[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDX5HHAKK2B2YMAX1KNE2T":3,"skill-same:01M7FDX5HHAKK2B2YMAX1KNE2T":52},{"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},"01M7FDX5HHAKK2B2YMAX1KNE2T","benchmark-methodology",null,"Use after competitive-platform-analysis has produced a tiered competitor set. Scores each competitor across nine weighted dimensions (positioning, voice, visual craft, offer packaging, evidence, enterprise-readiness, thought leadership, pricing, client's strategic tension) with explicit 1–5 rubrics and a tension-plot. Precedes competitive-report-structure.","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\u002F07-后端与架构\u002Fbenchmark-methodology-ECC\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: benchmark-methodology\ndescription: >-\n  Use after competitive-platform-analysis has produced a tiered competitor set.\n  Scores each competitor across nine weighted dimensions (positioning, voice,\n  visual craft, offer packaging, evidence, enterprise-readiness, thought\n  leadership, pricing, client's strategic tension) with explicit 1–5 rubrics\n  and a tension-plot. Precedes competitive-report-structure.\n---\n\n# Benchmark Methodology\n\nUse this skill to turn a scoped competitor set into **comparable, defensible\nscores**. Each competitor is assessed on the same nine dimensions, with\nexplicit 1–5 rubrics, then captured in a uniform profile card. Consistency is\nthe point: scores are only useful if the same evidence would earn the same\nnumber for any competitor.\n\n## When to Activate\n\n- A scoped, tiered competitor set from competitive-platform-analysis is ready to score.\n- Need comparable, evidence-anchored scores across competitors — not gut-feel rankings.\n- Client's strategic tension (the paired axes defining their target white-space) has been established.\n- Preparing to produce profile cards for assembly in competitive-report-structure.\n\n## Client positioning brief (establish first)\n\nBefore scoring, establish the client's positioning brief. It supplies:\n\n- **Strategic tension** — the two axes (e.g., memorability × hireability) whose\n  intersection marks the client's target white-space. Dimension 9 is always\n  the client's named tension; report both poles separately, never averaged.\n- **Differentiator** — what makes the client's moat. This informs which\n  dimensions matter most for the client's positioning argument.\n- **Brand balance** — the intended mix of distinct strategic emphases. Strategic\n  recommendations must not break this balance without flagging it.\n\n## Why these dimensions\n\nThe client competes on a **specific tension held across two poles**, not on\nservice breadth. The dimensions are weighted to reflect that moat. Two\ndimensions — the tension poles — are scored **separately and never averaged\ntogether**, because the client's strategic question is precisely whether a rival\nachieves both simultaneously.\n\n## The nine dimensions (with weights)\n\nWeights guide synthesis emphasis, not a single blended score (avoid a false\ncomposite — see Bias controls). Sum = 100%.\n\n1. **Positioning clarity & distinctiveness** (18%) — Is the studio's position\n   sharp, ownable, and instantly legible? Or generic?\n2. **Brand voice \u002F verbal distinctiveness** (15%) — Does the copy have an\n   ownable register, or is it interchangeable agency-speak?\n3. **Visual identity & site craft** (15%) — Quality and ownership of the visual\n   system; site as proof-of-craft.\n4. **Service offer & packaging** (12%) — Productized and legible (named\n   sprints\u002Faudits) vs vague. Packaging maturity.\n5. **Evidence & credibility** (12%) — Named clients, quantified outcomes,\n   case-study depth. Proof beyond assertion.\n6. **Enterprise-readiness \u002F commercial maturity** (10%) — Signals they can land\n   and hold SaaS\u002Ffintech\u002FB2B\u002Fenterprise work (process, logos, scale, contracts).\n7. **Thought leadership \u002F content presence** (8%) — Owned POV: writing, talks,\n   newsletters, frameworks. Depth over volume.\n8. **Pricing transparency & engagement model** (5%) — Is pricing\u002Fengagement\n   legible? Productized vs bespoke vs opaque.\n9. **[Client's strategic tension]** (5% as a flag; **score BOTH poles,\n   report separately**) — Read the tension name and axis descriptions from the\n   client's positioning brief. Plot both; the gap is the insight. The client's\n   target quadrant is the single most important finding: who else is already\n   there?\n\n## Scoring rubric (1–5, applies to dimensions 1–8)\n\nAnchor every score to observable evidence. Generic descriptors below; adapt the\nspecifics per dimension but keep the level meaning constant.\n\n- **1 — Absent \u002F generic.** No discernible position or craft; indistinguishable\n  from a template. Active liability.\n- **2 — Below par.** Some intent but inconsistent, derivative, or unconvincing.\n  Wouldn't survive a side-by-side.\n- **3 — Competent \u002F table-stakes.** Solid, professional, unremarkable. Meets\n  expectation, ownable by nobody.\n- **4 — Strong \u002F distinctive.** Clearly above peers; a real strength a buyer\n  would notice and cite.\n- **5 — Category-defining.** Best-in-class, ownable, hard to imitate. Sets the\n  bar others react to.\n\n### Tension axes (dimension 9) — score each 1–5\n\nRead the axis labels and their 1\u002F3\u002F5 anchors from the client's positioning\nbrief. Example anchors for a memorability × credibility tension:\n\n- **Memorability** — 1: forgotten instantly · 3: recognizable in context ·\n  5: unforgettable, talked-about, distinctively owned.\n- **Credibility** — 1: feels risky\u002Famateur · 3: safe, competent,\n  unexciting · 5: enterprise-trusted, obvious safe choice.\n\nPlot competitors on the tension 2×2. The client's target quadrant is named in\nthe positioning brief. Who else occupies that quadrant is the single most\nimportant finding of the benchmark.\n\n## How to collect the data\n\nFor each competitor, work the dimensions in this order (cheapest signal first):\n\n1. **Competitor's own site** — positioning, voice, offer packaging, pricing\n   posture, named clients, manifesto\u002FPOV. Screenshot the homepage + one case\n   study.\n2. **Case studies \u002F work** — evidence depth, quantified outcomes, client names.\n   Distinguish *asserted* (\"we delivered X\") from *proven* (metrics, named,\n   verifiable).\n3. **Review directories** — corroborate clients, project size, engagement model\n   → credibility & enterprise-readiness (e.g. Clutch.co or the niche equivalent).\n4. **LinkedIn** — team size\u002Fmodel, founder narrative, content cadence →\n   thought leadership, model.\n5. **Portfolio \u002F craft platforms** — craft register (use the showcase native to\n   the niche: design boards, showreels, published samples, etc.).\n6. **Content channels** — newsletter\u002Ftalks\u002Fwriting → thought-leadership depth.\n\n**What to record per dimension:** the score, one-line justification, and the\nsource link\u002Fscreenshot that earned it. No score without evidence.\n\n## Bias controls\n\n- **No single composite score.** Report dimension scores and the tension plot\n  separately. A weighted average hides the asymmetry that matters.\n- **Asserted vs proven.** Downgrade credibility\u002Fevidence scores for\n  self-reported claims with no corroboration. Site copy is marketing, not fact.\n- **Aesthetic affinity bias.** Reviewers may over-score studios whose aesthetic\n  they share and under-score rivals' commercial strength. Score craft and\n  credibility independently; a \"boring\" site may be winning bigger clients.\n- **Recency \u002F flashiness bias.** Award-winning, showpiece work dazzles but may\n  lack commercial depth — verify with directories\u002Fclients before scoring\n  credibility.\n- **Survivorship.** The visible, well-marketed studios aren't the whole market;\n  note strong-but-quiet operators found via directories\u002Freviews.\n- **Calibrate across the set, not in isolation.** Before finalizing, re-read\n  scores side-by-side — a \"4\" must mean the same thing for every competitor.\n  Adjust outliers.\n\n## Competitor profile card (output format)\n\nProduce one card per profiled competitor — the atomic unit the report assembles\nfrom:\n\n```\n## \u003CCompetitor name>\n- **Profile \u002F Tier:** \u003Cpositioning stance · specialization · size band> \u002F \u003CDirect | Adjacent | Aspirational>\n- **One-liner:** \u003Chow they position themselves, in their words>\n- **Model \u002F size \u002F geography:** \u003Csolo|micro|boutique> · \u003Cregion> · \u003Cpricing\u002Fengagement model>\n- **Notable clients \u002F evidence:** \u003Cnamed, with proven\u002Fasserted tag>\n\n### Dimension scores\n| Dimension | Score (1–5) | Justification (1 line) | Source |\n|---|---|---|---|\n| Positioning clarity & distinctiveness | | | |\n| Brand voice \u002F verbal distinctiveness | | | |\n| Visual identity & site craft | | | |\n| Service offer & packaging | | | |\n| Evidence & credibility | | | |\n| Enterprise-readiness \u002F commercial maturity | | | |\n| Thought leadership \u002F content presence | | | |\n| Pricing transparency & engagement model | | | |\n\n### Tension plot\n- **[Axis 1 from positioning brief]:** \u003C1–5> — \u003Cwhy>\n- **[Axis 2 from positioning brief]:** \u003C1–5> — \u003Cwhy>\n- **Quadrant:** \u003Chigh\u002Fhigh | high-1\u002Flow-2 | low-1\u002Fhigh-2 | low\u002Flow>\n\n### Read for [client]\n- **Strength to learn from:** \u003C…>\n- **Weakness to exploit \u002F white-space it exposes:** \u003C…>\n- **Threat to [client]:** \u003C…>\n```\n\nHand the completed cards plus the tension plot to `competitive-report-structure`.\n\n## Anti-Patterns\n\n- **Averaging the tension axes.** The two poles of the client's strategic tension must be scored and reported separately. Averaging destroys the insight — the gap between poles is the finding.\n- **Scoring without evidence.** Every score requires a one-line justification and a source link. A score without evidence is an opinion, not a benchmark.\n- **Creating a single composite score.** Report dimension scores individually. A weighted average hides the asymmetric strengths that matter for positioning.\n- **Applying generic rubric anchors without adapting.** The 1–5 anchors must be calibrated to the specific dimension and competitor set. The generic descriptions are a starting point, not a fixed standard.\n- **Running before the competitor set is scoped.** Use competitive-platform-analysis first to produce a tiered, pruned set. Scoring an unscoped list wastes effort on irrelevant competitors.\n\n## Related Skills\n\n- `competitive-platform-analysis` — the prerequisite; produces the tiered competitor set this skill scores.\n- `competitive-report-structure` — the next step; assembles the scored profile cards into a client-deliverable report.\n","# Benchmark Methodology\n\nUse this skill to turn a scoped competitor set into **comparable, defensible\nscores**. Each competitor is assessed on the same nine dimensions, with\nexplicit 1–5 rubrics, then captured in a uniform profile card. Consistency is\nthe point: scores are only useful if the same evidence would earn the same\nnumber for any competitor.\n\n## When to Activate\n\n- A scoped, tiered competitor set from competitive-platform-analysis is ready to score.\n- Need comparable, evidence-anchored scores across competitors — not gut-feel rankings.\n- Client's strategic tension (the paired axes defining their target white-space) has been established.\n- Preparing to produce profile cards for assembly in competitive-report-structure.\n\n## Client positioning brief (establish first)\n\nBefore scoring, establish the client's positioning brief. It supplies:\n\n- **Strategic tension** — the two axes (e.g., memorability × hireability) whose\n  intersection marks the client's target white-space. Dimension 9 is always\n  the client's named tension; report both poles separately, never averaged.\n- **Differentiator** — what makes the client's moat. This informs which\n  dimensions matter most for the client's positioning argument.\n- **Brand balance** — the intended mix of distinct strategic emphases. Strategic\n  recommendations must not break this balance without flagging it.\n\n## Why these dimensions\n\nThe client competes on a **specific tension held across two poles**, not on\nservice breadth. The dimensions are weighted to reflect that moat. Two\ndimensions — the tension poles — are scored **separately and never averaged\ntogether**, because the client's strategic question is precisely whether a rival\nachieves both simultaneously.\n\n## The nine dimensions (with weights)\n\nWeights guide synthesis emphasis, not a single blended score (avoid a false\ncomposite — see Bias controls). Sum = 100%.\n\n1. **Positioning clarity & distinctiveness** (18%) — Is the studio's position\n   sharp, ownable, and instantly legible? Or generic?\n2. **Brand voice \u002F verbal distinctiveness** (15%) — Does the copy have an\n   ownable register, or is it interchangeable agency-speak?\n3. **Visual identity & site craft** (15%) — Quality and ownership of the visual\n   system; site as proof-of-craft.\n4. **Service offer & packaging** (12%) — Productized and legible (named\n   sprints\u002Faudits) vs vague. Packaging maturity.\n5. **Evidence & credibility** (12%) — Named clients, quantified outcomes,\n   case-study depth. Proof beyond assertion.\n6. **Enterprise-readiness \u002F commercial maturity** (10%) — Signals they can land\n   and hold SaaS\u002Ffintech\u002FB2B\u002Fenterprise work (process, logos, scale, contracts).\n7. **Thought leadership \u002F content presence** (8%) — Owned POV: writing, talks,\n   newsletters, frameworks. Depth over volume.\n8. **Pricing transparency & engagement model** (5%) — Is pricing\u002Fengagement\n   legible? Productized vs bespoke vs opaque.\n9. **[Client's strategic tension]** (5% as a flag; **score BOTH poles,\n   report separately**) — Read the tension name and axis descriptions from the\n   client's positioning brief. Plot both; the gap is the insight. The client's\n   target quadrant is the single most important finding: who else is already\n   there?\n\n## Scoring rubric (1–5, applies to dimensions 1–8)\n\nAnchor every score to observable evidence. Generic descriptors below; adapt the\nspecifics per dimension but keep the level meaning constant.\n\n- **1 — Absent \u002F generic.** No discernible position or craft; indistinguishable\n  from a template. Active liability.\n- **2 — Below par.** Some intent but inconsistent, derivative, or unconvincing.\n  Wouldn't survive a side-by-side.\n- **3 — Competent \u002F table-stakes.** Solid, professional, unremarkable. Meets\n  expectation, ownable by nobody.\n- **4 — Strong \u002F distinctive.** Clearly above peers; a real strength a buyer\n  would notice and cite.\n- **5 — Category-defining.** Best-in-class, ownable, hard to imitate. Sets the\n  bar others react to.\n\n### Tension axes (dimension 9) — score each 1–5\n\nRead the axis labels and their 1\u002F3\u002F5 anchors from the client's positioning\nbrief. Example anchors for a memorability × credibility tension:\n\n- **Memorability** — 1: forgotten instantly · 3: recognizable in context ·\n  5: unforgettable, talked-about, distinctively owned.\n- **Credibility** — 1: feels risky\u002Famateur · 3: safe, competent,\n  unexciting · 5: enterprise-trusted, obvious safe choice.\n\nPlot competitors on the tension 2×2. The client's target quadrant is named in\nthe positioning brief. Who else occupies that quadrant is the single most\nimportant finding of the benchmark.\n\n## How to collect the data\n\nFor each competitor, work the dimensions in this order (cheapest signal first):\n\n1. **Competitor's own site** — positioning, voice, offer packaging, pricing\n   posture, named clients, manifesto\u002FPOV. Screenshot the homepage + one case\n   study.\n2. **Case studies \u002F work** — evidence depth, quantified outcomes, client names.\n   Distinguish *asserted* (\"we delivered X\") from *proven* (metrics, named,\n   verifiable).\n3. **Review directories** — corroborate clients, project size, engagement model\n   → credibility & enterprise-readiness (e.g. Clutch.co or the niche equivalent).\n4. **LinkedIn** — team size\u002Fmodel, founder narrative, content cadence →\n   thought leadership, model.\n5. **Portfolio \u002F craft platforms** — craft register (use the showcase native to\n   the niche: design boards, showreels, published samples, etc.).\n6. **Content channels** — newsletter\u002Ftalks\u002Fwriting → thought-leadership depth.\n\n**What to record per dimension:** the score, one-line justification, and the\nsource link\u002Fscreenshot that earned it. No score without evidence.\n\n## Bias controls\n\n- **No single composite score.** Report dimension scores and the tension plot\n  separately. A weighted average hides the asymmetry that matters.\n- **Asserted vs proven.** Downgrade credibility\u002Fevidence scores for\n  self-reported claims with no corroboration. Site copy is marketing, not fact.\n- **Aesthetic affinity bias.** Reviewers may over-score studios whose aesthetic\n  they share and under-score rivals' commercial strength. Score craft and\n  credibility independently; a \"boring\" site may be winning bigger clients.\n- **Recency \u002F flashiness bias.** Award-winning, showpiece work dazzles but may\n  lack commercial depth — verify with directories\u002Fclients before scoring\n  credibility.\n- **Survivorship.** The visible, well-marketed studios aren't the whole market;\n  note strong-but-quiet operators found via directories\u002Freviews.\n- **Calibrate across the set, not in isolation.** Before finalizing, re-read\n  scores side-by-side — a \"4\" must mean the same thing for every competitor.\n  Adjust outliers.\n\n## Competitor profile card (output format)\n\nProduce one card per profiled competitor — the atomic unit the report assembles\nfrom:\n\n```\n## \u003CCompetitor name>\n- **Profile \u002F Tier:** \u003Cpositioning stance · specialization · size band> \u002F \u003CDirect | Adjacent | Aspirational>\n- **One-liner:** \u003Chow they position themselves, in their words>\n- **Model \u002F size \u002F geography:** \u003Csolo|micro|boutique> · \u003Cregion> · \u003Cpricing\u002Fengagement model>\n- **Notable clients \u002F evidence:** \u003Cnamed, with proven\u002Fasserted tag>\n\n### Dimension scores\n| Dimension | Score (1–5) | Justification (1 line) | Source |\n|---|---|---|---|\n| Positioning clarity & distinctiveness | | | |\n| Brand voice \u002F verbal distinctiveness | | | |\n| Visual identity & site craft | | | |\n| Service offer & packaging | | | |\n| Evidence & credibility | | | |\n| Enterprise-readiness \u002F commercial maturity | | | |\n| Thought leadership \u002F content presence | | | |\n| Pricing transparency & engagement model | | | |\n\n### Tension plot\n- **[Axis 1 from positioning brief]:** \u003C1–5> — \u003Cwhy>\n- **[Axis 2 from positioning brief]:** \u003C1–5> — \u003Cwhy>\n- **Quadrant:** \u003Chigh\u002Fhigh | high-1\u002Flow-2 | low-1\u002Fhigh-2 | low\u002Flow>\n\n### Read for [client]\n- **Strength to learn from:** \u003C…>\n- **Weakness to exploit \u002F white-space it exposes:** \u003C…>\n- **Threat to [client]:** \u003C…>\n```\n\nHand the completed cards plus the tension plot to `competitive-report-structure`.\n\n## Anti-Patterns\n\n- **Averaging the tension axes.** The two poles of the client's strategic tension must be scored and reported separately. Averaging destroys the insight — the gap between poles is the finding.\n- **Scoring without evidence.** Every score requires a one-line justification and a source link. A score without evidence is an opinion, not a benchmark.\n- **Creating a single composite score.** Report dimension scores individually. A weighted average hides the asymmetric strengths that matter for positioning.\n- **Applying generic rubric anchors without adapting.** The 1–5 anchors must be calibrated to the specific dimension and competitor set. The generic descriptions are a starting point, not a fixed standard.\n- **Running before the competitor set is scoped.** Use competitive-platform-analysis first to produce a tiered, pruned set. Scoring an unscoped list wastes effort on irrelevant competitors.\n\n## Related Skills\n\n- `competitive-platform-analysis` — the prerequisite; produces the tiered competitor set this skill scores.\n- `competitive-report-structure` — the next step; assembles the scored profile cards into a client-deliverable report.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","07-后端与架构\u002Fbenchmark-methodology-ECC",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 benchmark-methodology",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill benchmark-methodology",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill benchmark-methodology","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fbenchmark-methodology-ECC\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",272,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fbenchmark-methodology-ECC\u002Fagents\u002Fopenai.yaml",[53,60,65,72,79,86],{"skillNo":54,"name":55,"nameZh":6,"description":56,"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":19},"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",[],[],{"skillNo":61,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"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",[],[]]