[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E8DF6VA74SJZYPM54C75AA":3,"skill-same:01M7E8DF6VA74SJZYPM54C75AA":60},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":53},"01M7E8DF6VA74SJZYPM54C75AA","02-plan",null,"Use when ranking validated pytest speedups from 01-benchmark into an approved, ordered, commit-by-commit plan.","tony\u002Fskills","tony","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26336?v=4","01M72E5RNJ7SQV8F9KBM5RKRMN","Tony Narlock","01M7E7MBN5C6YZ4JJJ5Y82KBJG",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fpytest-optimizer\u002Fskills\u002F02-plan\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: 02-plan\ndescription: \"Use when ranking validated pytest speedups from 01-benchmark into an approved, ordered, commit-by-commit plan.\"\nallowed-tools: [\"Bash\", \"Read\", \"Grep\", \"Glob\", \"Write\", \"AskUserQuestion\"]\nargument-hint: \"[--max-commits=N] [--min-score=\u003C0..1>] [--force] [--memory-dir=\u003Cpath>]\"\ndisable-model-invocation: true\n---\n\n# 02-plan\n\nTurn measured candidates into a reviewable commit plan. This phase writes only\n`plan.json` and `state.json`, and only after the user approves.\n\n`$ARGUMENTS` may pass `--max-commits=N` to cap the plan, `--min-score` to raise the\ninclusion threshold, `--force` to recompute, and `--memory-dir` to override the\nmemory location.\n\nArithmetic goes through `..\u002F..\u002Fscripts\u002Fmeasure.py` and the staleness check\nthrough `..\u002F..\u002Fscripts\u002Fisolate.py` (Python 3 standard library). Both paths\nresolve from this skill's own directory, not the project's working directory:\nresolve this file's directory, join each path, print the absolute paths once,\nand write those literal paths in each command below where `\u003Cmeasure.py>` and\n`\u003Cisolate.py>` appear.\n\n## Step 1: Load and score\n\nResolve the memory directory by the lookup order in\n`..\u002F..\u002Freferences\u002Fmemory-schema.md`. If none exists or `benchmarks.json` is\nmissing, stop with the halted-run shape in `..\u002F..\u002Freferences\u002Foutput-contract.md`\nand tell the user to run `pytest-optimizer:01-benchmark` first.\n\nRead `benchmarks.json`, `baseline.json` and `state.json`. The evidence must\nstill describe this checkout (a clean scan at this `HEAD`, and every validated\nentry carrying the scan's `env_token`, a `patch_sha256` and this `HEAD` as its\n`base_head`):\n\n```console\n$ python3 \u003Cisolate.py> stale \\\n    --memory-dir \u003Cmemory-dir> \\\n    --phase plan\n```\n\nOn exit 1, stop with the halted-run shape and send the user to the phase its\n`rerun` names (`pytest-optimizer:` followed by it).\n\nScore every `validated` candidate with `..\u002F..\u002Freferences\u002Fscoring-rubric.md`:\njudge safety, effort, confidence and reversibility against the rubric anchors,\nthen pass them with the entry's measured saving. The script derives `impact`\nitself, zero unless the entry's `clears_noise` is true, and returns the total\nand a `dropped` reason (exit 1 when a dimension is outside 0 to 1):\n\n```console\n$ python3 \u003Cmeasure.py> score \\\n    --delta \u003Cmedian_delta> \\\n    --baseline \u003Cbaseline median> \\\n    --clears-noise \\\n    --safety \u003C0..1> \\\n    --effort \u003C0..1> \\\n    --confidence \u003C0..1> \\\n    --reversibility \u003C0..1>\n```\n\nLeave out `--clears-noise` when the entry's `clears_noise` is not true. A\ncandidate benchmarked as `kind: \"hygiene\"` has no timing: pass `--hygiene` in\nplace of `--delta` and `--baseline`, which skips the noise gate and scores the\nother four dimensions. Plan it as a hygiene item, never drop it for saving no\ntime.\n\nDrop every candidate whose `dropped` is set. Capture each dropped item's\nprerequisite refactor, if any, as a labeled follow-up, never an auto-applied\ncommit.\n\n## Step 2: Order\n\nScore sets priority; the rubric's ordering constraints override it. One speedup\nper commit, never bundled. Honor `--max-commits` and `--min-score`.\n\n## Step 3: Draft commits\n\nFor each planned item, draft a commit from\n`..\u002F..\u002Ftemplates\u002Fcommit-message.tmpl`, adapting the `type(scope)` prefix to the\ntarget project's convention. Write the message per\n`..\u002F..\u002Freferences\u002Fprose-rules.md`. No `Co-Authored-By`, no \"Generated with\" or\nother tool trailer, no emoji: hosts add them by default. The approval reply shows\nthe draft subject only; the body goes into `plan.json` on approval. Keep the draft\nin the reply, not on disk: nothing is written until approval.\n\nConfirm each item's `files` exist at `HEAD`, unless its patch creates them\n(paths are relative to the repository root; exit 1 lists the absent ones):\n\n```console\n$ python3 \u003Cisolate.py> exists \\\n    --cwd . \\\n    --patch \u003Cmemory-dir>\u002F\u003Cpatch> \\\n    --file \u003Ceach path in files>\n```\n\nAn item whose target is absent is not planned: list it under `## Dropped at the\ngate` with \"target file absent at HEAD\", and count only the kept items in the\nhero line. A deselecting item (`removes_tests` in `benchmarks.json`) states\n\"removes N tests from the default run\", and its saving reads as time not spent\non those tests, not as a faster suite.\n\nAssemble the plan from the drafted judgment. Pipe a JSON list of items, each with\n`order`, `id`, `commit` (`subject`, `body`), `verify` (the project tests and\nquality checks), `depends_on` and `score` (the four judged dimensions), to the\nscript; it takes impact, files, token, patch, hash, `cache` and `removed_ids`\nfrom `benchmarks.json`, computes the total and every cumulative `expected_total`,\nand lists the items the rubric drops. Without `--out` it writes nothing, so it\nalso previews the plan in plan mode:\n\n```console\n$ python3 \u003Cmeasure.py> plan-build \\\n    --memory-dir \u003Cmemory-dir> \\\n    --draft -\n```\n\nEach saving was measured alone against the control. Independent changes can\noverlap (widening a sleeping fixture and removing its sleep do not add), so\nnever sum the savings or call them recovered: the plan states each as measured\nalone, and `03-execute` measures the combined result.\n\n## Step 4: Present for approval\n\nEnter plan mode before the first edit. In Claude Code call `EnterPlanMode`; in Cursor, Codex, or Gemini use `\u002Fplan` or `Shift+Tab`. Where plan mode is unavailable, present the plan as text.\n\nPresent the `02-plan`\nsections from `..\u002F..\u002Freferences\u002Foutput-contract.md`. Let the user reorder, drop\nitems, or cap the count; revise the draft in the reply after each change and write\nnothing, since plan mode blocks writes. Plan mode is the decision point, so omit\nthe `AskUserQuestion` panel.\n\nWithout plan mode, the reply is the same sections as text and nothing else: the\nhero line comes first and carries the approval request, with no remark about plan\nmode before it and no closing note after the last section. Wait for the reply:\n\n```text\n✓ 1 commit planned; reply \"approve\" to record the plan, or name items to drop or reorder\n\n## Ranked plan\n\n- 1. H10 mis-scoped fixture: widen make_config to session scope in tests\u002Fconftest.py under the subject \"tests(fixtures) Widen make_config to session scope\", total score 0.87, saved 2.7s measured alone above the 0.44s band, verified with pytest expecting 40 of 40 passing.\n\n## Dropped at the gate\n\n- H33 fixed sleep in test_report: saves 0.03s, inside the noise band, so impact is 0.\n```\n\nWithout an interactive session, write nothing and stop: an unapproved plan is not\nexecutable.\n\nOnce the user approves, exit plan mode and run the same `plan-build` command\nwith `--out \u003Cmemory-dir>\u002Fplan.json` on the approved draft, then hash it:\n\n```console\n$ python3 \u003Cmeasure.py> hash \u003Cmemory-dir>\u002Fplan.json\n```\n\nRecord the approval, which clears the later flags:\n\n```console\n$ python3 \u003Cmeasure.py> state \\\n    complete \u003Cmemory-dir>\u002Fstate.json \\\n    --phase plan \\\n    --set 'plan_hash=\"\u003Chash>\"'\n```\n\n`plan.json` is the contract `pytest-optimizer:03-execute` consumes; a request that\nexplicitly says to approve and apply the plan is approval for this plan only.\n","# 02-plan\n\nTurn measured candidates into a reviewable commit plan. This phase writes only\n`plan.json` and `state.json`, and only after the user approves.\n\n`$ARGUMENTS` may pass `--max-commits=N` to cap the plan, `--min-score` to raise the\ninclusion threshold, `--force` to recompute, and `--memory-dir` to override the\nmemory location.\n\nArithmetic goes through `..\u002F..\u002Fscripts\u002Fmeasure.py` and the staleness check\nthrough `..\u002F..\u002Fscripts\u002Fisolate.py` (Python 3 standard library). Both paths\nresolve from this skill's own directory, not the project's working directory:\nresolve this file's directory, join each path, print the absolute paths once,\nand write those literal paths in each command below where `\u003Cmeasure.py>` and\n`\u003Cisolate.py>` appear.\n\n## Step 1: Load and score\n\nResolve the memory directory by the lookup order in\n`..\u002F..\u002Freferences\u002Fmemory-schema.md`. If none exists or `benchmarks.json` is\nmissing, stop with the halted-run shape in `..\u002F..\u002Freferences\u002Foutput-contract.md`\nand tell the user to run `pytest-optimizer:01-benchmark` first.\n\nRead `benchmarks.json`, `baseline.json` and `state.json`. The evidence must\nstill describe this checkout (a clean scan at this `HEAD`, and every validated\nentry carrying the scan's `env_token`, a `patch_sha256` and this `HEAD` as its\n`base_head`):\n\n```console\n$ python3 \u003Cisolate.py> stale \\\n    --memory-dir \u003Cmemory-dir> \\\n    --phase plan\n```\n\nOn exit 1, stop with the halted-run shape and send the user to the phase its\n`rerun` names (`pytest-optimizer:` followed by it).\n\nScore every `validated` candidate with `..\u002F..\u002Freferences\u002Fscoring-rubric.md`:\njudge safety, effort, confidence and reversibility against the rubric anchors,\nthen pass them with the entry's measured saving. The script derives `impact`\nitself, zero unless the entry's `clears_noise` is true, and returns the total\nand a `dropped` reason (exit 1 when a dimension is outside 0 to 1):\n\n```console\n$ python3 \u003Cmeasure.py> score \\\n    --delta \u003Cmedian_delta> \\\n    --baseline \u003Cbaseline median> \\\n    --clears-noise \\\n    --safety \u003C0..1> \\\n    --effort \u003C0..1> \\\n    --confidence \u003C0..1> \\\n    --reversibility \u003C0..1>\n```\n\nLeave out `--clears-noise` when the entry's `clears_noise` is not true. A\ncandidate benchmarked as `kind: \"hygiene\"` has no timing: pass `--hygiene` in\nplace of `--delta` and `--baseline`, which skips the noise gate and scores the\nother four dimensions. Plan it as a hygiene item, never drop it for saving no\ntime.\n\nDrop every candidate whose `dropped` is set. Capture each dropped item's\nprerequisite refactor, if any, as a labeled follow-up, never an auto-applied\ncommit.\n\n## Step 2: Order\n\nScore sets priority; the rubric's ordering constraints override it. One speedup\nper commit, never bundled. Honor `--max-commits` and `--min-score`.\n\n## Step 3: Draft commits\n\nFor each planned item, draft a commit from\n`..\u002F..\u002Ftemplates\u002Fcommit-message.tmpl`, adapting the `type(scope)` prefix to the\ntarget project's convention. Write the message per\n`..\u002F..\u002Freferences\u002Fprose-rules.md`. No `Co-Authored-By`, no \"Generated with\" or\nother tool trailer, no emoji: hosts add them by default. The approval reply shows\nthe draft subject only; the body goes into `plan.json` on approval. Keep the draft\nin the reply, not on disk: nothing is written until approval.\n\nConfirm each item's `files` exist at `HEAD`, unless its patch creates them\n(paths are relative to the repository root; exit 1 lists the absent ones):\n\n```console\n$ python3 \u003Cisolate.py> exists \\\n    --cwd . \\\n    --patch \u003Cmemory-dir>\u002F\u003Cpatch> \\\n    --file \u003Ceach path in files>\n```\n\nAn item whose target is absent is not planned: list it under `## Dropped at the\ngate` with \"target file absent at HEAD\", and count only the kept items in the\nhero line. A deselecting item (`removes_tests` in `benchmarks.json`) states\n\"removes N tests from the default run\", and its saving reads as time not spent\non those tests, not as a faster suite.\n\nAssemble the plan from the drafted judgment. Pipe a JSON list of items, each with\n`order`, `id`, `commit` (`subject`, `body`), `verify` (the project tests and\nquality checks), `depends_on` and `score` (the four judged dimensions), to the\nscript; it takes impact, files, token, patch, hash, `cache` and `removed_ids`\nfrom `benchmarks.json`, computes the total and every cumulative `expected_total`,\nand lists the items the rubric drops. Without `--out` it writes nothing, so it\nalso previews the plan in plan mode:\n\n```console\n$ python3 \u003Cmeasure.py> plan-build \\\n    --memory-dir \u003Cmemory-dir> \\\n    --draft -\n```\n\nEach saving was measured alone against the control. Independent changes can\noverlap (widening a sleeping fixture and removing its sleep do not add), so\nnever sum the savings or call them recovered: the plan states each as measured\nalone, and `03-execute` measures the combined result.\n\n## Step 4: Present for approval\n\nEnter plan mode before the first edit. In Claude Code call `EnterPlanMode`; in Cursor, Codex, or Gemini use `\u002Fplan` or `Shift+Tab`. Where plan mode is unavailable, present the plan as text.\n\nPresent the `02-plan`\nsections from `..\u002F..\u002Freferences\u002Foutput-contract.md`. Let the user reorder, drop\nitems, or cap the count; revise the draft in the reply after each change and write\nnothing, since plan mode blocks writes. Plan mode is the decision point, so omit\nthe `AskUserQuestion` panel.\n\nWithout plan mode, the reply is the same sections as text and nothing else: the\nhero line comes first and carries the approval request, with no remark about plan\nmode before it and no closing note after the last section. Wait for the reply:\n\n```text\n✓ 1 commit planned; reply \"approve\" to record the plan, or name items to drop or reorder\n\n## Ranked plan\n\n- 1. H10 mis-scoped fixture: widen make_config to session scope in tests\u002Fconftest.py under the subject \"tests(fixtures) Widen make_config to session scope\", total score 0.87, saved 2.7s measured alone above the 0.44s band, verified with pytest expecting 40 of 40 passing.\n\n## Dropped at the gate\n\n- H33 fixed sleep in test_report: saves 0.03s, inside the noise band, so impact is 0.\n```\n\nWithout an interactive session, write nothing and stop: an unapproved plan is not\nexecutable.\n\nOnce the user approves, exit plan mode and run the same `plan-build` command\nwith `--out \u003Cmemory-dir>\u002Fplan.json` on the approved draft, then hash it:\n\n```console\n$ python3 \u003Cmeasure.py> hash \u003Cmemory-dir>\u002Fplan.json\n```\n\nRecord the approval, which clears the later flags:\n\n```console\n$ python3 \u003Cmeasure.py> state \\\n    complete \u003Cmemory-dir>\u002Fstate.json \\\n    --phase plan \\\n    --set 'plan_hash=\"\u003Chash>\"'\n```\n\n`plan.json` is the contract `pytest-optimizer:03-execute` consumes; a request that\nexplicitly says to approve and apply the plan is approval for this plan only.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":31,"disable-model-invocation":32},[25,26,27,28,29,30],"Bash","Read","Grep","Glob","Write","AskUserQuestion","[--max-commits=N] [--min-score=\u003C0..1>] [--force] [--memory-dir=\u003Cpath>]",true,"main","5fbeb3b47beedea13813be7b7023f736a8d97a65","plugins\u002Fpytest-optimizer\u002Fskills\u002F02-plan","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills","https:\u002F\u002Fgithub.com\u002Ftony","https:\u002F\u002Ftony.sh","lighthouse keeper","2026-11-08 17:57:34",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":32},[43,46,49],{"tool":44,"command":45},"npx","npx skills add tony\u002Fskills --skill 02-plan",{"tool":47,"command":48},"bunx","bunx skills add tony\u002Fskills --skill 02-plan",{"tool":50,"command":51},"pnpm","pnpm dlx skills add tony\u002Fskills --skill 02-plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fpytest-optimizer\u002Fskills\u002F02-plan\u002FSKILL.md",[54],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"agents\u002Fopenai.yaml","REFERENCE","参考文档",300,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fpytest-optimizer\u002Fskills\u002F02-plan\u002Fagents\u002Fopenai.yaml",[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7E8NCSHXV2JPW4J61R0TQS7","serene-bliss","Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fserene-bliss\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7E8N87MAVJD8RRQKQB1ZPS6","review","Weave code review: run independent adversarial reviews in parallel, then synthesize findings","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7E8N402XG4ZBFNACQ413163","refine","Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Frefine\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7E8N01KB86A7136P00GVKJW","prompt","Weave prompt: compare independent adversarial implementations, then adopt the single best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7E8MW7YJW2PCMDW3G9RTGNK","plan","Weave planning: compare independent adversarial plans, then synthesize the best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7E8MSBYXNCV4ZYWDS4PFJXK","fix-review","Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Ffix-review\u002FSKILL.md",[],[]]