[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77ZPFEDCWF4N4WRN7JSFJEH":3,"skill-same:01M77ZPFEDCWF4N4WRN7JSFJEH":98},{"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":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M77ZPFEDCWF4N4WRN7JSFJEH","dog-day",null,"Tempered orchestrator: chains frozen, deterministic decision trees (decide_walk, decide_meal, decide_vet) and keeps only the generative note. Use to run a daily dog-care flow with each decision made by code (no LLM) and only the prose left to the model.","CyrilLeMat\u002Ftemper-skills","CyrilLeMat","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7548748?v=4","01M77ZNW2E8N5EFRB577AQ4T85","Cyril Le Mat","01M77ZNW35JKH1AQHG996HV53G",4,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dog-day\ndescription: \"Tempered orchestrator: chains frozen, deterministic decision trees (decide_walk, decide_meal, decide_vet) and keeps only the generative note. Use to run a daily dog-care flow with each decision made by code (no LLM) and only the prose left to the model.\"\n---\n\n# dog-day — orchestrator (tempered by temper-skills)\n\nYou are an assistant.\n\n**The decisions below are frozen** — extract the features, call each tree, relay the verdict, don't re-derive. Only the generative step(s) are yours to phrase. This is the DMN-vs-BPMN split: the decisions are code, the orchestration and prose stay with you.\n\n## 1. `decide_walk` — frozen\nExtract `hours_since_last_walk`, `weather`, `temperature_c`, `dog_energy`, `owner_available`, `is_late`, then:\n```python\nfrom scripts.decide_walk import decide_walk\ndecide_walk_verdict = decide_walk({'hours_since_last_walk': hours_since_last_walk, 'weather': weather, 'temperature_c': temperature_c, 'dog_energy': dog_energy, 'owner_available': owner_available, 'is_late': is_late})\n```\n- gray zone: measured temperature_c overrides the label — >30°C always skips; the 'heat' label only skips when temperature is unmeasured (None). snow\u002Fcold carry no branch (source is silent) and degrade to normal_walk.\n- gray zone: late + owner-away falls through to a walk; source says don't postpone when late but never says who walks.\n\n## 2. `decide_meal` — frozen\nChained: feed the outcome of `decide_walk` into the matching feature below.\nExtract `hours_since_last_meal`, `time_of_day`, `last_meal_size`, `just_exercised`, `minutes_since_exercise`, `had_full_meal_today`, then:\n```python\nfrom scripts.decide_meal import decide_meal\ndecide_meal_verdict = decide_meal({'hours_since_last_meal': hours_since_last_meal, 'time_of_day': time_of_day, 'last_meal_size': last_meal_size, 'just_exercised': just_exercised, 'minutes_since_exercise': minutes_since_exercise, 'had_full_meal_today': had_full_meal_today})\n```\n- gray zone: Evening skip keys on the whole-day had_full_meal_today (added via schema re-gate r1); last_meal_size=='full' is only the fallback when the flag is None. Overlap case [evening + already_full + just_exercised + minutes\u003C30] resolves to treat_only, not wait_then_full_meal, because promising a full meal would violate the 'a treat at most' cap — the four-outcome set can't say 'wait, then a treat', so offer the treat once the dog settles.\n- gray zone: Within 30 min of exercise (or unknown timing) rest first; None minutes_since_exercise is treated as still-resting (conservative, honors 'never feed within 30 min').\n- gray zone: just_exercised is the governing exercise predicate; a stale minutes_since_exercise with just_exercised False is correctly ignored.\n- gray zone: Ate nothing today -> a real meal, not the token light_meal default.\n\n## 3. `decide_vet` — frozen\nExtract `symptom`, `severity`, `duration_hours`, `age_years`, then:\n```python\nfrom scripts.decide_vet import decide_vet\ndecide_vet_verdict = decide_vet({'symptom': symptom, 'severity': severity, 'duration_hours': duration_hours, 'age_years': age_years})\n```\n- gray zone: puppy(\u003C1)\u002Fsenior(>8) lower threshold applies even to a mild & brief symptom, so they never reach the monitor branch.\n\n## Then — generation, yours\n- Write the owner a short, warm summary: the walk call, the meal plan, any vet guidance, and anything to watch. This step is not frozen — phrase it naturally.\n\n---\nGenerated by `temper-skills decompose --temper-each`. Each decision is a pure function — testable (`temper-skills validate`) and evolvable (`temper-skills incremental`); regenerate this orchestrator when a tree changes.\n","# dog-day — orchestrator (tempered by temper-skills)\n\nYou are an assistant.\n\n**The decisions below are frozen** — extract the features, call each tree, relay the verdict, don't re-derive. Only the generative step(s) are yours to phrase. This is the DMN-vs-BPMN split: the decisions are code, the orchestration and prose stay with you.\n\n## 1. `decide_walk` — frozen\nExtract `hours_since_last_walk`, `weather`, `temperature_c`, `dog_energy`, `owner_available`, `is_late`, then:\n```python\nfrom scripts.decide_walk import decide_walk\ndecide_walk_verdict = decide_walk({'hours_since_last_walk': hours_since_last_walk, 'weather': weather, 'temperature_c': temperature_c, 'dog_energy': dog_energy, 'owner_available': owner_available, 'is_late': is_late})\n```\n- gray zone: measured temperature_c overrides the label — >30°C always skips; the 'heat' label only skips when temperature is unmeasured (None). snow\u002Fcold carry no branch (source is silent) and degrade to normal_walk.\n- gray zone: late + owner-away falls through to a walk; source says don't postpone when late but never says who walks.\n\n## 2. `decide_meal` — frozen\nChained: feed the outcome of `decide_walk` into the matching feature below.\nExtract `hours_since_last_meal`, `time_of_day`, `last_meal_size`, `just_exercised`, `minutes_since_exercise`, `had_full_meal_today`, then:\n```python\nfrom scripts.decide_meal import decide_meal\ndecide_meal_verdict = decide_meal({'hours_since_last_meal': hours_since_last_meal, 'time_of_day': time_of_day, 'last_meal_size': last_meal_size, 'just_exercised': just_exercised, 'minutes_since_exercise': minutes_since_exercise, 'had_full_meal_today': had_full_meal_today})\n```\n- gray zone: Evening skip keys on the whole-day had_full_meal_today (added via schema re-gate r1); last_meal_size=='full' is only the fallback when the flag is None. Overlap case [evening + already_full + just_exercised + minutes\u003C30] resolves to treat_only, not wait_then_full_meal, because promising a full meal would violate the 'a treat at most' cap — the four-outcome set can't say 'wait, then a treat', so offer the treat once the dog settles.\n- gray zone: Within 30 min of exercise (or unknown timing) rest first; None minutes_since_exercise is treated as still-resting (conservative, honors 'never feed within 30 min').\n- gray zone: just_exercised is the governing exercise predicate; a stale minutes_since_exercise with just_exercised False is correctly ignored.\n- gray zone: Ate nothing today -> a real meal, not the token light_meal default.\n\n## 3. `decide_vet` — frozen\nExtract `symptom`, `severity`, `duration_hours`, `age_years`, then:\n```python\nfrom scripts.decide_vet import decide_vet\ndecide_vet_verdict = decide_vet({'symptom': symptom, 'severity': severity, 'duration_hours': duration_hours, 'age_years': age_years})\n```\n- gray zone: puppy(\u003C1)\u002Fsenior(>8) lower threshold applies even to a mild & brief symptom, so they never reach the monitor branch.\n\n## Then — generation, yours\n- Write the owner a short, warm summary: the walk call, the meal plan, any vet guidance, and anything to watch. This step is not frozen — phrase it naturally.\n\n---\nGenerated by `temper-skills decompose --temper-each`. Each decision is a pure function — testable (`temper-skills validate`) and evolvable (`temper-skills incremental`); regenerate this orchestrator when a tree changes.\n",{"name":5,"description":7},"main","979724f91215a02d286fa9b7ad49b288cfae75dd","examples\u002Fdog_day\u002Foutput\u002Fdog-day",0,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills","https:\u002F\u002Fpypi.org\u002Fproject\u002Ftemper-skills\u002F","https:\u002F\u002Fgithub.com\u002FCyrilLeMat","2026-08-13 17:56:06",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add CyrilLeMat\u002Ftemper-skills --skill dog-day",{"tool":38,"command":39},"bunx","bunx skills add CyrilLeMat\u002Ftemper-skills --skill dog-day",{"tool":41,"command":42},"pnpm","pnpm dlx skills add CyrilLeMat\u002Ftemper-skills --skill dog-day","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002FSKILL.md",true,[46,52,58,62,66,70,74,78,82,86,90,94],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fdecide_meal.schema.py","SCRIPT","脚本",880,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fassets\u002Fdecide_meal.schema.py",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"assets\u002Fdecide_meal.validation.jsonl","ASSET","资产文件",5884,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fassets\u002Fdecide_meal.validation.jsonl",{"path":59,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":60,"sourceHtmlUrl":61},"assets\u002Fdecide_vet.schema.py",551,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fassets\u002Fdecide_vet.schema.py",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"assets\u002Fdecide_vet.validation.jsonl",4386,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fassets\u002Fdecide_vet.validation.jsonl",{"path":67,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":68,"sourceHtmlUrl":69},"assets\u002Fdecide_walk.schema.py",750,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fassets\u002Fdecide_walk.schema.py",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"assets\u002Fdecide_walk.validation.jsonl",4308,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fassets\u002Fdecide_walk.validation.jsonl",{"path":75,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fdecide_meal.py",2269,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fscripts\u002Fdecide_meal.py",{"path":79,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fdecide_vet.py",1186,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fscripts\u002Fdecide_vet.py",{"path":83,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fdecide_walk.py",1319,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fscripts\u002Fdecide_walk.py",{"path":87,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Ftest_decide_meal.py",5120,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fscripts\u002Ftest_decide_meal.py",{"path":91,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002Ftest_decide_vet.py",3662,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fscripts\u002Ftest_decide_vet.py",{"path":95,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Ftest_decide_walk.py",3841,"https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fdog_day\u002Foutput\u002Fdog-day\u002Fscripts\u002Ftest_decide_walk.py",[99,106,113,119,126,131],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M77ZQJPTSWJNJFJP2ZEFE1H2","temper-skills","Give an agent skill's decision logic a test suite and a deterministic implementation — a labeled validation dataset plus versionable Python — by driving the installed temper-skills CLI (never reimplementing the logic in prose). Use in agents without a native subagent primitive (Cursor, Hermes, generic tools) when the user wants to test, eval, audit, temper, freeze, or harden the routing\u002Fdecision logic of a prompt, skill.md, or playbook (\"test my skill\", \"what is this skill deciding?\"), including auditing a whole skills directory; requires `pip install temper-skills` and a model backend (a logged-in claude\u002Fopencode CLI or an API key). Not for continuous scoring, text generation, or logic with no documentation the model can reach.","https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fskills\u002Ftemper-skills\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M77ZQDC5XSYDWPDWTM8CF9SK","ticket-routing","Frozen, deterministic decision (no LLM): maps priority, security_score, customer_tier, category, sla_breached to one of human_review, escalate_security, escalate_urgent, route_billing, route_engineering, route_default. Use when this decision must be made consistently and auditably — extract the features, call route_ticket(), and relay its verdict without overriding it.","https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fticket_routing\u002Foutput\u002Fticket-routing\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M77ZQC1P7GQMSY2PMGK3R90V","input","https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fticket_routing\u002Finput\u002Fskill.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M77ZQ6Y0YG8WETA5CZGKXVA5","parking","Frozen, deterministic decision (no LLM): maps zone_type, day, hour, is_public_holiday, has_resident_permit to one of prohibited, no_parking_street_cleaning, pay_and_display_2h, free, permit_required. Use when this decision must be made consistently and auditably — extract the features, call can_i_park(), and relay its verdict without overriding it.","https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fparking\u002Foutput\u002Fparking\u002FSKILL.md",[],[],{"skillNo":127,"name":115,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":19},"01M77ZQ5H0421FJ3X3P9HPKTVN","https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Fparking\u002Finput\u002Fskill.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":19},"01M77ZPZNA3C1ZA3VVW5QYN8FD","license-compat","Frozen, deterministic decision (no LLM): maps project_license, dependency_license, linking, distributing, modified_dependency to one of ok_internal_use, must_offer_source, project_must_be_gpl, compatible, incompatible, review_required. Use when this decision must be made consistently and auditably — extract the features, call assess_license(), and relay its verdict without overriding it.","https:\u002F\u002Fgithub.com\u002FCyrilLeMat\u002Ftemper-skills\u002Fblob\u002Fmain\u002Fexamples\u002Flicense_compat\u002Foutput\u002Flicense-compat\u002FSKILL.md",[],[]]