[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D73DKHHYYMFNP7MAEHERHC":3,"skill-same:01M7D73DKHHYYMFNP7MAEHERHC":70},{"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":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7D73DKHHYYMFNP7MAEHERHC","amend-workitems",null,"Analyze user instructions and safely amend an entire work-item tree in the selected tracker. Use when a user supplies corrections or adjustments for an Epic or Feature and expects the Epic, Features, User Stories, and child Tasks to be scanned, placed, reviewed, and updated consistently. This skill gathers and presents a change set before any write, creates a recoverable tree backup, and never changes work items without explicit approval.","Monolith-INC\u002Fmonolithic-dev-harness","Monolith-INC","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235230192?v=4","01M75C94857P7W1N13N4K4E016","Monolith INC","01M7D737W93VBSP0P111E1AJ7M",1,"MIT","https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Famend-workitems\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: amend-workitems\ndescription: >\n  Analyze user instructions and safely amend an entire work-item tree in the selected tracker. Use when a user supplies corrections or adjustments for an Epic or Feature and expects the Epic, Features, User Stories, and child Tasks to be scanned, placed, reviewed, and updated consistently. This skill gathers and presents a change set before any write, creates a recoverable tree backup, and never changes work items without explicit approval.\nlicense: MIT\n---\n\n# Amend Work Items\n\nSafely incorporate approved corrections across a complete Epic or Feature tree. The skill is\ncontent-only by default: hierarchy, state, assignee, area, iteration, tags, and unrelated text\nremain unchanged. Read the references below before making placement or persistence decisions.\n\nReferences:\n\n- `.\u002Freferences\u002Fplacement.md` — keyword ranking and type\u002Fsection placement.\n- `.\u002Freferences\u002Fbackup-and-artifacts path.md` — backup, revision, Obsidian, and recovery rules.\n- `.\u002Freferences\u002Fapproval-and-persistence.md` — change-set approval and delegated writers.\n- `..\u002F..\u002Freferences\u002Fticket-structure.md` — artifacts path structure and section order.\n- `..\u002F..\u002Freferences\u002Ftracker-contract.md` — the tracker gateway: every read and write goes through\n  its `tracker_*` tools, never a tracker's own tools.\n- `..\u002Fenrich-work-item\u002Freferences\u002F` — canonical sections and examples for Epic, Feature, and Story.\n- `..\u002Fgenerate-breakdown-work-items\u002Freferences\u002F` — Implementation Plans and Task child rules.\n\n## Workflow\n\n### 1. Intake through UI\n\nAsk one question at a time through the host UI:\n\n1. Collect the amendment instructions verbatim. Do not paraphrase away corrections.\n2. Collect the reference Epic or Feature (tracker id or link, artifacts path, or filesystem path).\n3. Confirm scope as the complete descendant tree and the non-destructive, content-only policy.\n\nDo not read or write the tree before the reference is supplied. If the reference is ambiguous,\nstop and ask for a resolvable id, URL, or path.\n\n### 2. Resolve, snapshot, and scan\n\nRead `.\u002Freferences\u002Fbackup-and-ledger.md` before resolving the source. Create a backup of the entire tree before\nsemantic analysis. The snapshot must include every Epic, Feature, Story, and Task body; ids,\nrevisions, parent links, child links, attachments, and the related implementation plans in the items' folders. Verify\nthat the backup is readable and complete. A failed or partial backup is a hard stop.\n\nResolve the reference and enumerate descendants from Epic → Feature → User Story → Task before\nproposing changes. Read each node and retain its original revision. When a local Artifacts exists,\nuse `obsidian search`\u002FCLI first for title, id, and extracted keywords; use `rg` as the fallback or\nsecondary index. Search exact phrases, identifiers, normalized tokens, and stemmed terms from the\ninstructions. Keep unmatched instructions visible instead of silently dropping them.\n\n### 3. Analyze and offer placement\n\nSplit the instructions into atomic amendments. For each amendment, score candidate nodes and\ncanonical sections using exact identifiers, title matches, phrase matches, and type\u002Fsection\ncompatibility. Read `placement.md` and the relevant canonical\u002Fexample reference before deciding.\n\nPresent a single-select UI list for each amendment. Put the recommended placement first, include\nthe reason and affected node\u002Fsection, and make the final option exactly `Other` so the user can\ndescribe an alternative. Do not apply a placement until the user selects it. If a placement would\nrequire a new work item, structural relink, deletion, or state transition, flag it as out of scope\nand request explicit direction.\n\n### 4. Build and approve one change set\n\nProduce a consolidated preview containing, for every selected placement:\n\n- work-item id\u002Fpath, type, and section;\n- before\u002Fafter content or an exact insertion\u002Freplacement description;\n- linked Task and Implementation Plan consequences;\n- preserved fields and unresolved items;\n- backup location and source revisions.\n\nRe-read current revisions immediately before the approval prompt. If any revision changed since\nthe scan, refresh that node and rebuild the affected proposal. Write the change set as the reviewed drafts, show them with `harness workflow show\n--artifact \u003Cdraft>`, and ask `harness decision present --gate publish-items` with them as\n`--artifact`s. Cancellation or rejection ends the run without writes.\n\n### 5. Apply using existing Agile Backlog Toolkit skills\n\nAfter approval, delegate type-specific content work to the existing skills rather than inventing a\nparallel format:\n\n- Epic, Feature, or User Story prose\u002Fsection changes → `$enrich-work-item` with its canonical\n  references and approval gate.\n- Human-facing wording → `$generate-plain-language-documentation`.\n- An existing Story's plan-backed Task changes → `$generate-breakdown-work-items` rules; update\n  the saved Implementation Plan before reconciling its Tasks.\n- A missing required Task explicitly approved by the user → `$generate-work-item` and then link it\n  as a child of the Story.\n\nApply approved content top-down. Never mutate hierarchy, state, ownership, area, iteration, tags,\nor unrelated sections. Reconcile the Task child list without deleting existing Tasks: update only\naffected Task content, add approved missing Tasks, and report stale\u002Funmatched Tasks for review.\n\n**Any change to a Story's Task list invalidates its hour estimates.** Whenever Tasks are added,\nremoved, retitled, or rescoped, recompute the whole Story's split, write the new figures, and\nreport every one that moved (old → new). Nothing asked for approval, so nothing may move silently.\nRe-check the total against the assignee's remaining capacity in the active sprint; if it no longer\nfits, STOP and ask before writing. Full rules in\n`..\u002Fgenerate-breakdown-work-items\u002Freferences\u002Fatomic-tasks.md`.\nUpdate related Artifacts Implementation Plans when the amendment changes scope, acceptance coverage,\nor task sequencing. Read back every changed tracker item and artifacts file, verify parent links and\nrevisions, and run the applicable `validate-artifact` checks. Stop on the first failed write or\nread-back; leave the backup intact and report the exact recovery target.\n\n### 6. Report\n\nReport backup location, scanned tree counts, approved placements, changed nodes, recomputed\nTask hours (old → new), Task-list and\nImplementation-Plan updates, validation results, and unresolved instructions. State explicitly\nthat no state or hierarchy changes were made when that is true.\n\n## Safety invariants\n\n- Never write before backup, placement selection, consolidated preview, and explicit approval.\n- Never overwrite a newer revision; refresh and re-propose instead.\n- Never delete, relink, or change state without a separate explicit approval.\n- Preserve original instruction text and all unmatched items in the report.\n- If the tracker and the artifacts disagree, stop and present the conflict; do not guess which copy wins.\n","# Amend Work Items\n\nSafely incorporate approved corrections across a complete Epic or Feature tree. The skill is\ncontent-only by default: hierarchy, state, assignee, area, iteration, tags, and unrelated text\nremain unchanged. Read the references below before making placement or persistence decisions.\n\nReferences:\n\n- `.\u002Freferences\u002Fplacement.md` — keyword ranking and type\u002Fsection placement.\n- `.\u002Freferences\u002Fbackup-and-artifacts path.md` — backup, revision, Obsidian, and recovery rules.\n- `.\u002Freferences\u002Fapproval-and-persistence.md` — change-set approval and delegated writers.\n- `..\u002F..\u002Freferences\u002Fticket-structure.md` — artifacts path structure and section order.\n- `..\u002F..\u002Freferences\u002Ftracker-contract.md` — the tracker gateway: every read and write goes through\n  its `tracker_*` tools, never a tracker's own tools.\n- `..\u002Fenrich-work-item\u002Freferences\u002F` — canonical sections and examples for Epic, Feature, and Story.\n- `..\u002Fgenerate-breakdown-work-items\u002Freferences\u002F` — Implementation Plans and Task child rules.\n\n## Workflow\n\n### 1. Intake through UI\n\nAsk one question at a time through the host UI:\n\n1. Collect the amendment instructions verbatim. Do not paraphrase away corrections.\n2. Collect the reference Epic or Feature (tracker id or link, artifacts path, or filesystem path).\n3. Confirm scope as the complete descendant tree and the non-destructive, content-only policy.\n\nDo not read or write the tree before the reference is supplied. If the reference is ambiguous,\nstop and ask for a resolvable id, URL, or path.\n\n### 2. Resolve, snapshot, and scan\n\nRead `.\u002Freferences\u002Fbackup-and-ledger.md` before resolving the source. Create a backup of the entire tree before\nsemantic analysis. The snapshot must include every Epic, Feature, Story, and Task body; ids,\nrevisions, parent links, child links, attachments, and the related implementation plans in the items' folders. Verify\nthat the backup is readable and complete. A failed or partial backup is a hard stop.\n\nResolve the reference and enumerate descendants from Epic → Feature → User Story → Task before\nproposing changes. Read each node and retain its original revision. When a local Artifacts exists,\nuse `obsidian search`\u002FCLI first for title, id, and extracted keywords; use `rg` as the fallback or\nsecondary index. Search exact phrases, identifiers, normalized tokens, and stemmed terms from the\ninstructions. Keep unmatched instructions visible instead of silently dropping them.\n\n### 3. Analyze and offer placement\n\nSplit the instructions into atomic amendments. For each amendment, score candidate nodes and\ncanonical sections using exact identifiers, title matches, phrase matches, and type\u002Fsection\ncompatibility. Read `placement.md` and the relevant canonical\u002Fexample reference before deciding.\n\nPresent a single-select UI list for each amendment. Put the recommended placement first, include\nthe reason and affected node\u002Fsection, and make the final option exactly `Other` so the user can\ndescribe an alternative. Do not apply a placement until the user selects it. If a placement would\nrequire a new work item, structural relink, deletion, or state transition, flag it as out of scope\nand request explicit direction.\n\n### 4. Build and approve one change set\n\nProduce a consolidated preview containing, for every selected placement:\n\n- work-item id\u002Fpath, type, and section;\n- before\u002Fafter content or an exact insertion\u002Freplacement description;\n- linked Task and Implementation Plan consequences;\n- preserved fields and unresolved items;\n- backup location and source revisions.\n\nRe-read current revisions immediately before the approval prompt. If any revision changed since\nthe scan, refresh that node and rebuild the affected proposal. Write the change set as the reviewed drafts, show them with `harness workflow show\n--artifact \u003Cdraft>`, and ask `harness decision present --gate publish-items` with them as\n`--artifact`s. Cancellation or rejection ends the run without writes.\n\n### 5. Apply using existing Agile Backlog Toolkit skills\n\nAfter approval, delegate type-specific content work to the existing skills rather than inventing a\nparallel format:\n\n- Epic, Feature, or User Story prose\u002Fsection changes → `$enrich-work-item` with its canonical\n  references and approval gate.\n- Human-facing wording → `$generate-plain-language-documentation`.\n- An existing Story's plan-backed Task changes → `$generate-breakdown-work-items` rules; update\n  the saved Implementation Plan before reconciling its Tasks.\n- A missing required Task explicitly approved by the user → `$generate-work-item` and then link it\n  as a child of the Story.\n\nApply approved content top-down. Never mutate hierarchy, state, ownership, area, iteration, tags,\nor unrelated sections. Reconcile the Task child list without deleting existing Tasks: update only\naffected Task content, add approved missing Tasks, and report stale\u002Funmatched Tasks for review.\n\n**Any change to a Story's Task list invalidates its hour estimates.** Whenever Tasks are added,\nremoved, retitled, or rescoped, recompute the whole Story's split, write the new figures, and\nreport every one that moved (old → new). Nothing asked for approval, so nothing may move silently.\nRe-check the total against the assignee's remaining capacity in the active sprint; if it no longer\nfits, STOP and ask before writing. Full rules in\n`..\u002Fgenerate-breakdown-work-items\u002Freferences\u002Fatomic-tasks.md`.\nUpdate related Artifacts Implementation Plans when the amendment changes scope, acceptance coverage,\nor task sequencing. Read back every changed tracker item and artifacts file, verify parent links and\nrevisions, and run the applicable `validate-artifact` checks. Stop on the first failed write or\nread-back; leave the backup intact and report the exact recovery target.\n\n### 6. Report\n\nReport backup location, scanned tree counts, approved placements, changed nodes, recomputed\nTask hours (old → new), Task-list and\nImplementation-Plan updates, validation results, and unresolved instructions. State explicitly\nthat no state or hierarchy changes were made when that is true.\n\n## Safety invariants\n\n- Never write before backup, placement selection, consolidated preview, and explicit approval.\n- Never overwrite a newer revision; refresh and re-propose instead.\n- Never delete, relink, or change state without a separate explicit approval.\n- Preserve original instruction text and all unmatched items in the report.\n- If the tracker and the artifacts disagree, stop and present the conflict; do not guess which copy wins.\n",{"name":5,"license":15,"description":24},"Analyze user instructions and safely amend an entire work-item tree in the selected tracker. Use when a user supplies corrections or adjustments for an Epic or Feature and expects the Epic, Features, User Stories, and child Tasks to be scanned, placed, reviewed, and updated consistently. This skill gathers and presents a change set before any write, creates a recoverable tree backup, and never changes work items without explicit approval.\n","main","beda2ad5b6cc4caf3b0f62bc488106ae1d319f8e","plugins\u002Fmonolithic-dev-harness\u002Fskills\u002Famend-workitems",0,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness","https:\u002F\u002Fmonolithic-dev-harness.balmyangel65.chatgpt.site\u002F","https:\u002F\u002Fgithub.com\u002FMonolith-INC","Agentical Monolithics Cognitivity","2026-11-14 19:32:36",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Monolith-INC\u002Fmonolithic-dev-harness --skill amend-workitems",{"tool":40,"command":41},"bunx","bunx skills add Monolith-INC\u002Fmonolithic-dev-harness --skill amend-workitems",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Monolith-INC\u002Fmonolithic-dev-harness --skill amend-workitems","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Famend-workitems\u002FSKILL.md",true,[48,54,58,62,66],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",257,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Famend-workitems\u002Fagents\u002Fopenai.yaml",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"manifest.json",807,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Famend-workitems\u002Fmanifest.json",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fapproval-and-persistence.md",1293,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Famend-workitems\u002Freferences\u002Fapproval-and-persistence.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fbackup-and-ledger.md",1499,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Famend-workitems\u002Freferences\u002Fbackup-and-ledger.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fplacement.md",1470,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Famend-workitems\u002Freferences\u002Fplacement.md",[71,78,85,92,99,106],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7D7D832ZX48F36GB1F76PST","validate-artifact","Validate a single agile artifact (Epic, Feature, User Story, or Task) against the toolkit rule set. Use when the user asks to \"validate this story\u002Ffeature\u002Fepic\", \"check this ticket\", \"is this artifact ready?\", or provides a local draft path or provider item and wants a quality report. Accepts a local draft or a tracker work item. Runs all checks non-blocking and emits a terminal report + persisted report. One artifact per invocation.","https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fvalidate-artifact\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7D7C4SS2NP2RPWVV1MCKV1P","split-story","Lateral story-sizing skill. Takes a single User Story and determines if it should be split, how many sub-stories to create, and what split pattern to use — then drafts sub-stories and hands them off. Use when the user asks \"split this story\", \"is this story too big?\", \"analyze this story for sizing\", or provides an artifacts path \u002F tracker id \u002F file path \u002F raw text and wants a split recommendation. One story per invocation.","https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fsplit-story\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7D7ACZA52N346HGSMMJZNB4","research-decision","Research a product, market, domain, competitor, user, or technical question in service of a named decision, producing a cited decision brief. Use when planning depends on current evidence rather than more ideation.","https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fresearch-decision\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7D7A1TWTKH944PBW4TZAN8B","product-spec","Distill an idea, brief, PRD, UX contract, architecture spine, issue, or mixed notes into a compact canonical product contract with stable capabilities and companions. Use before backlog decomposition when intent is defined; update or validate an existing product spec through the same skill.","https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fproduct-spec\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7D79VZH4BJPBF85MBG0W5T4","product-requirements","Create, update, or validate a right-sized Product Requirements Document with stable requirements, explicit scope, user journeys where useful, and measurable outcomes. Use for multi-person or multi-epic alignment; skip it when a concise product spec is enough.","https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fproduct-requirements\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7D79QNTG9953KQCM4QZ6QSM","product-brief","Create, update, or validate a concise product brief that captures a clear concept, its users, value, scope, and success criteria. Use when the user wants a one- or two-page product narrative before a PRD or product spec.","https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fproduct-brief\u002FSKILL.md",[],[]]