[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DH00RJ81SWNNQGQXH37KP2":3,"skill-same:01M7DH00RJ81SWNNQGQXH37KP2":47},{"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":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7DH00RJ81SWNNQGQXH37KP2","backlog",null,"View the product backlog in score order, recommend the next card to specify, file a new card with its GitHub issue, rescore cards or drop one — every change filed for maintainer approval","turbokast\u002Fmythhelm","turbokast","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F335585049?v=4","01M7DGYYSHNA1BW1Y9GJFN6DVC","TurboKast","01M7DGYYT6GTPCFADDKS5ZXM1Y",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbacklog\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: backlog\ndescription: View the product backlog in score order, recommend the next card to specify, file a new card with its GitHub issue, rescore cards or drop one — every change filed for maintainer approval\nargument-hint: \"show | next | add \\\"\u003Cidea or #issue>\\\" | rescore [MH-\u003Cn>] | drop MH-\u003Cn> \\\"\u003Creason>\\\"\"\n---\n\n# Backlog\n\n`product\u002Fbacklog.md` is the plan of record: one card per piece of work, scored by `(value + urgency + risk) \u002F effort` and kept in score order by `scripts\u002Fpm\u002Fpm.py`. The schema and the scoring rubric are at the top of that file. This skill reads it freely and changes it only through §File a change in `.claude\u002Fskills\u002Fpm-sync-core\u002FSKILL.md`, which files the change for a maintainer's approval.\n\n## Input\n\n`$ARGUMENTS`: a subcommand. With none, `show`.\n\n- `show`: the backlog in score order.\n- `next`: the card to specify next, and the commands that take it there.\n- `add \"\u003Cidea>\"` or `add #\u003Cissue>`: score and file a new card.\n- `rescore [MH-\u003Cn>]`: rescore one card, or every open card after the current stage changed.\n- `drop MH-\u003Cn> \"\u003Creason>\"`: close a card that will not be done.\n\n## Invocation contexts\n\n- **Slash command**: `show` and `next` only read. `add`, `rescore` and `drop` present the draft and its scoring, and file approval requests once the person confirms (write gate); creating the GitHub issue for a new card is a second write gate, after the card is approved.\n- **Model-invoked**: the same.\n- **Non-interactive**: `show` and `next` run as usual. For `add`, `rescore` and `drop`, filing the approval requests is allowed without pre-approval, because nothing reaches `product\u002F` until the maintainer signs; the draft and the request ids are the result. Creating a GitHub issue is public and needs explicit pre-approval in `$ARGUMENTS` or the dispatching prompt; without it, report the `gh issue create` command instead of running it.\n\n## show\n\nRun `python3 scripts\u002Fpm\u002Fpm.py list` (add `--status \u003Cs>` to filter, `--json` for fields). Present it grouped: in flight (`specced`, `implementing`), ready (`triaged`), ideas (`idea`), then closed. For each card give the id, title, score, stage and issue link.\n\n## next\n\n1. `python3 scripts\u002Fpm\u002Fpm.py next`: the highest-scored `triaged` or `idea` card in an earlier stage, the current stage or the next stage ([`product\u002Fobjectives.md`](..\u002F..\u002F..\u002Fproduct\u002Fobjectives.md)).\n2. Read its linked issue (`gh issue view \u003Cn> -R turbokast\u002Fmythhelm --comments`) for discussion the card does not reflect yet.\n3. Check that nothing already covers it: `grep -rlE \"MH-\u003Cn>([^0-9]|$)\" specs\u002F` and the specs in `specs\u002Fin-progress\u002F` and `specs\u002Ftodo\u002F`.\n4. Present the card, why it is first (its score inputs against the runner-up) and the path to shipping it:\n\n```text\nNext: MH-\u003Cn> — \u003Ctitle> (score \u003Cs>, stage \u003Cstage>, issue #\u003Ci>)\nWhy now: \u003Cone or two sentences from the score inputs and the stage exit gate>\nThen: \u002Fcreate-spec MH-\u003Cn> → \u002Frefine-spec \u003Cname> → \u002Fspec \u003Cname> → run-spec \u003Cname> → finalize-spec \u003Cname>\n```\n\n## add\n\n1. **Source.** For `#\u003Cissue>`, read it with `gh issue view \u003Cn> -R turbokast\u002Fmythhelm --json number,title,body,labels,comments,url`. For free text, use it as given.\n2. **Triage** it with `.claude\u002Fskills\u002Ftriage\u002FSKILL.md` (duplicates, commitments, score). Stop at a duplicate or a commitment conflict and report it: that is the answer, not a card.\n3. **Ground the premise** (`.claude\u002Frules\u002Fproduct-management.md` §Premise grounding): a Summary that says something is missing or broken today is checked at source before it is filed.\n4. **Present** the draft card: title, stage, gates, the four score inputs with one line of reasoning each, the resulting score, where it would rank (`pm.py list`), source sections and summary. Ask to file it (write gate).\n5. **File** with §File a change: `pm.py --product-dir \"$STAGE\" add --title ... --stage ... --gates ... --value ... --risk ... --effort ... --source ... --summary ... [--issue \u003Cn>] --out \"$STAGE\u002Fbacklog.md\"` (the verb reserves the id), then `decide --type card-add` naming the card, then the roadmap. The id exists only from this step on.\n6. **Issue.** Once the card is approved and committed, and only if it has no issue yet, create one (second write gate):\n   `gh issue create -R turbokast\u002Fmythhelm --title \"\u003Ctitle> (MH-\u003Cn>)\" --label \u003Clabels> --body-file \u003Cfile>`. Labels come from the existing set (`gh label list -R turbokast\u002Fmythhelm`): `enhancement` plus the area (`adapter`, `host`, `routing`, `tui`, `billing`, `plugins`, `protocol`, `ci`, `documentation`, `security`, `harness`). The body links the card and cites the spec sections, in public-safe words (`.claude\u002Frules\u002Fpublic-repo-hygiene.md`). Never create milestones or projects. Then file `pm.py ... set MH-\u003Cn> issue \u003Cnumber>` through §File a change.\n\nWhen the idea came from an issue, step 5 passes `--issue \u003Cn>` and step 6 is skipped; comment on the issue only when the person asks.\n\n## rescore\n\n1. `rescore MH-\u003Cn>`: re-derive value, risk and effort from current evidence (new signals, impact reviews, a changed dependency), present old and new inputs with the reason for each change, and on confirmation file `pm.py ... rescore MH-\u003Cn> [--value N] [--risk N] [--effort N] [--stage S]` plus a `rescore` decision.\n2. `rescore` with no card: after `product\u002Fobjectives.md`'s current stage changes, urgencies are stale and the `product` lint fails. `pm.py ... rescore` recomputes every open card's urgency; file it together with the `objective-change` decision that moved the stage.\n3. Present the new order (`pm.py --product-dir \"$STAGE\" list`) and the cards whose rank changed.\n\n## drop\n\nConfirm the reason, then file `set-status MH-\u003Cn> dropped`, a `card-drop` decision whose rationale gives the reason, and the roadmap. Close the card's issue only when the person asks, with a comment linking the decision.\n\n## Output\n\nThe listing, the recommendation, or for a change: the draft, the request ids, and the maintainer's commands (`scripts\u002Forchestration\u002Fapprove.sh show \u003Cid>` then `approve \u003Cid> --apply`).\n","# Backlog\n\n`product\u002Fbacklog.md` is the plan of record: one card per piece of work, scored by `(value + urgency + risk) \u002F effort` and kept in score order by `scripts\u002Fpm\u002Fpm.py`. The schema and the scoring rubric are at the top of that file. This skill reads it freely and changes it only through §File a change in `.claude\u002Fskills\u002Fpm-sync-core\u002FSKILL.md`, which files the change for a maintainer's approval.\n\n## Input\n\n`$ARGUMENTS`: a subcommand. With none, `show`.\n\n- `show`: the backlog in score order.\n- `next`: the card to specify next, and the commands that take it there.\n- `add \"\u003Cidea>\"` or `add #\u003Cissue>`: score and file a new card.\n- `rescore [MH-\u003Cn>]`: rescore one card, or every open card after the current stage changed.\n- `drop MH-\u003Cn> \"\u003Creason>\"`: close a card that will not be done.\n\n## Invocation contexts\n\n- **Slash command**: `show` and `next` only read. `add`, `rescore` and `drop` present the draft and its scoring, and file approval requests once the person confirms (write gate); creating the GitHub issue for a new card is a second write gate, after the card is approved.\n- **Model-invoked**: the same.\n- **Non-interactive**: `show` and `next` run as usual. For `add`, `rescore` and `drop`, filing the approval requests is allowed without pre-approval, because nothing reaches `product\u002F` until the maintainer signs; the draft and the request ids are the result. Creating a GitHub issue is public and needs explicit pre-approval in `$ARGUMENTS` or the dispatching prompt; without it, report the `gh issue create` command instead of running it.\n\n## show\n\nRun `python3 scripts\u002Fpm\u002Fpm.py list` (add `--status \u003Cs>` to filter, `--json` for fields). Present it grouped: in flight (`specced`, `implementing`), ready (`triaged`), ideas (`idea`), then closed. For each card give the id, title, score, stage and issue link.\n\n## next\n\n1. `python3 scripts\u002Fpm\u002Fpm.py next`: the highest-scored `triaged` or `idea` card in an earlier stage, the current stage or the next stage ([`product\u002Fobjectives.md`](..\u002F..\u002F..\u002Fproduct\u002Fobjectives.md)).\n2. Read its linked issue (`gh issue view \u003Cn> -R turbokast\u002Fmythhelm --comments`) for discussion the card does not reflect yet.\n3. Check that nothing already covers it: `grep -rlE \"MH-\u003Cn>([^0-9]|$)\" specs\u002F` and the specs in `specs\u002Fin-progress\u002F` and `specs\u002Ftodo\u002F`.\n4. Present the card, why it is first (its score inputs against the runner-up) and the path to shipping it:\n\n```text\nNext: MH-\u003Cn> — \u003Ctitle> (score \u003Cs>, stage \u003Cstage>, issue #\u003Ci>)\nWhy now: \u003Cone or two sentences from the score inputs and the stage exit gate>\nThen: \u002Fcreate-spec MH-\u003Cn> → \u002Frefine-spec \u003Cname> → \u002Fspec \u003Cname> → run-spec \u003Cname> → finalize-spec \u003Cname>\n```\n\n## add\n\n1. **Source.** For `#\u003Cissue>`, read it with `gh issue view \u003Cn> -R turbokast\u002Fmythhelm --json number,title,body,labels,comments,url`. For free text, use it as given.\n2. **Triage** it with `.claude\u002Fskills\u002Ftriage\u002FSKILL.md` (duplicates, commitments, score). Stop at a duplicate or a commitment conflict and report it: that is the answer, not a card.\n3. **Ground the premise** (`.claude\u002Frules\u002Fproduct-management.md` §Premise grounding): a Summary that says something is missing or broken today is checked at source before it is filed.\n4. **Present** the draft card: title, stage, gates, the four score inputs with one line of reasoning each, the resulting score, where it would rank (`pm.py list`), source sections and summary. Ask to file it (write gate).\n5. **File** with §File a change: `pm.py --product-dir \"$STAGE\" add --title ... --stage ... --gates ... --value ... --risk ... --effort ... --source ... --summary ... [--issue \u003Cn>] --out \"$STAGE\u002Fbacklog.md\"` (the verb reserves the id), then `decide --type card-add` naming the card, then the roadmap. The id exists only from this step on.\n6. **Issue.** Once the card is approved and committed, and only if it has no issue yet, create one (second write gate):\n   `gh issue create -R turbokast\u002Fmythhelm --title \"\u003Ctitle> (MH-\u003Cn>)\" --label \u003Clabels> --body-file \u003Cfile>`. Labels come from the existing set (`gh label list -R turbokast\u002Fmythhelm`): `enhancement` plus the area (`adapter`, `host`, `routing`, `tui`, `billing`, `plugins`, `protocol`, `ci`, `documentation`, `security`, `harness`). The body links the card and cites the spec sections, in public-safe words (`.claude\u002Frules\u002Fpublic-repo-hygiene.md`). Never create milestones or projects. Then file `pm.py ... set MH-\u003Cn> issue \u003Cnumber>` through §File a change.\n\nWhen the idea came from an issue, step 5 passes `--issue \u003Cn>` and step 6 is skipped; comment on the issue only when the person asks.\n\n## rescore\n\n1. `rescore MH-\u003Cn>`: re-derive value, risk and effort from current evidence (new signals, impact reviews, a changed dependency), present old and new inputs with the reason for each change, and on confirmation file `pm.py ... rescore MH-\u003Cn> [--value N] [--risk N] [--effort N] [--stage S]` plus a `rescore` decision.\n2. `rescore` with no card: after `product\u002Fobjectives.md`'s current stage changes, urgencies are stale and the `product` lint fails. `pm.py ... rescore` recomputes every open card's urgency; file it together with the `objective-change` decision that moved the stage.\n3. Present the new order (`pm.py --product-dir \"$STAGE\" list`) and the cards whose rank changed.\n\n## drop\n\nConfirm the reason, then file `set-status MH-\u003Cn> dropped`, a `card-drop` decision whose rationale gives the reason, and the roadmap. Close the card's issue only when the person asks, with a comment linking the decision.\n\n## Output\n\nThe listing, the recommendation, or for a change: the draft, the request ids, and the maintainer's commands (`scripts\u002Forchestration\u002Fapprove.sh show \u003Cid>` then `approve \u003Cid> --apply`).\n",{"name":5,"description":7,"argument-hint":24},"show | next | add \"\u003Cidea or #issue>\" | rescore [MH-\u003Cn>] | drop MH-\u003Cn> \"\u003Creason>\"","main","6e250ec86158119da148ddc017b960ed3b2bee2b",".claude\u002Fskills\u002Fbacklog",1,"https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm","https:\u002F\u002Fgithub.com\u002Fturbokast","https:\u002F\u002Fturbokast.com","2026-11-10 17:37:03",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add turbokast\u002Fmythhelm --skill backlog",{"tool":39,"command":40},"bunx","bunx skills add turbokast\u002Fmythhelm --skill backlog",{"tool":42,"command":43},"pnpm","pnpm dlx skills add turbokast\u002Fmythhelm --skill backlog","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbacklog\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7DH77QH78C95S7A5V1GFKKF","mythhelm-deliver-backlog","Coordinate a MYTHHELM backlog run with the shared stage checks and maintainer checkpoints.","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.grok\u002Fskills\u002Fmythhelm-deliver-backlog\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DH748EXYG9RVBWPBJ73M27","mythhelm-bootstrap","Orient a Grok Build session in the MYTHHELM repository before task or spec work.","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.grok\u002Fskills\u002Fmythhelm-bootstrap\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7DH70XJE0DZA4T5DYR1TWKZ","vendor-consult","Run one advisory stage consult (premise-ground, spec-validate, task-review, change-review, stuck-oracle, dossier) with an optional external vendor, then adjudicate the answer at its anchors","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvendor-consult\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DH6X9HSQ308P5FNDSKYR5R","update-docs","Bring README, docs\u002F, knowledge\u002F, WORKFLOW.md and CLAUDE.md in line with what a shipped spec or a merged change actually did — find every statement the change made stale, fix it where readers look, and add only the new facts they need","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fupdate-docs\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DH6T82XR40XQFNRTN4AHGN","triage","Score an idea or a GitHub issue against the master spec's stages, gates and commitments, check it for duplicates, and recommend whether it becomes a backlog card; read-only","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DH6Q17PM4ESX978QYFV6H6","test-driven-development","Red-green-refactor for Go — use when implementing any feature, bug fix or behaviour change, before writing implementation code","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]