[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7432D4VG1B0YWD4572NN7NK":3,"skill-same:01M7432D4VG1B0YWD4572NN7NK":46},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7432D4VG1B0YWD4572NN7NK","pair-benchmark-all-executors",null,"Run one benchmark script that compares pairv2, pair via Claude Teams, and pair via direct Python","jleechanorg\u002Fjleechan-skills","jleechanorg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221404966?v=4","01M6C1VJ99XG950X1DWPEBCBGX","01M6C1VJDK5YVDNT3362RT5WSB",6,"MIT","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-11-09-no-usage-evidence\u002Fpair-benchmark-all-executors\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: pair-benchmark-all-executors\ndescription: Run one benchmark script that compares pairv2, pair via Claude Teams, and pair via direct Python\ntype: usage\nscope: project\n---\n\n# Pair Benchmark (All Executors)\n\n## Purpose\nUse one script to benchmark all pair executors:\n- `pairv2` (`.claude\u002Fpair\u002Fpair_execute_v2.py`)\n- `\u002Fpair` via Claude Teams prompt path\n- `\u002Fpair` via direct Python (`.claude\u002Fpair\u002Fpair_execute.py`)\n\n## Script\n`python .claude\u002Fpair\u002Fbenchmark_pair_executors.py` (or `venv\u002Fbin\u002Fpython` when using a virtualenv)\n\n## Quick Start\nRun all three executors in one benchmark:\n\n```bash\npython .claude\u002Fpair\u002Fbenchmark_pair_executors.py \\\n  --executor-set all \\\n  --benchmark-iterations 1 \\\n  --timeout-seconds 180 \\\n  --teams-command \"claude --print\" \\\n  --artifact \u002Ftmp\u002F{repo}\u002F{branch}\u002Fpair\u002Fall_three.json\n```\n\nRun a small, named Amazon-style ecommerce preset:\n\n```bash\npython .claude\u002Fpair\u002Fbenchmark_pair_executors.py \\\n  --task-preset amazon_clone \\\n  --pairv2-max-cycles 2 \\\n  --timeout-seconds 1200 \\\n  --artifact \u002Ftmp\u002F{repo}\u002F{branch}\u002Fpair\u002Famazon_clone_benchmark.json\n```\n\nFor historical benchmark prompts, including alternate Amazon-style variants, see\n`testing_llm\u002Fpair\u002Fbenchmark_tasks.json`.\n\nRun all three in parallel:\n\n```bash\npython .claude\u002Fpair\u002Fbenchmark_pair_executors.py \\\n  --executor-set all \\\n  --parallel \\\n  --benchmark-iterations 1 \\\n  --timeout-seconds 180 \\\n  --teams-command \"claude --print\" \\\n  --artifact \u002Ftmp\u002F{repo}\u002F{branch}\u002Fpair\u002Fall_three_parallel.json\n```\n\n## Executor Modes\n- `--executor-set all`: pair python + pair teams + pairv2\n- `--executor-set legacy-vs-v2`: pair python vs pairv2\n- `--executor-set teams-vs-v2`: pair teams vs pairv2\n- `--executor-set pairv2-only`: pairv2 only\n\n## Key Output Fields\n- `pair_python`, `pair_python_status_counts`, `pair_python_raw`\n- `pair_claude_teams`, `pair_teams_status_counts`, `pair_teams_raw`\n- `pairv2_langgraph`, `pairv2_status_counts`, `pairv2_raw`\n- `speedup_ratio_pair_python_over_v2`\n- `speedup_ratio_pair_teams_over_v2`\n- `speedup_ratio_pair_python_over_teams`\n\n## Current Defaults (updated Feb 2026)\n\n- `--executor-set`: `pairv2-only`\n- `--coder-cli`: `minimax`\n- `--verifier-cli`: `minimax`\n- `--task`: hello world script + pytest test (default); overridden by `--task-preset` when provided\n- `--timeout-seconds`: `600`\n\nRun with no args to use these defaults:\n```bash\nvenv\u002Fbin\u002Fpython .claude\u002Fpair\u002Fbenchmark_pair_executors.py\n```\n\n## Notes\n- **`minimax` is not a CLI binary** — it runs `claude` with MiniMax API endpoint.\n","# Pair Benchmark (All Executors)\n\n## Purpose\nUse one script to benchmark all pair executors:\n- `pairv2` (`.claude\u002Fpair\u002Fpair_execute_v2.py`)\n- `\u002Fpair` via Claude Teams prompt path\n- `\u002Fpair` via direct Python (`.claude\u002Fpair\u002Fpair_execute.py`)\n\n## Script\n`python .claude\u002Fpair\u002Fbenchmark_pair_executors.py` (or `venv\u002Fbin\u002Fpython` when using a virtualenv)\n\n## Quick Start\nRun all three executors in one benchmark:\n\n```bash\npython .claude\u002Fpair\u002Fbenchmark_pair_executors.py \\\n  --executor-set all \\\n  --benchmark-iterations 1 \\\n  --timeout-seconds 180 \\\n  --teams-command \"claude --print\" \\\n  --artifact \u002Ftmp\u002F{repo}\u002F{branch}\u002Fpair\u002Fall_three.json\n```\n\nRun a small, named Amazon-style ecommerce preset:\n\n```bash\npython .claude\u002Fpair\u002Fbenchmark_pair_executors.py \\\n  --task-preset amazon_clone \\\n  --pairv2-max-cycles 2 \\\n  --timeout-seconds 1200 \\\n  --artifact \u002Ftmp\u002F{repo}\u002F{branch}\u002Fpair\u002Famazon_clone_benchmark.json\n```\n\nFor historical benchmark prompts, including alternate Amazon-style variants, see\n`testing_llm\u002Fpair\u002Fbenchmark_tasks.json`.\n\nRun all three in parallel:\n\n```bash\npython .claude\u002Fpair\u002Fbenchmark_pair_executors.py \\\n  --executor-set all \\\n  --parallel \\\n  --benchmark-iterations 1 \\\n  --timeout-seconds 180 \\\n  --teams-command \"claude --print\" \\\n  --artifact \u002Ftmp\u002F{repo}\u002F{branch}\u002Fpair\u002Fall_three_parallel.json\n```\n\n## Executor Modes\n- `--executor-set all`: pair python + pair teams + pairv2\n- `--executor-set legacy-vs-v2`: pair python vs pairv2\n- `--executor-set teams-vs-v2`: pair teams vs pairv2\n- `--executor-set pairv2-only`: pairv2 only\n\n## Key Output Fields\n- `pair_python`, `pair_python_status_counts`, `pair_python_raw`\n- `pair_claude_teams`, `pair_teams_status_counts`, `pair_teams_raw`\n- `pairv2_langgraph`, `pairv2_status_counts`, `pairv2_raw`\n- `speedup_ratio_pair_python_over_v2`\n- `speedup_ratio_pair_teams_over_v2`\n- `speedup_ratio_pair_python_over_teams`\n\n## Current Defaults (updated Feb 2026)\n\n- `--executor-set`: `pairv2-only`\n- `--coder-cli`: `minimax`\n- `--verifier-cli`: `minimax`\n- `--task`: hello world script + pytest test (default); overridden by `--task-preset` when provided\n- `--timeout-seconds`: `600`\n\nRun with no args to use these defaults:\n```bash\nvenv\u002Fbin\u002Fpython .claude\u002Fpair\u002Fbenchmark_pair_executors.py\n```\n\n## Notes\n- **`minimax` is not a CLI binary** — it runs `claude` with MiniMax API endpoint.\n",{"name":5,"type":23,"scope":24,"description":7},"usage","project","main","50e7fa573f58907a944e9c70833c315899ebb57c",".claude\u002Fskills_archive\u002F2026-11-09-no-usage-evidence\u002Fpair-benchmark-all-executors",0,"https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills","https:\u002F\u002Fgithub.com\u002Fjleechanorg","2026-11-14 14:55:35",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add jleechanorg\u002Fjleechan-skills --skill pair-benchmark-all-executors",{"tool":38,"command":39},"bunx","bunx skills add jleechanorg\u002Fjleechan-skills --skill pair-benchmark-all-executors",{"tool":41,"command":42},"pnpm","pnpm dlx skills add jleechanorg\u002Fjleechan-skills --skill pair-benchmark-all-executors","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-11-09-no-usage-evidence\u002Fpair-benchmark-all-executors\u002FSKILL.md",true,[],[47,55,62,70,77,86],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"01M7DRVZXXMGY4G81K5GVF4V20","disk-reclaim-playbook","Use Disk Magician to diagnose disk growth or qualify cleanup on macOS or Linux.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdisk-reclaim-playbook\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":54},"01M7B63PNTT2TY78RFKHD8SP3X","claudea-bench","Compare `claudea` and normal `claude` on a fair split of comparable work by default; use `--strict` for duplicate runs of the exact same task.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fclaudea-bench\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":69},"01M7622KQJ32AV4K5BXEMVSSEB","pr","Alias for the canonical pr-lifecycle PR workflow skill (\u002Fpr-workflow, \u002Fprw).","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fpr\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M7432W92AKC4D1TKJ00VCMMT","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-11-09-no-usage-evidence\u002Fwhisper\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":81,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7432T6BN1A9SHB8RBQR5EMP","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-11-09-no-usage-evidence\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-11-09-no-usage-evidence\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7432NDC7S6C6MX7M6RW8CTT","pr-report","This skill should be used when the user asks for a PR report, PR audit, PR delta analysis, \u002Fpr-report, or wants per-PR summary with delta files\u002Flines. Generates a structured report for one or more open PRs covering purpose, files changed, +\u002F− line counts, \u002Fcode-standards + \u002Fthermo review findings, \u002Fponytail simplification opportunities, file-overlap combination candidates, and \u002Fgreen status per pr-green-definition. Output: machine-readable JSONL + human-readable markdown. Read-only by default; can apply simplifications if user opts in.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-11-09-no-usage-evidence\u002Fpr-report\u002FSKILL.md",[],[]]