[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C9SW8YC2TWRYH6BN7NRDH9":3,"skill-same:01M7C9SW8YC2TWRYH6BN7NRDH9":91},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M7C9SW8YC2TWRYH6BN7NRDH9","requeue",null,"Reviews and reorders the queue an engineering loop or team works from — backlog, roadmap, todo, milestones — so the next work picked up is the right work. Pulls every open item with the attributes that decide order (acceptance stated or not, blocked, human-only, duplicated, contradicted between files, stale), ranks them against the project's intent by unblocking power, purpose, readiness, decay and cost, splits them into lanes (the loop can finish it · needs a bounded subloop · needs a gauntlet of approaches · needs a human), rewrites the top vague items into tasks with an object, a test and a bound, and proposes the new order without touching the repo. Use when someone asks what to work on next, wants the backlog or roadmap reprioritised, re-ranked, triaged or cleaned up, says the priorities are wrong or the roadmap is stale, asks which items the autonomous loop should be fed, or arrives from loop-economist because the loop's problem is its input rather than its actor.","Busy-Office\u002Fai-skills","Busy-Office","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F295484308?v=4","01M7C9Q87FQYDQSSBXBRNMQ1CW","01M7C9Q880V3XY9NB38T9ZCWFG",0,"MIT","https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: requeue\ndescription: Reviews and reorders the queue an engineering loop or team works from — backlog, roadmap, todo, milestones — so the next work picked up is the right work. Pulls every open item with the attributes that decide order (acceptance stated or not, blocked, human-only, duplicated, contradicted between files, stale), ranks them against the project's intent by unblocking power, purpose, readiness, decay and cost, splits them into lanes (the loop can finish it · needs a bounded subloop · needs a gauntlet of approaches · needs a human), rewrites the top vague items into tasks with an object, a test and a bound, and proposes the new order without touching the repo. Use when someone asks what to work on next, wants the backlog or roadmap reprioritised, re-ranked, triaged or cleaned up, says the priorities are wrong or the roadmap is stale, asks which items the autonomous loop should be fed, or arrives from loop-economist because the loop's problem is its input rather than its actor.\n---\n\n# Requeue\n\nA loop is only as good as what it is fed. Most loops that look broken are\nbeing handed items that were never tasks: no acceptance test, a decision\nburied inside, or the same item twice in two files with opposite statuses.\nNo model fixes that. Requeue fixes the input.\n\n```mermaid\nflowchart LR\n  A[\"queue.mjs\u003Cbr\u002F>items + attributes · read-only\"] --> B[\"hygiene\u003Cbr\u002F>duplicate · contradiction · ghost · stale\"]\n  B --> C[\"rank\u003Cbr\u002F>unblocks › intent › readiness › decay › cost\"]\n  C --> D[\"lanes\u003Cbr\u002F>loop · subloop · gauntlet · human\"]\n  D --> E[\"sharpen the top\u003Cbr\u002F>object · test · bound\"]\n  E --> F[\"proposal\u003Cbr\u002F>order · reasons · asks\"]\n  F -. only when asked .-> G[\"write the queue file\"]\n```\n\n## The guard-rail\n\n- **Propose; do not rewrite.** The repo is untouched unless the person\n  names the file and asks. Reordering someone's roadmap unasked is the one\n  thing this skill must never do.\n- **Rank against a written purpose.** If no intent document exists, say so\n  in the first line and rank on unblocking and readiness only — and say\n  that the ranking is unanchored.\n- **Read bounded.** Queue files fully; everything else by header.\n- **No subagents.** One context, one pass.\n- **Leave a receipt**: files read, items considered, repo untouched.\n\n## Workflow\n\n### 1. Collect\n\n```bash\nnode \u003Cskill-dir>\u002Fscripts\u002Fqueue.mjs \u003Crepo-path> > \u003Cscratchpad>\u002Fqueue.json\n```\n\nEvery open item with file:line, section, whether it states an acceptance\ntest, whether it is worded only as judgement, blocked markers, human-only\nmarkers, first-seen date, plus duplicates, contradictions between files,\nand the intent documents. Read all of it.\n\nNo queue file → say so in three lines and stop. There is nothing to\nreprioritise, and inventing a backlog is not the ask.\n\n### 2. Hygiene first\n\n`references\u002Franking.md`, hygiene section. Duplicates, contradictions,\nghosts, stale items. Resolve *before* ranking: ranking a list that\ncontains the same item twice produces two ranks for one piece of work.\n\nFor a contradiction, decide which is true from the repo — the commit, the\ncode, the test — not from whichever file was edited last.\n\n### 3. Rank\n\nFive factors in strict precedence: **unblocks › intent › readiness ›\ndecay › cost**. One line of reason per ranked item, naming the deciding\nfactor, and naming the loser when two factors disagreed. An item that\ntraces to no sentence of intent is a deletion candidate, not a low rank.\n\n### 4. Split the lanes\n\n- **loop** — the loop can finish it unattended.\n- **loop, subloop** — the approach is uncertain: budget try · verify ·\n  adjust rounds with a round cap.\n- **loop, gauntlet** — more than one plausible approach and a costly wrong\n  choice: the bar gets written before the attempts run.\n- **human** — a credential, an account, a decision, a signature. It leaves\n  the loop's queue and becomes a gate item with the exact ask.\n- **blocked** — the blocker is named; if it is not, *naming it* is the\n  item.\n\nMixing human-only items into the loop's lane is the most common cause of\na loop that stalls while looking busy.\n\n### 5. Sharpen the top\n\n`references\u002Fsharpening.md`. Rewrite the top vague items — enough for the\nnext few ticks, not the whole list — into object · test · bound. Where no\ntest can be written, choose honestly between a question for a person, a\nbounded spike, and deletion. Never pass an untestable item to the loop.\n\n### 6. Write the proposal\n\n`references\u002Freport-template.md`, exactly: ≤ 50 words, queue health, the\nproposed order with reasons and lanes, what leaves the loop's queue, the\nsharpened rewrites, hygiene rows, do-next (≤ 5), footer receipt. Then a\nterminal summary of ≤ 8 lines.\n\n### 7. Apply — only when asked\n\nWrite the accepted order into the file the loop actually reads, one\ncommit, diff shown first. Keep the items' wording as sharpened, keep the\nfile's existing format, and never delete an item in the same commit as a\nreorder — deletions are their own decision and their own diff.\n\n## Judgement calls\n\n**Unblocking beats value.** A small thing three items wait on ships more\nwork this week than the biggest item on the list.\n\n**Readiness is a cap, not a factor.** An unready item cannot sit at rank\n1: sharpen it, then rank it. Feeding it up the queue anyway is how a loop\nburns a run discovering the item was a wish.\n\n**Old is not the same as dead.** Say the age; let the reader decide.\nPropose deletion only when nothing waits on it *and* it traces to no\nintent.\n\n**The queue the loop reads is the real one.** When two files disagree,\nthe file the driver loads wins, and the other becomes a pointer.\n\n**Don't rank what a person must do.** Human items get a lane and an exact\nask, not a position in a queue nobody is working.\n\n**Say when the order barely changes.** \"The current order is right; two\nitems need sharpening\" is a good outcome and a cheap one.\n\n## Files\n\n- `scripts\u002Fqueue.mjs` — item + attribute collector; `--self-test`.\n- `references\u002Franking.md` — the five factors, lanes, hygiene classes.\n- `references\u002Fsharpening.md` — object · test · bound, and the three\n  honest outcomes when no test can be written.\n- `references\u002Freport-template.md` — the proposal, exactly.\n- `evals\u002F` — the prompts, and `gauntlet\u002FBAR.md`, the bar this skill's\n  proposals are graded against by a blind critic.\n\n## Related\n\n`loop-economist` measures what the runs cost and hands off here when the\nbinding constraint is the input. `loop-doctor` reviews the loop's design.\n","# Requeue\n\nA loop is only as good as what it is fed. Most loops that look broken are\nbeing handed items that were never tasks: no acceptance test, a decision\nburied inside, or the same item twice in two files with opposite statuses.\nNo model fixes that. Requeue fixes the input.\n\n```mermaid\nflowchart LR\n  A[\"queue.mjs\u003Cbr\u002F>items + attributes · read-only\"] --> B[\"hygiene\u003Cbr\u002F>duplicate · contradiction · ghost · stale\"]\n  B --> C[\"rank\u003Cbr\u002F>unblocks › intent › readiness › decay › cost\"]\n  C --> D[\"lanes\u003Cbr\u002F>loop · subloop · gauntlet · human\"]\n  D --> E[\"sharpen the top\u003Cbr\u002F>object · test · bound\"]\n  E --> F[\"proposal\u003Cbr\u002F>order · reasons · asks\"]\n  F -. only when asked .-> G[\"write the queue file\"]\n```\n\n## The guard-rail\n\n- **Propose; do not rewrite.** The repo is untouched unless the person\n  names the file and asks. Reordering someone's roadmap unasked is the one\n  thing this skill must never do.\n- **Rank against a written purpose.** If no intent document exists, say so\n  in the first line and rank on unblocking and readiness only — and say\n  that the ranking is unanchored.\n- **Read bounded.** Queue files fully; everything else by header.\n- **No subagents.** One context, one pass.\n- **Leave a receipt**: files read, items considered, repo untouched.\n\n## Workflow\n\n### 1. Collect\n\n```bash\nnode \u003Cskill-dir>\u002Fscripts\u002Fqueue.mjs \u003Crepo-path> > \u003Cscratchpad>\u002Fqueue.json\n```\n\nEvery open item with file:line, section, whether it states an acceptance\ntest, whether it is worded only as judgement, blocked markers, human-only\nmarkers, first-seen date, plus duplicates, contradictions between files,\nand the intent documents. Read all of it.\n\nNo queue file → say so in three lines and stop. There is nothing to\nreprioritise, and inventing a backlog is not the ask.\n\n### 2. Hygiene first\n\n`references\u002Franking.md`, hygiene section. Duplicates, contradictions,\nghosts, stale items. Resolve *before* ranking: ranking a list that\ncontains the same item twice produces two ranks for one piece of work.\n\nFor a contradiction, decide which is true from the repo — the commit, the\ncode, the test — not from whichever file was edited last.\n\n### 3. Rank\n\nFive factors in strict precedence: **unblocks › intent › readiness ›\ndecay › cost**. One line of reason per ranked item, naming the deciding\nfactor, and naming the loser when two factors disagreed. An item that\ntraces to no sentence of intent is a deletion candidate, not a low rank.\n\n### 4. Split the lanes\n\n- **loop** — the loop can finish it unattended.\n- **loop, subloop** — the approach is uncertain: budget try · verify ·\n  adjust rounds with a round cap.\n- **loop, gauntlet** — more than one plausible approach and a costly wrong\n  choice: the bar gets written before the attempts run.\n- **human** — a credential, an account, a decision, a signature. It leaves\n  the loop's queue and becomes a gate item with the exact ask.\n- **blocked** — the blocker is named; if it is not, *naming it* is the\n  item.\n\nMixing human-only items into the loop's lane is the most common cause of\na loop that stalls while looking busy.\n\n### 5. Sharpen the top\n\n`references\u002Fsharpening.md`. Rewrite the top vague items — enough for the\nnext few ticks, not the whole list — into object · test · bound. Where no\ntest can be written, choose honestly between a question for a person, a\nbounded spike, and deletion. Never pass an untestable item to the loop.\n\n### 6. Write the proposal\n\n`references\u002Freport-template.md`, exactly: ≤ 50 words, queue health, the\nproposed order with reasons and lanes, what leaves the loop's queue, the\nsharpened rewrites, hygiene rows, do-next (≤ 5), footer receipt. Then a\nterminal summary of ≤ 8 lines.\n\n### 7. Apply — only when asked\n\nWrite the accepted order into the file the loop actually reads, one\ncommit, diff shown first. Keep the items' wording as sharpened, keep the\nfile's existing format, and never delete an item in the same commit as a\nreorder — deletions are their own decision and their own diff.\n\n## Judgement calls\n\n**Unblocking beats value.** A small thing three items wait on ships more\nwork this week than the biggest item on the list.\n\n**Readiness is a cap, not a factor.** An unready item cannot sit at rank\n1: sharpen it, then rank it. Feeding it up the queue anyway is how a loop\nburns a run discovering the item was a wish.\n\n**Old is not the same as dead.** Say the age; let the reader decide.\nPropose deletion only when nothing waits on it *and* it traces to no\nintent.\n\n**The queue the loop reads is the real one.** When two files disagree,\nthe file the driver loads wins, and the other becomes a pointer.\n\n**Don't rank what a person must do.** Human items get a lane and an exact\nask, not a position in a queue nobody is working.\n\n**Say when the order barely changes.** \"The current order is right; two\nitems need sharpening\" is a good outcome and a cheap one.\n\n## Files\n\n- `scripts\u002Fqueue.mjs` — item + attribute collector; `--self-test`.\n- `references\u002Franking.md` — the five factors, lanes, hygiene classes.\n- `references\u002Fsharpening.md` — object · test · bound, and the three\n  honest outcomes when no test can be written.\n- `references\u002Freport-template.md` — the proposal, exactly.\n- `evals\u002F` — the prompts, and `gauntlet\u002FBAR.md`, the bar this skill's\n  proposals are graded against by a blind critic.\n\n## Related\n\n`loop-economist` measures what the runs cost and hands off here when the\nbinding constraint is the input. `loop-doctor` reviews the loop's design.\n",{"name":5,"description":7},"main","ee822ad7e3f1e7dd3305c8e03565dc584906fb76","skills\u002Frequeue","https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills","https:\u002F\u002Fgithub.com\u002FBusy-Office","2026-09-27 17:58:58",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add Busy-Office\u002Fai-skills --skill requeue",{"tool":35,"command":36},"bunx","bunx skills add Busy-Office\u002Fai-skills --skill requeue",{"tool":38,"command":39},"pnpm","pnpm dlx skills add Busy-Office\u002Fai-skills --skill requeue","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002FSKILL.md",true,[43,49,53,57,61,65,69,73,77,81,85],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"evals\u002Fevals.json","REFERENCE","参考文档",2321,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Fevals\u002Fevals.json",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"evals\u002Fgauntlet\u002FBAR.md",4316,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Fevals\u002Fgauntlet\u002FBAR.md",{"path":54,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":55,"sourceHtmlUrl":56},"evals\u002Fgauntlet\u002FROUNDS.md",641,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Fevals\u002Fgauntlet\u002FROUNDS.md",{"path":58,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":59,"sourceHtmlUrl":60},"fixtures\u002Fmixed-queue\u002Fdocs\u002FBACKLOG.md",415,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Ffixtures\u002Fmixed-queue\u002Fdocs\u002FBACKLOG.md",{"path":62,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":63,"sourceHtmlUrl":64},"fixtures\u002Fmixed-queue\u002Fdocs\u002FROADMAP.md",108,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Ffixtures\u002Fmixed-queue\u002Fdocs\u002FROADMAP.md",{"path":66,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":67,"sourceHtmlUrl":68},"fixtures\u002Fmixed-queue\u002Fexpect.json",335,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Ffixtures\u002Fmixed-queue\u002Fexpect.json",{"path":70,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":71,"sourceHtmlUrl":72},"fixtures\u002Fmixed-queue\u002FREADME.md",52,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Ffixtures\u002Fmixed-queue\u002FREADME.md",{"path":74,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Franking.md",3087,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Freferences\u002Franking.md",{"path":78,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Freport-template.md",1803,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Freferences\u002Freport-template.md",{"path":82,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fsharpening.md",2168,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Freferences\u002Fsharpening.md",{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fqueue.mjs","SCRIPT","脚本",10392,"https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Frequeue\u002Fscripts\u002Fqueue.mjs",[92,99,105,112,118,125],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7C9TK43J3W13Q83AHM3ZCWV","loop","one tick","https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwake-weight\u002Ffixtures\u002Fheavy-wake\u002F.claude\u002Fskills\u002Floop\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M7C9TG9ND44SG4X5735RAKVE","wake-weight","https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwake-weight\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":18},"01M7C9T6K5HNKMW49F9XXAPZVH","solo-flow","Prescribes and audits a trunk-based git workflow for a repository with exactly one writer — a single autonomous agent or loop, with no other humans committing. One branch (main), local-only short-lived work branches, CI as the sole independent check (no PRs, nothing to review socially), and releases as tags cut directly off main rather than a develop\u002Frelease branch dance. Use whenever someone is setting up or reviewing git\u002Fbranching\u002Frelease conventions for an agent-driven or loop-driven repo, asks whether to use GitFlow\u002FGitHub Flow\u002FGitLab Flow\u002Ftrunk-based development, wants AGENTS.md or CLAUDE.md git rules written, is deciding whether a develop branch or long-lived feature branches earn their keep, or reports branch drift, a forgotten back-merge, or an autonomous loop that got confused about which branch it was on. Also use to sanity-check an existing branching setup that looks like GitFlow but has no other human collaborators to justify it, and when deciding how the agent should isolate each unit of work (git worktrees, a primary checkout that never leaves main, running items in parallel).","https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsolo-flow\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M7C9T3HA83YMNZNR8VSM5694","sharpen-intent","https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsharpen-intent\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":18},"01M7C9SQXNBEVGRFZR40W24AMW","progress-dashboard","Publishes a one-page stakeholder progress dashboard for any git project — where it stands, what's waiting on people, whether it's stalled — from whatever records the project keeps (ADRs, decision notes, design graphs, roadmaps, gates, backlogs, changelogs, PRs). Use whenever someone asks how a project is going, wants a status update or progress report, asks \"where are we\", \"what's blocked\", \"what's waiting on me\u002Fus\", \"what's left\", or wants an existing dashboard refreshed.","https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fprogress-dashboard\u002FSKILL.md",[],[],{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":18},"01M7C9S3PCMCKWXS4T2AMCK0C4","loop-economist","Reviews what an engineering loop's actual runs cost and produced — reading Claude Code session transcripts and git history rather than the loop's documents. Reports tokens per shipped change, cache and subagent spend, rework and thrash, how often a human had to intervene, and whether the right agent, model or persona did each kind of work; scores six dimensions (effectiveness, efficiency, budget, plan quality, agent fit, convergence) into a verdict, and prescribes what closes each finding — a verifier seam, routing the searching out, a bounded subloop or a gauntlet for items one run cannot converge on, or handing the queue to requeue when the input rather than the actor is the problem. Use when someone asks how efficient or effective their loop or agents are, what the loop is costing in tokens or budget, whether it is worth running, why it keeps redoing the same work, whether it is using the right model or agents, how to orchestrate multiple agents or personas across the work, or wants their multi-agent build loop analysed, scored or made cheaper.","https:\u002F\u002Fgithub.com\u002FBusy-Office\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Floop-economist\u002FSKILL.md",[],[]]