", \"second opinion\". Batches fact-checking against sources, adds scoped advisor personas for the angles that need judgment, then re-emits the response grouped into verified, flagged, and conflict, with a mandatory validation delta. Requires a subagent-spawning tool; without one it must decline rather than simulate.","https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvoice\u002Fskills\u002Fsecond-opinion\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M78DBTTZAK0Z8FZ7RCFX92NM","machine-voice","Compression rules for standalone machine-read artifacts the reader scans — agent traces, tool-call logs, status lines, progress updates, handoff notes, state dumps, config, schemas, reference cards, and structured data another agent parses. Applies three layers: lexical compression, markdown structure as navigation, and emojis as typed status markers. Reach for it when emitting one of those artifacts on its own. Companion to human-voice, which governs prose a human reads and also owns any table or block that serves surrounding explanation. Neither skill applies to code or file contents the user will save, commit messages, creative writing, or turns that are only a clarifying question — those ship unstyled and uncompressed.","https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvoice\u002Fskills\u002Fmachine-voice\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M78DBH7MPRD7ZNKVRA6JK76S","human-voice","Style for prose a human reads — answers, recommendations, explanations, research summaries, comparisons. Use on every conversational reply that contains prose for a person to read: triage intent, lead with the verdict, keep it scannable, tag claim confidence. Reach for it whenever answering a technical question, comparing options, or making a recommendation, even when the user says nothing about style. Companion to machine-voice, which instead governs standalone machine-read artifacts — agent traces, tool-call logs, status lines, progress updates, handoff notes, state dumps, config, schemas, reference cards, and structured data another agent parses. Neither skill applies to code or file contents, commit messages, creative writing, or turns that are only a clarifying question — those ship unstyled.","https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvoice\u002Fskills\u002Fhuman-voice\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":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M78DB9587AD3Y46FYVE2V3T4","ai-writing-mistakes","Catch and repair the tells that mark prose as machine-written — the negation-flip (\"it's not X, it's Y\"), rule-of-three padding, hedge stacking, unearned intensifiers, filler verbs like delve and leverage, participle trailers (\"...ensuring seamless integration\"), sycophantic openers, empty closing summaries, and uniform em-dash\u002Fsentence rhythm. Use when drafting or revising any prose a human will read, including documents you were asked to author — READMEs, docs, PR bodies, release notes, emails — and when the user asks whether something \"sounds like AI\" or wants writing tightened. This is a wording pass, not a voice: human-voice still decides layout and confidence tags, machine-voice still owns traces and logs, and neither this skill nor those two touch code, commit messages, or quoted text.","https:\u002F\u002Fgithub.com\u002FJRichlen\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvoice\u002Fskills\u002Fai-writing-mistakes\u002FSKILL.md",[],[]]