[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EX3Y79AHVGX99PS19W9M68":3,"skill-same:01M7EX3Y79AHVGX99PS19W9M68":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EX3Y79AHVGX99PS19W9M68","audit-choices",null,"Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or committing AI-implemented work, when integrating a delegated subagent's pass, or when a fix \"works\" but might be a point fix.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Faudit-choices\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: audit-choices\ndescription: Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or committing AI-implemented work, when integrating a delegated subagent's pass, or when a fix \"works\" but might be a point fix.\n---\n\n# Audit Choices\n\nGiven a good decision, an agent implements it faithfully; wherever the task is\nunderspecified, it makes the decision itself — silently, and the diff won't\nflag it. Reviewing thousands of changed lines doesn't scale, and it inspects\nthe execution, which was probably fine. The audit that scales is of the\n**choices**: surface every decision the implementer made on its own, judge\nthat list, and record the verdicts.\n\nThis is about architecture more than bugs. An implementation can work\nperfectly and still rest on decisions the user never made — a data shape, a\nstorage location, a dependency, an API contract, a tradeoff of memory for\nspeed — and every one of them is load-bearing for future work. The user needs\nto know them not because they're wrong, but because they now own them.\n\nThis is purely a decision audit — it is not about modifying code, and it can\nbe called at any time. The job is to **trace back**: walk every step this\nsession has taken, and every step each subagent took (a live implementer\ntraces its own; otherwise reconstruct from its reports, transcripts, and\ndiffs), and surface every single decision that was made on the user's behalf\nthat was not in the original spec or prompt. The ledger of those decisions\nreplaces reading the code as the user's review surface — that is the whole\npoint. Acting on the verdicts (redoing an unsound choice, applying a\nprovisional call) belongs to the caller: the implementing workflow mid-run,\nor the user after reading the report.\n\nTwo ways in, same audit:\n\n- **Called by a workflow** (per pass or per slice): audit that pass, append\n  its entries to the ledger, and return; the workflow presents the\n  accumulated ledger when it hands back.\n- **Called directly by the user**: audit the whole body of work in front of\n  you (session, branch, or named change) and present the report immediately.\n  Recommend; change nothing.\n\n## Workflow\n\n1. **Elicit and trace back.** When an implementer reports done, ask: *\"While\n   working on this, which choices did you make that you're not confident of?\n   List all.\"* — but treat the self-report as a starting point, not the\n   boundary: agents under-report. Trace the history yourself — the session's\n   steps, subagent reports, diffs, commits — and collect every decision that\n   is in the work but not in the original spec or prompt. Sweep the\n   architectural categories, not just the suspect fixes: data shapes and\n   formats, storage and naming schemes, API contracts and their error\n   behavior, dependencies added, concurrency\u002Fperf tradeoffs, scope\n   interpretations, patterns future code will imitate. Auditing your own\n   session, trace your own steps the same way. Choices the plan explicitly\n   delegated to the implementer are discretion, not audit items.\n2. **Triage each choice on evidence.** Forced by the plan, or invented?\n   Invented ones get the scrutiny: is this the general solution, or a fix\n   shaped to the one failing case? Verdict per choice: **sound**, **unsound**,\n   or **needs-user** — and alongside the verdict, a **confidence**: how sure\n   the audit is that the user would have made this same call. Confidence is\n   what ranks the report. Reserve needs-user for genuinely user-only calls\n   (taste, product direction, external cost); every needs-user entry records a\n   recommended provisional call that is reversible, so an unsupervised caller\n   can proceed without waiting. The audit never stalls a run: each entry is a\n   judgment handed over for action or review, not a question that halts.\n3. **State the corrected decision, don't sketch a patch.** For each unsound\n   choice, the entry names the decision the work should be redone from — the\n   property that must hold in general — not an edit to layer on top. A patch\n   on top of a bad decision preserves the decision; the redo itself is the\n   caller's, after the ledger is reviewed.\n4. **Bank every choice in the ledger** (below), and promote load-bearing\n   sound ones into the plan's handoff so later passes inherit them as givens\n   instead of re-deciding.\n5. **Present the ledger: grouped by verdict, ranked by confidence.** The\n   audit's deliverable is the ledger, handed to whoever acts next — the\n   calling workflow mid-run, the user at run's end. Each verdict group maps\n   to an action — needs-user (decide, with the provisional calls), unsound\n   (redo, with the corrected decisions), sound (acknowledge: the\n   architecture the user now owns) — and within each group choices are\n   ranked by confidence, least confident first. When the ledger is long,\n   open the report with the two or three least-confident choices overall,\n   whatever their group: the \"review these first\" line. Sound is not\n   skippable. Only trivial discretion (internal naming, cosmetic calls)\n   compresses to a one-line count.\n\n   **Write every entry ELI5 — by default, not on request.** The reader\n   didn't live the session: write each entry in the\n   [eli5](..\u002Feli5\u002FSKILL.md) register — a concrete scenario walked end to\n   end (the triggering event, what the work does today, what the unbuilt\n   alternative would do), every term of art defined at first use, and\n   pseudocode at the level of the decision when the choice is about control\n   flow, ordering, or timing. \"A gated ask is dropped, not deferred\" is a\n   headline, not an entry. A compressed entry that makes the user ask\n   \"explain this one\" has failed; the ledger must stand alone without the\n   diff, the spec, or the transcript.\n\n## The Choices Ledger\n\nA dedicated file that outlives every pass: `choices.md` beside the plan\n(`specs\u002F\u003Cfeature>\u002Fchoices.md` when a spec owns the work). One entry per\naudited choice:\n\n- **When** — pass or commit it landed in.\n- **The choice** — a one-line headline, then the ELI5 scenario: the\n  triggering event, what the work does today, what the unbuilt alternative\n  would do, with terms of art defined in place.\n- **The gap** — what the plan left unspecified that forced it.\n- **The reach** — what future work this decision constrains or enables; why\n  the user needs to know it exists.\n- **Verdict** — sound \u002F unsound \u002F needs-user, with a one-line why. For\n  unsound: the corrected decision to redo from. For needs-user: the\n  recommended provisional call and how to reverse it.\n- **Confidence** — how sure the audit is that the user would have made the\n  same call (low \u002F medium \u002F high). Ranks the report, ascending.\n\nRules of the ledger:\n\n- Banked is settled: a choice already in the ledger (or promoted into the\n  plan) is a given for later passes — never re-listed, never re-decided.\n- The ledger is a plan-quality signal. Entries clustering around one slice or\n  area mean the plan is foggy there — reslice or send that part back through\n  the spec rather than triaging the same class of choice forever.\n- **ELI5 survives every rewrite.** The entry format above — headline plus the\n  walked scenario with terms defined in place — is the *storage* format, not\n  presentation polish. When entries are consolidated, merged, re-audited at\n  close, or copied into a final ledger, each surviving entry keeps (or\n  regains) its full scenario. The known failure mode is exactly this\n  compression: a closeout rewrite that shrinks banked entries to their\n  headlines produces a ledger the reader must interrogate — \"The checkpoint\n  loads rows in mailbox order and rejects the list when a later reference\n  has an earlier createdAt\" reads as settled, but only the walked version\n  (two sessions, per-session sequence numbers that can't be compared, the\n  shared insert-timestamp clock) lets a reader actually judge the choice. A\n  consolidation that drops scenarios has failed even if every fact survives —\n  and so has one that keeps the scenario but leans on labels the build\n  invented (\"the retry envelope\", \"the evidence seam\") without defining them\n  where they're used.\n\n## Rules\n\n- **\"It works\" is not a verdict on the choice.** The recurring smell is the\n  coincidental fix: a resized buffer, bumped timeout, or special case whose\n  magnitude happens to cover the failing input while the underlying cause\n  stays dormant. Ask what property *guarantees* the fix in general; if the\n  answer is \"this case passes,\" the choice is unsound even though the code is\n  green.\n- Declared success is the point of maximum risk — the implementer's confidence\n  is highest exactly when its unexamined choices are about to be merged. Never\n  skip the audit because the result looks clean.\n- An empty list on nontrivial work is a red flag, not a pass. Probe: what did\n  the task leave unspecified? Something filled those gaps.\n- The audit changes no code, tests, or build state. Finding an unsound choice\n  is the deliverable, not a license to fix it — record the corrected decision\n  and leave the tree exactly as audited, so the ledger and the tree agree on\n  what the caller is deciding about. Evidence-gathering is fair game: read\n  anything, run the existing tests, write transient probes — but remove every\n  probe before handback.\n\n## Done\n\nThe audit is done when every invented choice in the pass has a ledger entry\nwith a verdict, every unsound entry names the corrected decision to redo\nfrom, every needs-user entry carries a reversible provisional call, and the\nledger has been presented — grouped by verdict, least-confident-first within\neach group, every entry readable ELI5 without follow-up questions — to\nwhoever acts next, with the tree untouched. A handback that shows the diff\ninstead of the choices, or a \"fix\" applied during the audit, is not done.\n","# Audit Choices\n\nGiven a good decision, an agent implements it faithfully; wherever the task is\nunderspecified, it makes the decision itself — silently, and the diff won't\nflag it. Reviewing thousands of changed lines doesn't scale, and it inspects\nthe execution, which was probably fine. The audit that scales is of the\n**choices**: surface every decision the implementer made on its own, judge\nthat list, and record the verdicts.\n\nThis is about architecture more than bugs. An implementation can work\nperfectly and still rest on decisions the user never made — a data shape, a\nstorage location, a dependency, an API contract, a tradeoff of memory for\nspeed — and every one of them is load-bearing for future work. The user needs\nto know them not because they're wrong, but because they now own them.\n\nThis is purely a decision audit — it is not about modifying code, and it can\nbe called at any time. The job is to **trace back**: walk every step this\nsession has taken, and every step each subagent took (a live implementer\ntraces its own; otherwise reconstruct from its reports, transcripts, and\ndiffs), and surface every single decision that was made on the user's behalf\nthat was not in the original spec or prompt. The ledger of those decisions\nreplaces reading the code as the user's review surface — that is the whole\npoint. Acting on the verdicts (redoing an unsound choice, applying a\nprovisional call) belongs to the caller: the implementing workflow mid-run,\nor the user after reading the report.\n\nTwo ways in, same audit:\n\n- **Called by a workflow** (per pass or per slice): audit that pass, append\n  its entries to the ledger, and return; the workflow presents the\n  accumulated ledger when it hands back.\n- **Called directly by the user**: audit the whole body of work in front of\n  you (session, branch, or named change) and present the report immediately.\n  Recommend; change nothing.\n\n## Workflow\n\n1. **Elicit and trace back.** When an implementer reports done, ask: *\"While\n   working on this, which choices did you make that you're not confident of?\n   List all.\"* — but treat the self-report as a starting point, not the\n   boundary: agents under-report. Trace the history yourself — the session's\n   steps, subagent reports, diffs, commits — and collect every decision that\n   is in the work but not in the original spec or prompt. Sweep the\n   architectural categories, not just the suspect fixes: data shapes and\n   formats, storage and naming schemes, API contracts and their error\n   behavior, dependencies added, concurrency\u002Fperf tradeoffs, scope\n   interpretations, patterns future code will imitate. Auditing your own\n   session, trace your own steps the same way. Choices the plan explicitly\n   delegated to the implementer are discretion, not audit items.\n2. **Triage each choice on evidence.** Forced by the plan, or invented?\n   Invented ones get the scrutiny: is this the general solution, or a fix\n   shaped to the one failing case? Verdict per choice: **sound**, **unsound**,\n   or **needs-user** — and alongside the verdict, a **confidence**: how sure\n   the audit is that the user would have made this same call. Confidence is\n   what ranks the report. Reserve needs-user for genuinely user-only calls\n   (taste, product direction, external cost); every needs-user entry records a\n   recommended provisional call that is reversible, so an unsupervised caller\n   can proceed without waiting. The audit never stalls a run: each entry is a\n   judgment handed over for action or review, not a question that halts.\n3. **State the corrected decision, don't sketch a patch.** For each unsound\n   choice, the entry names the decision the work should be redone from — the\n   property that must hold in general — not an edit to layer on top. A patch\n   on top of a bad decision preserves the decision; the redo itself is the\n   caller's, after the ledger is reviewed.\n4. **Bank every choice in the ledger** (below), and promote load-bearing\n   sound ones into the plan's handoff so later passes inherit them as givens\n   instead of re-deciding.\n5. **Present the ledger: grouped by verdict, ranked by confidence.** The\n   audit's deliverable is the ledger, handed to whoever acts next — the\n   calling workflow mid-run, the user at run's end. Each verdict group maps\n   to an action — needs-user (decide, with the provisional calls), unsound\n   (redo, with the corrected decisions), sound (acknowledge: the\n   architecture the user now owns) — and within each group choices are\n   ranked by confidence, least confident first. When the ledger is long,\n   open the report with the two or three least-confident choices overall,\n   whatever their group: the \"review these first\" line. Sound is not\n   skippable. Only trivial discretion (internal naming, cosmetic calls)\n   compresses to a one-line count.\n\n   **Write every entry ELI5 — by default, not on request.** The reader\n   didn't live the session: write each entry in the\n   [eli5](..\u002Feli5\u002FSKILL.md) register — a concrete scenario walked end to\n   end (the triggering event, what the work does today, what the unbuilt\n   alternative would do), every term of art defined at first use, and\n   pseudocode at the level of the decision when the choice is about control\n   flow, ordering, or timing. \"A gated ask is dropped, not deferred\" is a\n   headline, not an entry. A compressed entry that makes the user ask\n   \"explain this one\" has failed; the ledger must stand alone without the\n   diff, the spec, or the transcript.\n\n## The Choices Ledger\n\nA dedicated file that outlives every pass: `choices.md` beside the plan\n(`specs\u002F\u003Cfeature>\u002Fchoices.md` when a spec owns the work). One entry per\naudited choice:\n\n- **When** — pass or commit it landed in.\n- **The choice** — a one-line headline, then the ELI5 scenario: the\n  triggering event, what the work does today, what the unbuilt alternative\n  would do, with terms of art defined in place.\n- **The gap** — what the plan left unspecified that forced it.\n- **The reach** — what future work this decision constrains or enables; why\n  the user needs to know it exists.\n- **Verdict** — sound \u002F unsound \u002F needs-user, with a one-line why. For\n  unsound: the corrected decision to redo from. For needs-user: the\n  recommended provisional call and how to reverse it.\n- **Confidence** — how sure the audit is that the user would have made the\n  same call (low \u002F medium \u002F high). Ranks the report, ascending.\n\nRules of the ledger:\n\n- Banked is settled: a choice already in the ledger (or promoted into the\n  plan) is a given for later passes — never re-listed, never re-decided.\n- The ledger is a plan-quality signal. Entries clustering around one slice or\n  area mean the plan is foggy there — reslice or send that part back through\n  the spec rather than triaging the same class of choice forever.\n- **ELI5 survives every rewrite.** The entry format above — headline plus the\n  walked scenario with terms defined in place — is the *storage* format, not\n  presentation polish. When entries are consolidated, merged, re-audited at\n  close, or copied into a final ledger, each surviving entry keeps (or\n  regains) its full scenario. The known failure mode is exactly this\n  compression: a closeout rewrite that shrinks banked entries to their\n  headlines produces a ledger the reader must interrogate — \"The checkpoint\n  loads rows in mailbox order and rejects the list when a later reference\n  has an earlier createdAt\" reads as settled, but only the walked version\n  (two sessions, per-session sequence numbers that can't be compared, the\n  shared insert-timestamp clock) lets a reader actually judge the choice. A\n  consolidation that drops scenarios has failed even if every fact survives —\n  and so has one that keeps the scenario but leans on labels the build\n  invented (\"the retry envelope\", \"the evidence seam\") without defining them\n  where they're used.\n\n## Rules\n\n- **\"It works\" is not a verdict on the choice.** The recurring smell is the\n  coincidental fix: a resized buffer, bumped timeout, or special case whose\n  magnitude happens to cover the failing input while the underlying cause\n  stays dormant. Ask what property *guarantees* the fix in general; if the\n  answer is \"this case passes,\" the choice is unsound even though the code is\n  green.\n- Declared success is the point of maximum risk — the implementer's confidence\n  is highest exactly when its unexamined choices are about to be merged. Never\n  skip the audit because the result looks clean.\n- An empty list on nontrivial work is a red flag, not a pass. Probe: what did\n  the task leave unspecified? Something filled those gaps.\n- The audit changes no code, tests, or build state. Finding an unsound choice\n  is the deliverable, not a license to fix it — record the corrected decision\n  and leave the tree exactly as audited, so the ledger and the tree agree on\n  what the caller is deciding about. Evidence-gathering is fair game: read\n  anything, run the existing tests, write transient probes — but remove every\n  probe before handback.\n\n## Done\n\nThe audit is done when every invented choice in the pass has a ledger entry\nwith a verdict, every unsound entry names the corrected decision to redo\nfrom, every needs-user entry carries a reversible provisional call, and the\nledger has been presented — grouped by verdict, least-confident-first within\neach group, every entry readable ELI5 without follow-up questions — to\nwhoever acts next, with the tree untouched. A handback that shows the diff\ninstead of the choices, or a \"fix\" applied during the audit, is not done.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Faudit-choices",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill audit-choices",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill audit-choices",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill audit-choices","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Faudit-choices\u002FSKILL.md",true,[],[47,55,60,67,74,81],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":56,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":54},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":54},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":54},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":54},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":54},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]