[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FC76RW06G1D9RSZTC5ADEY":3,"skill-same:01M7FC76RW06G1D9RSZTC5ADEY":44},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7FC76RW06G1D9RSZTC5ADEY","setup-pstack",null,"Configure which models pstack uses per role and at what reasoning budget. Detects the models Pi can launch and writes the role map that overrides the skill defaults. Use for \u002Fsetup-pstack, \"configure pstack models\", \"pstack budget\", or changing pstack's model choices.","chinlung\u002Fpi-pstack","chinlung","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F696924?v=4","01M7FC70KK37NN6FE15PYSFZPD","SCL","01M7FC70M6AD8EN4NSGZ2BJ7M1",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack\u002Fblob\u002Fmain\u002Foverrides\u002Fskills\u002Fsetup-pstack\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: setup-pstack\ndescription: Configure which models pstack uses per role and at what reasoning budget. Detects the models Pi can launch and writes the role map that overrides the skill defaults. Use for \u002Fsetup-pstack, \"configure pstack models\", \"pstack budget\", or changing pstack's model choices.\n---\n\n# Setup pstack\n\nThe pstack role map sets the model each pstack role runs on and the reasoning budget for all of them. The `pi-pstack` extension owns it: `\u002Fsetup-pstack` writes it, `\u002Fpstack-models` shows it, and the `pstack_models` tool returns it resolved.\n\n## Steps\n\n### 1. Hand the user the command\n\n`\u002Fsetup-pstack` is the user's command. You cannot type slash commands. Tell the user to run it, with the budget as its argument when they already named one:\n\n```text\n\u002Fsetup-pstack large\n```\n\nThe command detects the models the session can launch, asks for a budget when none was given, keeps every role the user set before whose model is still available, lets the user confirm or change each role, and writes the map. A budget argument only skips the budget question; with dialog UI the user still confirms the roles.\n\n### 2. Explain the budget when asked\n\nThe budget caps the reasoning level of every role's model, panel seats included.\n\n- `unlimited — max reasoning`\n- `large — xhigh reasoning` (upstream pstack's default)\n- `medium — high reasoning`\n- `small — medium reasoning`\n\nThe budget is stored once. Role values carry no level; a role resolves to the highest level its model supports at or below the budget. A model that offers only levels above the budget runs at its lowest one and is reported as above budget.\n\n### 3. Show the current map when asked\n\nCall the `pstack_models` tool. It returns the budget, whether the map is the user's stored map or defaults, and each role's seats with the level applied.\n\n### 4. Write the map by hand only when the command is unavailable\n\nAsk the user first. The file is JSON at `~\u002F.pi\u002Fagent\u002Fstate\u002Fpi-pstack\u002Fmodels.json`. Write all of it, so a re-run stays idempotent. A role's value is a `provider\u002Fid` model id, a list of them for a panel role, or `inherit-parent` \u002F `auto` for the parent chat model. An alias in a panel still counts as a seat.\n\n```json\n{\n  \"budget\": \"large\",\n  \"roles\": {\n    \"feature, refactoring\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"bug-fix\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"perf-issue\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"hillclimb\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"judgment and prose\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"hardest tasks\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"how explorer\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"how explainer\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"why investigators\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"why synthesizer\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"reflect tooling\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"reflect judgment, divergent, synthesizer\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"arena runners\": { \"value\": [\"anthropic\u002Fclaude-sonnet-5-5\", \"openai\u002Fgpt-6-sol\"] },\n    \"arena cross-judge pool\": { \"value\": [\"anthropic\u002Fclaude-opus-5-5\", \"openai\u002Fgpt-6-astra\"] },\n    \"swarm workers\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"architect runners\": { \"value\": [\"anthropic\u002Fclaude-opus-5-5\", \"openai\u002Fgpt-6-astra\"] },\n    \"interrogate reviewers\": { \"value\": [\"anthropic\u002Fclaude-opus-5-5\", \"openai\u002Fgpt-6-astra\"] }\n  }\n}\n```\n\nThe model ids above are examples. Use ids from the `pstack_models` tool or from the user. Give a panel's seats different model families (`claude`, `gpt`, `gemini`, …), not one model through two providers, because a panel exists to get a second opinion. A role name not listed above is retired and is dropped when the map is read.\n\n### 5. Confirm\n\nTell the user the map was written and that it applies to subagents launched after it. Re-running `\u002Fsetup-pstack` updates it.\n\n### 6. Offer a verification skill (optional)\n\nCheck whether the project has a way to drive the real app for proof (a `verify-*` skill, or an existing harness). If not, offer once: \"want a project-local verification skill, so agents can drive the app the way a user does and prove changes work? I can generate one with \u002Fcreate-verification-skill.\" On yes, invoke `\u002Fcreate-verification-skill`. On no, move on without pushing.\n\n### 7. Offer a formal verification skill (optional)\n\nCheck whether the project already has a formal verification skill (a project skill that runs a model checker, a proof, or another verifier against the code). If not, offer once: \"want a formal verification skill, so agents can prove a key property of your code holds in every case in scope, not only the cases tests reach? I can generate one with \u002Fcreate-formal-verification-skill.\" On yes, invoke `\u002Fcreate-formal-verification-skill`. On no, move on without pushing.\n","# Setup pstack\n\nThe pstack role map sets the model each pstack role runs on and the reasoning budget for all of them. The `pi-pstack` extension owns it: `\u002Fsetup-pstack` writes it, `\u002Fpstack-models` shows it, and the `pstack_models` tool returns it resolved.\n\n## Steps\n\n### 1. Hand the user the command\n\n`\u002Fsetup-pstack` is the user's command. You cannot type slash commands. Tell the user to run it, with the budget as its argument when they already named one:\n\n```text\n\u002Fsetup-pstack large\n```\n\nThe command detects the models the session can launch, asks for a budget when none was given, keeps every role the user set before whose model is still available, lets the user confirm or change each role, and writes the map. A budget argument only skips the budget question; with dialog UI the user still confirms the roles.\n\n### 2. Explain the budget when asked\n\nThe budget caps the reasoning level of every role's model, panel seats included.\n\n- `unlimited — max reasoning`\n- `large — xhigh reasoning` (upstream pstack's default)\n- `medium — high reasoning`\n- `small — medium reasoning`\n\nThe budget is stored once. Role values carry no level; a role resolves to the highest level its model supports at or below the budget. A model that offers only levels above the budget runs at its lowest one and is reported as above budget.\n\n### 3. Show the current map when asked\n\nCall the `pstack_models` tool. It returns the budget, whether the map is the user's stored map or defaults, and each role's seats with the level applied.\n\n### 4. Write the map by hand only when the command is unavailable\n\nAsk the user first. The file is JSON at `~\u002F.pi\u002Fagent\u002Fstate\u002Fpi-pstack\u002Fmodels.json`. Write all of it, so a re-run stays idempotent. A role's value is a `provider\u002Fid` model id, a list of them for a panel role, or `inherit-parent` \u002F `auto` for the parent chat model. An alias in a panel still counts as a seat.\n\n```json\n{\n  \"budget\": \"large\",\n  \"roles\": {\n    \"feature, refactoring\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"bug-fix\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"perf-issue\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"hillclimb\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"judgment and prose\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"hardest tasks\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"how explorer\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"how explainer\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"why investigators\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"why synthesizer\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"reflect tooling\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"reflect judgment, divergent, synthesizer\": { \"value\": \"anthropic\u002Fclaude-opus-5-5\" },\n    \"arena runners\": { \"value\": [\"anthropic\u002Fclaude-sonnet-5-5\", \"openai\u002Fgpt-6-sol\"] },\n    \"arena cross-judge pool\": { \"value\": [\"anthropic\u002Fclaude-opus-5-5\", \"openai\u002Fgpt-6-astra\"] },\n    \"swarm workers\": { \"value\": \"openai\u002Fgpt-6-sol\" },\n    \"architect runners\": { \"value\": [\"anthropic\u002Fclaude-opus-5-5\", \"openai\u002Fgpt-6-astra\"] },\n    \"interrogate reviewers\": { \"value\": [\"anthropic\u002Fclaude-opus-5-5\", \"openai\u002Fgpt-6-astra\"] }\n  }\n}\n```\n\nThe model ids above are examples. Use ids from the `pstack_models` tool or from the user. Give a panel's seats different model families (`claude`, `gpt`, `gemini`, …), not one model through two providers, because a panel exists to get a second opinion. A role name not listed above is retired and is dropped when the map is read.\n\n### 5. Confirm\n\nTell the user the map was written and that it applies to subagents launched after it. Re-running `\u002Fsetup-pstack` updates it.\n\n### 6. Offer a verification skill (optional)\n\nCheck whether the project has a way to drive the real app for proof (a `verify-*` skill, or an existing harness). If not, offer once: \"want a project-local verification skill, so agents can drive the app the way a user does and prove changes work? I can generate one with \u002Fcreate-verification-skill.\" On yes, invoke `\u002Fcreate-verification-skill`. On no, move on without pushing.\n\n### 7. Offer a formal verification skill (optional)\n\nCheck whether the project already has a formal verification skill (a project skill that runs a model checker, a proof, or another verifier against the code). If not, offer once: \"want a formal verification skill, so agents can prove a key property of your code holds in every case in scope, not only the cases tests reach? I can generate one with \u002Fcreate-formal-verification-skill.\" On yes, invoke `\u002Fcreate-formal-verification-skill`. On no, move on without pushing.\n",{"name":5,"description":7},"main","33efbcc2e2adf18daa64a5fb25f4acc2b793934f","overrides\u002Fskills\u002Fsetup-pstack","https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack","https:\u002F\u002Fgithub.com\u002Fchinlung","2026-11-13 05:25:09",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add chinlung\u002Fpi-pstack --skill setup-pstack",{"tool":36,"command":37},"bunx","bunx skills add chinlung\u002Fpi-pstack --skill setup-pstack",{"tool":39,"command":40},"pnpm","pnpm dlx skills add chinlung\u002Fpi-pstack --skill setup-pstack","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack\u002Fblob\u002Fmain\u002Foverrides\u002Fskills\u002Fsetup-pstack\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7FCJD85PKWYNRB7ME57GF6X","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack\u002Fblob\u002Fmain\u002Fupstream\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7FCJA8WYNVGYP7TABXXPWZ6","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack\u002Fblob\u002Fmain\u002Fupstream\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7FCJ76BHPVWF4583V7SYBE2","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack\u002Fblob\u002Fmain\u002Fupstream\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"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":19},"01M7FCJ3M78YVZTRAHW9EDACSN","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack\u002Fblob\u002Fmain\u002Fupstream\u002Fskills\u002Ftechnical-writing\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":19},"01M7FCJ04VJRBF2EYQX2268B20","teach","Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack\u002Fblob\u002Fmain\u002Fupstream\u002Fskills\u002Fteach\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":19},"01M7FCHWHTS5C05PKY2FFVD134","tdd","Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.","https:\u002F\u002Fgithub.com\u002Fchinlung\u002Fpi-pstack\u002Fblob\u002Fmain\u002Fupstream\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]