[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79EGGGMCPH9MC9DN19TBVSC":3,"skill-same:01M79EGGGMCPH9MC9DN19TBVSC":65},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79EGGGMCPH9MC9DN19TBVSC","benchmark-checklist",null,"Check whether a measured speedup, regression or tool comparison is valid before reporting it or choosing an option.","AO-HyS\u002Fdevelopment-system","AO-HyS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286554351?v=4","01M79DCXZGC6076EH5QATNXCY2","AO HyS","01M79DCY06TSBCJ946VP0BT0RG",0,"MIT","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.1.4\u002Fskills\u002Fexternal\u002Fbenchmark-checklist\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.1.4\u002Fskills\u002Fexternal\u002Fbenchmark-checklist\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: benchmark-checklist\ndescription: Check whether a measured speedup, regression or tool comparison is valid before reporting it or choosing an option.\n---\n\n# Benchmark checklist\n\nAdapted from Poteto's PStack, based on Brendan Gregg's benchmarking checklist.\nSee [provenance and adaptations](UPSTREAM.md) when updating.\n\nUse existing measurements or an authorized bounded comparison. This skill does\nnot authorize new paid services, production workloads or an automated evaluation\nplatform. If no measurement exists, report the missing evidence; do not invent\na benchmark merely to exercise the skill.\n\n## Define the claim\n\nWrite the exact claim and its scope before measuring: operation, dataset,\nenvironment, versions, completion condition and time boundary. Inspect the\nmeasurement mechanism and what it excludes. Separate preparation, first run,\nreplay, retries, corrections and total usable-result time for agent workflows.\nUse identical starting state, task context and expected outcomes per option.\n\nCheck machine load and concurrency. On macOS use `uptime` and\n`sysctl -n hw.logicalcpu`; use available platform equivalents elsewhere.\nPreserve unrelated processes. Interleave options to reduce drift and disclose\nremaining interference. Keep profiling separate from reported timing.\n\n## Validate the evidence\n\n1. **Limiter:** locate the bottleneck using relevant observations. A saturated\n   driver or wait outside the operation can dominate the measured time.\n2. **Configuration:** use representative builds, data, cache state, connection\n   settings and supported tuning for both options. Name model\u002Fprovider changes\n   separately; a combined comparison cannot isolate the tool's contribution.\n3. **Plausibility:** compare throughput with available CPU, disk or network and\n   the original share of time. An implausible gain may be a cache hit or no-op.\n4. **Correctness:** count failures, omissions, retries and false positives.\n   Inspect the expected result. Fast rejection or skipped work is not success.\n5. **Repeatability:** for an adoption comparison, aim for at least five\n   alternating successful runs per option within the authorized limits, report\n   all attempts and failures, plus median and range. Retain failures rather\n   than timing successes alone. If scope or resources permit fewer runs, label\n   the result preliminary; do not quietly increase limits or pick a winner\n   from a difference within observed variation. A requested one-run estimate\n   remains an estimate and still requires correctness and actual-work checks.\n6. **Practical effect:** report total time to the usable outcome alongside a\n   micro measurement. Include resource consumption or cost only when observed.\n7. **Actual work:** confirm that the operation ran inside the timed interval\n   and its result was consumed. Inspect relevant persistence, server receipt or\n   visible state through the authorized verification channel.\n\n## Report\n\nConclude faster, slower, no measurable difference or inconclusive for the stated\nscope. Include units, run counts, all failure counts, range, environment and\nlimiter; link detailed evidence from the existing task record. Missing correct\noutputs, unbalanced configuration or unobserved work prevents an adoption claim.\nDo not infer product acceptance from timing or attribute savings causally when\nthe comparison did not control the relevant variables.\n","# Benchmark checklist\n\nAdapted from Poteto's PStack, based on Brendan Gregg's benchmarking checklist.\nSee [provenance and adaptations](UPSTREAM.md) when updating.\n\nUse existing measurements or an authorized bounded comparison. This skill does\nnot authorize new paid services, production workloads or an automated evaluation\nplatform. If no measurement exists, report the missing evidence; do not invent\na benchmark merely to exercise the skill.\n\n## Define the claim\n\nWrite the exact claim and its scope before measuring: operation, dataset,\nenvironment, versions, completion condition and time boundary. Inspect the\nmeasurement mechanism and what it excludes. Separate preparation, first run,\nreplay, retries, corrections and total usable-result time for agent workflows.\nUse identical starting state, task context and expected outcomes per option.\n\nCheck machine load and concurrency. On macOS use `uptime` and\n`sysctl -n hw.logicalcpu`; use available platform equivalents elsewhere.\nPreserve unrelated processes. Interleave options to reduce drift and disclose\nremaining interference. Keep profiling separate from reported timing.\n\n## Validate the evidence\n\n1. **Limiter:** locate the bottleneck using relevant observations. A saturated\n   driver or wait outside the operation can dominate the measured time.\n2. **Configuration:** use representative builds, data, cache state, connection\n   settings and supported tuning for both options. Name model\u002Fprovider changes\n   separately; a combined comparison cannot isolate the tool's contribution.\n3. **Plausibility:** compare throughput with available CPU, disk or network and\n   the original share of time. An implausible gain may be a cache hit or no-op.\n4. **Correctness:** count failures, omissions, retries and false positives.\n   Inspect the expected result. Fast rejection or skipped work is not success.\n5. **Repeatability:** for an adoption comparison, aim for at least five\n   alternating successful runs per option within the authorized limits, report\n   all attempts and failures, plus median and range. Retain failures rather\n   than timing successes alone. If scope or resources permit fewer runs, label\n   the result preliminary; do not quietly increase limits or pick a winner\n   from a difference within observed variation. A requested one-run estimate\n   remains an estimate and still requires correctness and actual-work checks.\n6. **Practical effect:** report total time to the usable outcome alongside a\n   micro measurement. Include resource consumption or cost only when observed.\n7. **Actual work:** confirm that the operation ran inside the timed interval\n   and its result was consumed. Inspect relevant persistence, server receipt or\n   visible state through the authorized verification channel.\n\n## Report\n\nConclude faster, slower, no measurable difference or inconclusive for the stated\nscope. Include units, run counts, all failure counts, range, environment and\nlimiter; link detailed evidence from the existing task record. Missing correct\noutputs, unbalanced configuration or unobserved work prevents an adoption claim.\nDo not infer product acceptance from timing or attribute savings causally when\nthe comparison did not control the relevant variables.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F2.1.4\u002Fskills\u002Fexternal\u002Fbenchmark-checklist","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system","https:\u002F\u002Fgithub.com\u002FAO-HyS","https:\u002F\u002Faohys.net\u002F","Software Boutique, we make your projects come true live. ","2026-11-14 03:17:27",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add AO-HyS\u002Fdevelopment-system --skill benchmark-checklist",{"tool":39,"command":40},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill benchmark-checklist",{"tool":42,"command":43},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill benchmark-checklist","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.1.4\u002Fskills\u002Fexternal\u002Fbenchmark-checklist\u002FSKILL.md",true,[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",309,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.1.4\u002Fskills\u002Fexternal\u002Fbenchmark-checklist\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":16},"LICENSE","许可证",1067,{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"upstream.json",374,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.1.4\u002Fskills\u002Fexternal\u002Fbenchmark-checklist\u002Fupstream.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"UPSTREAM.md",1146,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.1.4\u002Fskills\u002Fexternal\u002Fbenchmark-checklist\u002FUPSTREAM.md",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":20},"01M79EQ4BPYQTX8RWN1Y1J2K1F","working-backwards","Define a software feature through PRFAQ and staged documents when the user requests working backwards before coding.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fworking-backwards\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":20},"01M79EQ2E8P85Y1Y7VNJZMNEJE","flow-implement","Implement a requested software change through verification, corrections, and its authorized delivery endpoint.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fflow-implement\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":20},"01M79EQ0PNMKHPJ78F8WMNX06P","development-steward","Run the scheduled, read-only weekly maintenance review for the six explicitly opted-in repositories and prepare one concise private report for Check-in.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fdevelopment-steward\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":20},"01M79EPXJ56MX7955GWP1HD4B0","grill-with-docs","Run one recoverable interview for functional, visual, or mixed software grills; reuse equivalent answers and offer the shared HTML questionnaire.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Finternal\u002Fgrill-with-docs\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":20},"01M79EPTFPHYEV40ZG52Z0GVS2","global-agent-guardrails","Install, audit, test, or update the Development System's global destructive-command guard for Codex, Claude Code and T3 Code. Use when configuring agent safety hooks or investigating whether dangerous shell operations are blocked.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Finternal\u002Fglobal-agent-guardrails\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":105,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":20},"01M79EPR0KPHKAFN7V6CEEDR0Y","impeccable","Design or refine frontend UI using project context and a focused design playbook; also handles visual critique and polish.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Fexternal\u002Fimpeccable\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Fexternal\u002Fimpeccable\u002FSKILL.md",[],[]]