[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D7C4SS2NP2RPWVV1MCKV1P":3,"skill-same:01M7D7C4SS2NP2RPWVV1MCKV1P":62},{"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},"01M7D7C4SS2NP2RPWVV1MCKV1P","split-story",null,"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.","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\u002Fsplit-story\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: split-story\ndescription: >\n  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.\nlicense: MIT\n---\n\n# split-story\n\nLateral story-sizing skill. Load reference files as each phase needs them.\n\nReferences (shared, in `..\u002F..\u002Freferences\u002F`):\n- `decomposition-rules.md` — 6-driver MAX heuristic, story-point ceiling, DoR, hierarchy rules.\n- `ticket-structure.md` — body sections, frontmatter constraints, content hygiene.\n- `tracker-contract.md` — the tracker gateway: every read and write goes through its `tracker_*`\n  tools, never a tracker's own tools.\n\nReferences (skill-specific, in `.\u002Freferences\u002F`):\n- `split-patterns.md` — split pattern catalog with detection signals and auto-selection rules.\n- `scoring-guide.md` — 6-driver scoring table, ceiling logic, spike detection rule, discrepancy\n  handling.\n- `..\u002F..\u002Fcommon\u002Ftemplates\u002Fcanonical-user-story.md` — **read-only shape contract** for split sub-story drafts\n  (seven emoji sections). Do not edit; validate output against this template.\n- `..\u002F..\u002Fcommon\u002Fcontracts\u002Fsplit-story\u002Fcanonical-spike.md` — **read-only shape contract** for spike stubs.\n  Do not edit; validate spike output against this template.\n\n---\n\n## PHASE 1 — INGEST\n\n**Input:** one of — local draft path, tracker id or link, arbitrary file system path, or raw\ntext pasted inline.\n\nDetermine source from the argument:\n\n**If local draft path** (path under the artifacts path, recognized by artifacts path prefix or `.md`\nextension inside the artifacts tree):\n1. Read the markdown file. Parse frontmatter: extract `work_item_type`, `story_points`,\n   `parent_id`, `provider_id`. Parse body: identify sections by emoji + label headings.\n\n**If a tracker id or link:**\n1. Call `tracker_get_work_item(ref=\u003Cid>)`.\n2. Extract: `title`, `description`, the Story's points (the estimate field `tracker_describe`\n   names), `parent_id`.\n\n**If file system path** (non-artifacts path to a `.md` or `.txt` file):\n1. Read the file from disk. Parse as markdown. Extract any frontmatter if present; treat body\n   as the full description.\n\n**If raw text** (multi-line pasted content, no recognizable path or ID):\n1. Use the pasted content directly as the body. No frontmatter to parse; treat the entire\n   input as the story description.\n\nNormalize into a unified artifact record:\n\n```text\n{\n  title:                string | null   (frontmatter\u002Ftitle field, or first heading, or null)\n  body:                 string          (full description \u002F body text)\n  story_points:         number | null   (null if not declared in any source)\n  acceptance_criteria:  string[]        (each AC line from the ✅ Critérios de Aceite section;\n                                         empty array if the section is absent)\n  parent_id:             string | null\n  provider:              the selected tracker's name\n  provider_id:           string | null\n  source:                \"artifacts path\" | \"tracker\" | \"filesystem\" | \"raw\"\n}\n```\n\nExtract `acceptance_criteria` by reading the `✅ Critérios de Aceite` section and splitting on\ncheckbox lines (`- [ ]` or `- [x]`). For a tracker source, parse the same section from the\nitem's `description`. For raw text or filesystem source, parse from the body if the\nsection heading is present; otherwise `acceptance_criteria = []`.\n\nIf artifact cannot be parsed (empty content, unreadable file, MCP error): STOP and report the\nspecific failure. Do not proceed.\n\n---\n\n## PHASE 2 — SCORE\n\nRead `.\u002Freferences\u002Fscoring-guide.md` for the complete driver table, ceiling value, spike rule,\nand discrepancy-handling protocol before scoring.\n\nApply the 6-driver MAX heuristic to the normalized artifact:\n\n1. Score each driver (Escopo, Incerteza, Integrações, Dados, QA, Rollout) on the 1\u002F2\u002F3\u002F5 scale.\n2. `calculated_points = MAX(all driver scores)`.\n3. Record which driver(s) are at the MAX — these are the dominant drivers.\n\n**Discrepancy check** (run only if `story_points` is declared and non-null):\n- If `declared == calculated`: proceed with `active_points = declared`.\n- If `declared ≠ calculated`: follow the discrepancy-handling protocol in `scoring-guide.md`\n  exactly — show both values with driver breakdown and wait for user choice.\n  `active_points = user-chosen value`.\n\n**If `story_points` not declared:** `active_points = calculated_points`. No prompt shown.\n\n---\n\n## PHASE 3 — ANALYZE\n\nRead `.\u002Freferences\u002Fsplit-patterns.md` for the pattern catalog and auto-selection decision tree.\n\n**Branch A — No split needed:**\n\nIf `active_points ≤ ceiling` (default 5, or override from invocation argument):\n\n1. Print: `Story is right-sized at \u003Cactive_points> pts (ceiling: \u003Cceiling>).`\n2. Print the driver breakdown (all six driver scores).\n3. STOP. No files written. No further phases execute.\n\n**Branch B — Spike recommended:**\n\nIf `Incerteza == 5` AND Incerteza is the sole MAX driver (no other driver also scored 5):\n\n1. Present spike rationale: uncertainty dominates; scope-splitting does not reduce risk —\n   investigation does.\n2. Show the user the specific unknown that caused Incerteza=5 (derived from the story body).\n3. Ask: \"Recommend a Spike instead of a scope split. Shall I draft a Spike stub?\"\n4. Wait for user confirmation before proceeding to DRAFT.\n   - Confirmed → proceed to DRAFT (Spike mode).\n   - Declined → STOP.\n\n**Branch C — Split:**\n\n1. `split_count = ⌈active_points \u002F ceiling⌉`.\n2. Auto-select split pattern using the decision tree in `split-patterns.md`.\n3. Show reasoning: one sentence per pattern considered; one winner with justification.\n4. Derive `split_count` sub-story titles and one-line scopes.\n5. Estimate point value per sub-story: re-apply driver scoring to the narrowed scope.\n   Each sub-story should score ≤ ceiling after the split.\n6. Map which ACs from the original story belong to each sub-story.\n\n**── GATE 1: present split plan to user ──**\n\nShow:\n- Pattern chosen and why (one sentence)\n- Number of sub-stories\n- For each sub-story: proposed title + one-line scope + estimated points\n- Which original ACs map to each sub-story\n\nAsk `harness decision present --gate refinement-split` before entering DRAFT.\nIf the user revises the plan (different pattern, different count, adjusted titles): incorporate\nrevisions and re-show the updated plan. Do not proceed until the plan is approved.\n\n---\n\n## PHASE 4 — DRAFT\n\nRead `..\u002F..\u002Freferences\u002Fticket-structure.md` and `..\u002F..\u002Freferences\u002Fdecomposition-rules.md`\nbefore writing any files.\n\n**Spike mode** (Branch B confirmed):\n\n1. Draft one local file at the path `harness document path --type ticket --new user-story\n   --title \"\u003Cspike title>\" --parent \u003Cparent_id>` prints (in `Tickets\u002FReady\u002F`).\n2. Fill all 7 body sections using the Spike stub format from `.\u002Freferences\u002Fscoring-guide.md`.\n3. Fill each `[placeholder]` with content derived from the original story.\n\n**Split mode** (Branch C approved):\n\nFor each approved sub-story:\n\n1. Path: the one `harness document path --type ticket --new user-story --title \"\u003Ctitle>\"\n   --parent \u003Cparent_id>` prints (in `Tickets\u002FReady\u002F`).\n2. The draft keeps that name; nothing is renamed after the item is created.\n3. Frontmatter (hook-valid — no `status:` and no `provider_id` before provider creation):\n\n```yaml\n---\ndate: \u003CYYYY-MM-DD>\ntype: ticket\nwork_item_type: User Story\nparent_id: \u003Cparent_id>\nprovider: local\nstory_points: \u003Cestimated-points>\n---\n```\n\n4. Body: all 7 sections per `ticket-structure.md` and `..\u002F..\u002Fcommon\u002Ftemplates\u002Fcanonical-user-story.md`\n   (in order):\n   - 🎯 O quê\n   - 💡 Por quê\n   - 📋 Comportamento esperado\n   - ✅ Critérios de Aceite\n   - 🔧 Notas Técnicas\n   - 📊 Complexidade — driver breakdown for this sub-story's narrowed scope\n   - 📄 Descrição Original — the exact verbatim slice of the original story's ACs that this\n     sub-story covers. No paraphrasing.\n\n**Coverage check** (run after all files are written, before HANDOFF):\n\n1. List every AC item from the original story.\n2. For each item, confirm it appears in exactly one sub-story's `📄 Descrição Original`.\n3. If any AC item appears in zero sub-stories: STOP and report\n   `ORPHAN AC: \u003Citem>` — dropped requirement.\n4. If any AC item appears in two or more sub-stories: STOP and report\n   `DUPLICATE COVERAGE: \u003Citem>` — ambiguous scope.\n5. Any gap or duplicate must be resolved by revising the draft files before HANDOFF.\n   Do not silently patch — surface the issue to the user.\n\n---\n\n## PHASE 5 — HANDOFF\n\nPresent a summary:\n- List each sub-story: title + point estimate + file path.\n- Coverage confirmation: \"All \u003CN> original ACs covered.\"\n\nShow options:\n\n```text\nSub-stories drafted. What would you like to do?\n\n1. Keep as local drafts — done; continue manually or via decompose-backlog.\n2. Create them in the selected tracker under the parent Feature.\n3. Discard drafts — delete files and stop.\n```\n\nWait for user choice.\n\n**Option 1 — Keep:**\nReport file paths and stop. No further action.\n\n**Option 2 — Provider:**\nRead `..\u002F..\u002Fcommon\u002Fproviders.md`. Show the drafts with `harness workflow show --artifact \u003Cdraft>`\nand ask `harness decision present --gate publish-items` with every draft as `--artifact`.\n\nFor each sub-story draft (in order):\n\n1. `tracker_create_work_item` (`kind: \"user_story\"`, Markdown description = full body from the\n   draft, `parentRef` = `parent_id`, `storyPoints` = the draft's estimate as a whole number).\n2. Assert the response carries the new item's `key`. If absent: STOP and report failure with the\n   item title and the raw error.\n3. Read back: `tracker_get_work_item(ref=\u003Cnew key>)`. Assert its `parent_id == parent_id`.\n   If the assertion fails: STOP and report\n   `LINK ASSERTION FAILED for \u003Ctitle>: expected parent \u003Cparent_id>, got \u003Cactual>`.\n4. Update local draft frontmatter: set `provider_id: \u003Cnew key>` (with the local tracker, creating\n   the item already did this). The file keeps its name.\n\nAfter all items: report each title, provider identifier, and parent link status.\n\n**Option 3 — Discard:**\nDelete each local draft file written in PHASE 4. Report `Drafts discarded.` and stop.\n\n---\n\n## Guardrails\n\n- **One story per run.** Process only the first argument if multiple are given.\n- **No silent patching.** Coverage gaps and duplicates surface to the user — never auto-resolved.\n- **No provider writes without user consent.** Connector calls execute only if the user selects\n  HANDOFF option 2.\n- **Gate before draft.** DRAFT phase does not execute until GATE 1 is explicitly approved.\n- **Spike ≠ split.** When Incerteza is the sole dominant driver, recommend a Spike; do not\n  force a scope split.\n","# split-story\n\nLateral story-sizing skill. Load reference files as each phase needs them.\n\nReferences (shared, in `..\u002F..\u002Freferences\u002F`):\n- `decomposition-rules.md` — 6-driver MAX heuristic, story-point ceiling, DoR, hierarchy rules.\n- `ticket-structure.md` — body sections, frontmatter constraints, content hygiene.\n- `tracker-contract.md` — the tracker gateway: every read and write goes through its `tracker_*`\n  tools, never a tracker's own tools.\n\nReferences (skill-specific, in `.\u002Freferences\u002F`):\n- `split-patterns.md` — split pattern catalog with detection signals and auto-selection rules.\n- `scoring-guide.md` — 6-driver scoring table, ceiling logic, spike detection rule, discrepancy\n  handling.\n- `..\u002F..\u002Fcommon\u002Ftemplates\u002Fcanonical-user-story.md` — **read-only shape contract** for split sub-story drafts\n  (seven emoji sections). Do not edit; validate output against this template.\n- `..\u002F..\u002Fcommon\u002Fcontracts\u002Fsplit-story\u002Fcanonical-spike.md` — **read-only shape contract** for spike stubs.\n  Do not edit; validate spike output against this template.\n\n---\n\n## PHASE 1 — INGEST\n\n**Input:** one of — local draft path, tracker id or link, arbitrary file system path, or raw\ntext pasted inline.\n\nDetermine source from the argument:\n\n**If local draft path** (path under the artifacts path, recognized by artifacts path prefix or `.md`\nextension inside the artifacts tree):\n1. Read the markdown file. Parse frontmatter: extract `work_item_type`, `story_points`,\n   `parent_id`, `provider_id`. Parse body: identify sections by emoji + label headings.\n\n**If a tracker id or link:**\n1. Call `tracker_get_work_item(ref=\u003Cid>)`.\n2. Extract: `title`, `description`, the Story's points (the estimate field `tracker_describe`\n   names), `parent_id`.\n\n**If file system path** (non-artifacts path to a `.md` or `.txt` file):\n1. Read the file from disk. Parse as markdown. Extract any frontmatter if present; treat body\n   as the full description.\n\n**If raw text** (multi-line pasted content, no recognizable path or ID):\n1. Use the pasted content directly as the body. No frontmatter to parse; treat the entire\n   input as the story description.\n\nNormalize into a unified artifact record:\n\n```text\n{\n  title:                string | null   (frontmatter\u002Ftitle field, or first heading, or null)\n  body:                 string          (full description \u002F body text)\n  story_points:         number | null   (null if not declared in any source)\n  acceptance_criteria:  string[]        (each AC line from the ✅ Critérios de Aceite section;\n                                         empty array if the section is absent)\n  parent_id:             string | null\n  provider:              the selected tracker's name\n  provider_id:           string | null\n  source:                \"artifacts path\" | \"tracker\" | \"filesystem\" | \"raw\"\n}\n```\n\nExtract `acceptance_criteria` by reading the `✅ Critérios de Aceite` section and splitting on\ncheckbox lines (`- [ ]` or `- [x]`). For a tracker source, parse the same section from the\nitem's `description`. For raw text or filesystem source, parse from the body if the\nsection heading is present; otherwise `acceptance_criteria = []`.\n\nIf artifact cannot be parsed (empty content, unreadable file, MCP error): STOP and report the\nspecific failure. Do not proceed.\n\n---\n\n## PHASE 2 — SCORE\n\nRead `.\u002Freferences\u002Fscoring-guide.md` for the complete driver table, ceiling value, spike rule,\nand discrepancy-handling protocol before scoring.\n\nApply the 6-driver MAX heuristic to the normalized artifact:\n\n1. Score each driver (Escopo, Incerteza, Integrações, Dados, QA, Rollout) on the 1\u002F2\u002F3\u002F5 scale.\n2. `calculated_points = MAX(all driver scores)`.\n3. Record which driver(s) are at the MAX — these are the dominant drivers.\n\n**Discrepancy check** (run only if `story_points` is declared and non-null):\n- If `declared == calculated`: proceed with `active_points = declared`.\n- If `declared ≠ calculated`: follow the discrepancy-handling protocol in `scoring-guide.md`\n  exactly — show both values with driver breakdown and wait for user choice.\n  `active_points = user-chosen value`.\n\n**If `story_points` not declared:** `active_points = calculated_points`. No prompt shown.\n\n---\n\n## PHASE 3 — ANALYZE\n\nRead `.\u002Freferences\u002Fsplit-patterns.md` for the pattern catalog and auto-selection decision tree.\n\n**Branch A — No split needed:**\n\nIf `active_points ≤ ceiling` (default 5, or override from invocation argument):\n\n1. Print: `Story is right-sized at \u003Cactive_points> pts (ceiling: \u003Cceiling>).`\n2. Print the driver breakdown (all six driver scores).\n3. STOP. No files written. No further phases execute.\n\n**Branch B — Spike recommended:**\n\nIf `Incerteza == 5` AND Incerteza is the sole MAX driver (no other driver also scored 5):\n\n1. Present spike rationale: uncertainty dominates; scope-splitting does not reduce risk —\n   investigation does.\n2. Show the user the specific unknown that caused Incerteza=5 (derived from the story body).\n3. Ask: \"Recommend a Spike instead of a scope split. Shall I draft a Spike stub?\"\n4. Wait for user confirmation before proceeding to DRAFT.\n   - Confirmed → proceed to DRAFT (Spike mode).\n   - Declined → STOP.\n\n**Branch C — Split:**\n\n1. `split_count = ⌈active_points \u002F ceiling⌉`.\n2. Auto-select split pattern using the decision tree in `split-patterns.md`.\n3. Show reasoning: one sentence per pattern considered; one winner with justification.\n4. Derive `split_count` sub-story titles and one-line scopes.\n5. Estimate point value per sub-story: re-apply driver scoring to the narrowed scope.\n   Each sub-story should score ≤ ceiling after the split.\n6. Map which ACs from the original story belong to each sub-story.\n\n**── GATE 1: present split plan to user ──**\n\nShow:\n- Pattern chosen and why (one sentence)\n- Number of sub-stories\n- For each sub-story: proposed title + one-line scope + estimated points\n- Which original ACs map to each sub-story\n\nAsk `harness decision present --gate refinement-split` before entering DRAFT.\nIf the user revises the plan (different pattern, different count, adjusted titles): incorporate\nrevisions and re-show the updated plan. Do not proceed until the plan is approved.\n\n---\n\n## PHASE 4 — DRAFT\n\nRead `..\u002F..\u002Freferences\u002Fticket-structure.md` and `..\u002F..\u002Freferences\u002Fdecomposition-rules.md`\nbefore writing any files.\n\n**Spike mode** (Branch B confirmed):\n\n1. Draft one local file at the path `harness document path --type ticket --new user-story\n   --title \"\u003Cspike title>\" --parent \u003Cparent_id>` prints (in `Tickets\u002FReady\u002F`).\n2. Fill all 7 body sections using the Spike stub format from `.\u002Freferences\u002Fscoring-guide.md`.\n3. Fill each `[placeholder]` with content derived from the original story.\n\n**Split mode** (Branch C approved):\n\nFor each approved sub-story:\n\n1. Path: the one `harness document path --type ticket --new user-story --title \"\u003Ctitle>\"\n   --parent \u003Cparent_id>` prints (in `Tickets\u002FReady\u002F`).\n2. The draft keeps that name; nothing is renamed after the item is created.\n3. Frontmatter (hook-valid — no `status:` and no `provider_id` before provider creation):\n\n```yaml\n---\ndate: \u003CYYYY-MM-DD>\ntype: ticket\nwork_item_type: User Story\nparent_id: \u003Cparent_id>\nprovider: local\nstory_points: \u003Cestimated-points>\n---\n```\n\n4. Body: all 7 sections per `ticket-structure.md` and `..\u002F..\u002Fcommon\u002Ftemplates\u002Fcanonical-user-story.md`\n   (in order):\n   - 🎯 O quê\n   - 💡 Por quê\n   - 📋 Comportamento esperado\n   - ✅ Critérios de Aceite\n   - 🔧 Notas Técnicas\n   - 📊 Complexidade — driver breakdown for this sub-story's narrowed scope\n   - 📄 Descrição Original — the exact verbatim slice of the original story's ACs that this\n     sub-story covers. No paraphrasing.\n\n**Coverage check** (run after all files are written, before HANDOFF):\n\n1. List every AC item from the original story.\n2. For each item, confirm it appears in exactly one sub-story's `📄 Descrição Original`.\n3. If any AC item appears in zero sub-stories: STOP and report\n   `ORPHAN AC: \u003Citem>` — dropped requirement.\n4. If any AC item appears in two or more sub-stories: STOP and report\n   `DUPLICATE COVERAGE: \u003Citem>` — ambiguous scope.\n5. Any gap or duplicate must be resolved by revising the draft files before HANDOFF.\n   Do not silently patch — surface the issue to the user.\n\n---\n\n## PHASE 5 — HANDOFF\n\nPresent a summary:\n- List each sub-story: title + point estimate + file path.\n- Coverage confirmation: \"All \u003CN> original ACs covered.\"\n\nShow options:\n\n```text\nSub-stories drafted. What would you like to do?\n\n1. Keep as local drafts — done; continue manually or via decompose-backlog.\n2. Create them in the selected tracker under the parent Feature.\n3. Discard drafts — delete files and stop.\n```\n\nWait for user choice.\n\n**Option 1 — Keep:**\nReport file paths and stop. No further action.\n\n**Option 2 — Provider:**\nRead `..\u002F..\u002Fcommon\u002Fproviders.md`. Show the drafts with `harness workflow show --artifact \u003Cdraft>`\nand ask `harness decision present --gate publish-items` with every draft as `--artifact`.\n\nFor each sub-story draft (in order):\n\n1. `tracker_create_work_item` (`kind: \"user_story\"`, Markdown description = full body from the\n   draft, `parentRef` = `parent_id`, `storyPoints` = the draft's estimate as a whole number).\n2. Assert the response carries the new item's `key`. If absent: STOP and report failure with the\n   item title and the raw error.\n3. Read back: `tracker_get_work_item(ref=\u003Cnew key>)`. Assert its `parent_id == parent_id`.\n   If the assertion fails: STOP and report\n   `LINK ASSERTION FAILED for \u003Ctitle>: expected parent \u003Cparent_id>, got \u003Cactual>`.\n4. Update local draft frontmatter: set `provider_id: \u003Cnew key>` (with the local tracker, creating\n   the item already did this). The file keeps its name.\n\nAfter all items: report each title, provider identifier, and parent link status.\n\n**Option 3 — Discard:**\nDelete each local draft file written in PHASE 4. Report `Drafts discarded.` and stop.\n\n---\n\n## Guardrails\n\n- **One story per run.** Process only the first argument if multiple are given.\n- **No silent patching.** Coverage gaps and duplicates surface to the user — never auto-resolved.\n- **No provider writes without user consent.** Connector calls execute only if the user selects\n  HANDOFF option 2.\n- **Gate before draft.** DRAFT phase does not execute until GATE 1 is explicitly approved.\n- **Spike ≠ split.** When Incerteza is the sole dominant driver, recommend a Spike; do not\n  force a scope split.\n",{"name":5,"license":15,"description":24},"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.\n","main","beda2ad5b6cc4caf3b0f62bc488106ae1d319f8e","plugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fsplit-story",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 split-story",{"tool":40,"command":41},"bunx","bunx skills add Monolith-INC\u002Fmonolithic-dev-harness --skill split-story",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Monolith-INC\u002Fmonolithic-dev-harness --skill split-story","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fsplit-story\u002FSKILL.md",true,[48,54,58],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"manifest.json","REFERENCE","参考文档",610,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fsplit-story\u002Fmanifest.json",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fscoring-guide.md",5844,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fsplit-story\u002Freferences\u002Fscoring-guide.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fsplit-patterns.md",6846,"https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fsplit-story\u002Freferences\u002Fsplit-patterns.md",[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7D79JHQ04YQD4WQ9HMDXZJV","plan-initiative","Route a raw idea through the smallest useful discovery and product-planning path, ending in a compact product spec ready for backlog decomposition. Use when the user wants to explore, validate, plan, define, or architect an idea before creating work items or starting implementation.","https:\u002F\u002Fgithub.com\u002FMonolith-INC\u002Fmonolithic-dev-harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmonolithic-dev-harness\u002Fskills\u002Fplan-initiative\u002FSKILL.md",[],[]]