[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F6VZT62HREYKHPEFEPAS84":3,"skill-same:01M7F6VZT62HREYKHPEFEPAS84":47},{"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":31,"updatedAt":32,"install":33,"resources":46},"01M7F6VZT62HREYKHPEFEPAS84","plan",null,"Builds a phase plan (goal, progress, research, Opus plan review). Use for \"plan\", \"plan this\", \"adapt this plan\", \"planejar\", \"crie o plano\", \"monte a fase\", or a pasted outside plan. Small idea becomes a 1-part plan.","stage2dev\u002Ftune-up","stage2dev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F205088513?v=4","01M7F6TJSVA061K0AHEMXHHZAA","01M7F6TJTDN359R5QXK9C5RAZD",1,"MIT","https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up\u002Fblob\u002Fmain\u002Fskills\u002Fplan\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: plan\ndescription: Builds a phase plan (goal, progress, research, Opus plan review). Use for \"plan\", \"plan this\", \"adapt this plan\", \"planejar\", \"crie o plano\", \"monte a fase\", or a pasted outside plan. Small idea becomes a 1-part plan.\nargument-hint: \"\u003Crequest, topic or pasted plan>\"\nallowed-tools: Bash(sh \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fpy\" scripts\u002Fguarda.py info)\n---\n\n# Phase plan\n\nContext: !`sh \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fpy\" scripts\u002Fguarda.py info`\n\nRequest: $ARGUMENTS\n\nThe JSON above is the context. Write to the user in its `language` (final answer short, `reply_style` honored). Use document names from `names` (keys such as `goal`, `research`, `progress`, `plan_review`, `later`, `open_questions`, `need_you`, `part_closed`), never literal. Models and effort per role come from `models`; if a role is missing use the default in the table. If `info` failed, say so and use the defaults.\n\nYou (main session, highest effort) coordinate: think, decide, dispatch, check. You do not write the long document or map the code.\n\n## Roles\n\n| Role | Agent | Default model | Effort |\n|---|---|---|---|\n| Map code | `tune-up:mapper` | haiku | medium |\n| Official external docs | `tune-up:researcher` | sonnet | medium |\n| Write documents | `tune-up:writer` | sonnet | medium |\n| Pick skills per item | `tune-up:skill-finder` | haiku | medium |\n| Review the plan | `tune-up:plan-reviewer` | opus | high |\n\n- Pass `model` and `effort` on every call. Never use a model listed in `forbidden_subagent_models` (default `[\"fable\"]`).\n- Independent agents go in ONE message, in background. Do not wait awake; do not read the agent's output file.\n- Production: read only. No commit, push or external write unless asked.\n- Planning changes no app file. A finding during planning becomes a GOAL item, never a PR.\n- If the user said \"research only\" \u002F \"change nothing\": stop after Step 2 and use `\u002Ftune-up:research`.\n\n## Workflow scripts\n\nIf you orchestrate with the Workflow tool, every `agent()` carries a literal `agentType` from the table above (`tune-up:mapper`, `tune-up:researcher`, `tune-up:writer`, `tune-up:plan-reviewer`), plus `model` and `effort`.\nA generic agent (no `agentType`) only for work that needs MCP tools, a browser or images, marked with `\u002F\u002F tune-up: allow-generic \u003Creason>` on the line above.\nTemplate and review-loop rules: see \"Workflow scripts\" in the `part` skill.\n\n## Step 1 - Prepare\n\n1. Read the project profile (`profile_path` from `info`; ask nothing) and the repo AGENTS\u002FCLAUDE file: plans folder, production, pitfalls.\n2. `git fetch`; note the hash of `origin\u002F\u003Cmain>`. Do not trust a previous session's summary.\n3. Read-only worktree of `origin\u002F\u003Cmain>` in the scratchpad (`git worktree add --detach \u003Cscratchpad>\u002Fwt-main origin\u002F\u003Cmain>`). Every map uses this base and cites the hash.\n4. Number the phase: `ls \u003Cplans_dir>\u002Fphases | sort -t- -k1,1n | tail -5` right BEFORE `mkdir` (parallel sessions collide). Folder `NNN-short-kebab\u002F`.\n5. Pasted request: save a verbatim copy as `ORIGINAL-REQUEST.md`. Outside plans are adapted to this format, never executed as they came.\n6. If the profile mandates synced folders, run `chmod u+w` (macOS\u002FLinux; on Windows `attrib -r`) in the SAME command as `mkdir`.\n7. Small idea (one behavior, few files): plan ONE part with few items; skip extra mappers and the second review round.\n\n## Step 2 - Research (one message, all parallel)\n\n- 2 to 4 `tune-up:mapper`, one theme each. Each request has: base (worktree + hash), numbered questions, \"answer with file:line\".\n- 1 `tune-up:researcher` if there is an external dependency: numbered questions plus the \"decisive question\" (the one that can kill the plan). Ask for URL, date, status.\n- You: read-only production queries to measure what the plan assumes (how many, who, since when). A measured number beats a guess.\n- Collect everything in scratchpad files (`map-*.md`, `research-*.md`).\n\n## Step 3 - Coordinator brief\n\nWrite `\u003Cscratchpad>\u002F\u003Cphase>\u002F` brief (name `names.brief`) from `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates\u002Fphase\u002Fbrief.md`. This is where you think: what research overturned, the design, items with size (S\u002FM\u002FL) and executor, criteria C as query\u002Fcommand, Parts, open questions with a recommendation. Be specific (file:line, column names): the writer decides nothing.\n\n## Step 4 - Skills per item\n\nFor each item call `tune-up:skill-finder` (one message, parallel) with the item text and the absolute catalog path (`info.catalog_path`); it returns up to 3 skills (name, SKILL.md path, why). Fill \"Skills\" in the goal document and \"Skills to read\" in each work order. No catalog (`catalog_path` empty or the agent answers `none`): leave them empty and say so.\n\n## Step 5 - Write\n\nOne `tune-up:writer` writes from the brief + maps, each file named by `names` and shaped by the template in `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates\u002Fphase\u002F`: `goal.md` -> `names.goal`; `research.md` -> `names.research` (suffix the date); `progress.md` -> `names.progress`; `later.md` -> `names.later`. It returns ambiguities: resolve all in the brief and apply in one round.\n\n## Step 6 - Plan review (Opus, high)\n\n1. Round 1: `tune-up:plan-reviewer` with the base, the paths of goal\u002Fresearch and your main worry. Save as `names.plan_review` (template `plan-review.md`).\n2. For each finding decide the fix in `\u003Cscratchpad>\u002F\u003Cphase>\u002Ffixes-round1.md`; verify doubtful proofs yourself.\n3. The writer applies all and records a \"Plan review\" section in the goal document.\n4. Round 2: reviewer checks ONLY that each CRITICAL\u002FHIGH closed, plus new ones. New MEDIUM: you apply. Max 2 rounds; CRITICAL\u002FHIGH left after round 2 -> `names.need_you` with the exact ask.\n\n## Step 7 - Owner decisions\n\n- `AskUserQuestion`, up to 4 questions only the owner can decide; recommended first, \"(Recommended)\" and why in one line. Nothing the code can answer.\n- Answers go under the `names.decisions_heading` heading in goal and progress. `names.open_questions` keeps only what stays open.\n- A decision that adds an item or changes the design: quick map + measurement -> brief -> writer -> focused review of that item only.\n\n## Step 8 - Final check\n\nReread risky items yourself (database, trigger, access rules, external sending). Look for the pitfalls in the profile, plus the pitfall skills of the project's modules (skills whose name or description says pitfalls\u002Farmadilhas), plus: a gate that does not test what it decides, non-atomic writes, data already present at deploy, off-then-on, supposed numbers, external service without dedupe. Fix with `Edit`, confirm with `grep`.\n\n## Step 9 - Close\n\n1. Progress document: state, decisions, next owner action, `\u002Fgoal` commands for ready Parts, each ending with ` - follow \u002Ftune-up:part. Stop when: \"\u003Cnames.part_closed>\" in progress OR you wrote \u003Cnames.need_you> OR 40 turns.`\n2. If the project has a Claude memory, record a short note there (facts that change everything, Parts, decisions).\n3. Short plain answer: the finding that changed the plan, what is decided, what depends on whom, the Part commands. Say nothing was committed.\n","# Phase plan\n\nContext: !`sh \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fpy\" scripts\u002Fguarda.py info`\n\nRequest: $ARGUMENTS\n\nThe JSON above is the context. Write to the user in its `language` (final answer short, `reply_style` honored). Use document names from `names` (keys such as `goal`, `research`, `progress`, `plan_review`, `later`, `open_questions`, `need_you`, `part_closed`), never literal. Models and effort per role come from `models`; if a role is missing use the default in the table. If `info` failed, say so and use the defaults.\n\nYou (main session, highest effort) coordinate: think, decide, dispatch, check. You do not write the long document or map the code.\n\n## Roles\n\n| Role | Agent | Default model | Effort |\n|---|---|---|---|\n| Map code | `tune-up:mapper` | haiku | medium |\n| Official external docs | `tune-up:researcher` | sonnet | medium |\n| Write documents | `tune-up:writer` | sonnet | medium |\n| Pick skills per item | `tune-up:skill-finder` | haiku | medium |\n| Review the plan | `tune-up:plan-reviewer` | opus | high |\n\n- Pass `model` and `effort` on every call. Never use a model listed in `forbidden_subagent_models` (default `[\"fable\"]`).\n- Independent agents go in ONE message, in background. Do not wait awake; do not read the agent's output file.\n- Production: read only. No commit, push or external write unless asked.\n- Planning changes no app file. A finding during planning becomes a GOAL item, never a PR.\n- If the user said \"research only\" \u002F \"change nothing\": stop after Step 2 and use `\u002Ftune-up:research`.\n\n## Workflow scripts\n\nIf you orchestrate with the Workflow tool, every `agent()` carries a literal `agentType` from the table above (`tune-up:mapper`, `tune-up:researcher`, `tune-up:writer`, `tune-up:plan-reviewer`), plus `model` and `effort`.\nA generic agent (no `agentType`) only for work that needs MCP tools, a browser or images, marked with `\u002F\u002F tune-up: allow-generic \u003Creason>` on the line above.\nTemplate and review-loop rules: see \"Workflow scripts\" in the `part` skill.\n\n## Step 1 - Prepare\n\n1. Read the project profile (`profile_path` from `info`; ask nothing) and the repo AGENTS\u002FCLAUDE file: plans folder, production, pitfalls.\n2. `git fetch`; note the hash of `origin\u002F\u003Cmain>`. Do not trust a previous session's summary.\n3. Read-only worktree of `origin\u002F\u003Cmain>` in the scratchpad (`git worktree add --detach \u003Cscratchpad>\u002Fwt-main origin\u002F\u003Cmain>`). Every map uses this base and cites the hash.\n4. Number the phase: `ls \u003Cplans_dir>\u002Fphases | sort -t- -k1,1n | tail -5` right BEFORE `mkdir` (parallel sessions collide). Folder `NNN-short-kebab\u002F`.\n5. Pasted request: save a verbatim copy as `ORIGINAL-REQUEST.md`. Outside plans are adapted to this format, never executed as they came.\n6. If the profile mandates synced folders, run `chmod u+w` (macOS\u002FLinux; on Windows `attrib -r`) in the SAME command as `mkdir`.\n7. Small idea (one behavior, few files): plan ONE part with few items; skip extra mappers and the second review round.\n\n## Step 2 - Research (one message, all parallel)\n\n- 2 to 4 `tune-up:mapper`, one theme each. Each request has: base (worktree + hash), numbered questions, \"answer with file:line\".\n- 1 `tune-up:researcher` if there is an external dependency: numbered questions plus the \"decisive question\" (the one that can kill the plan). Ask for URL, date, status.\n- You: read-only production queries to measure what the plan assumes (how many, who, since when). A measured number beats a guess.\n- Collect everything in scratchpad files (`map-*.md`, `research-*.md`).\n\n## Step 3 - Coordinator brief\n\nWrite `\u003Cscratchpad>\u002F\u003Cphase>\u002F` brief (name `names.brief`) from `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates\u002Fphase\u002Fbrief.md`. This is where you think: what research overturned, the design, items with size (S\u002FM\u002FL) and executor, criteria C as query\u002Fcommand, Parts, open questions with a recommendation. Be specific (file:line, column names): the writer decides nothing.\n\n## Step 4 - Skills per item\n\nFor each item call `tune-up:skill-finder` (one message, parallel) with the item text and the absolute catalog path (`info.catalog_path`); it returns up to 3 skills (name, SKILL.md path, why). Fill \"Skills\" in the goal document and \"Skills to read\" in each work order. No catalog (`catalog_path` empty or the agent answers `none`): leave them empty and say so.\n\n## Step 5 - Write\n\nOne `tune-up:writer` writes from the brief + maps, each file named by `names` and shaped by the template in `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates\u002Fphase\u002F`: `goal.md` -> `names.goal`; `research.md` -> `names.research` (suffix the date); `progress.md` -> `names.progress`; `later.md` -> `names.later`. It returns ambiguities: resolve all in the brief and apply in one round.\n\n## Step 6 - Plan review (Opus, high)\n\n1. Round 1: `tune-up:plan-reviewer` with the base, the paths of goal\u002Fresearch and your main worry. Save as `names.plan_review` (template `plan-review.md`).\n2. For each finding decide the fix in `\u003Cscratchpad>\u002F\u003Cphase>\u002Ffixes-round1.md`; verify doubtful proofs yourself.\n3. The writer applies all and records a \"Plan review\" section in the goal document.\n4. Round 2: reviewer checks ONLY that each CRITICAL\u002FHIGH closed, plus new ones. New MEDIUM: you apply. Max 2 rounds; CRITICAL\u002FHIGH left after round 2 -> `names.need_you` with the exact ask.\n\n## Step 7 - Owner decisions\n\n- `AskUserQuestion`, up to 4 questions only the owner can decide; recommended first, \"(Recommended)\" and why in one line. Nothing the code can answer.\n- Answers go under the `names.decisions_heading` heading in goal and progress. `names.open_questions` keeps only what stays open.\n- A decision that adds an item or changes the design: quick map + measurement -> brief -> writer -> focused review of that item only.\n\n## Step 8 - Final check\n\nReread risky items yourself (database, trigger, access rules, external sending). Look for the pitfalls in the profile, plus the pitfall skills of the project's modules (skills whose name or description says pitfalls\u002Farmadilhas), plus: a gate that does not test what it decides, non-atomic writes, data already present at deploy, off-then-on, supposed numbers, external service without dedupe. Fix with `Edit`, confirm with `grep`.\n\n## Step 9 - Close\n\n1. Progress document: state, decisions, next owner action, `\u002Fgoal` commands for ready Parts, each ending with ` - follow \u002Ftune-up:part. Stop when: \"\u003Cnames.part_closed>\" in progress OR you wrote \u003Cnames.need_you> OR 40 turns.`\n2. If the project has a Claude memory, record a short note there (facts that change everything, Parts, decisions).\n3. Short plain answer: the finding that changed the plan, what is decided, what depends on whom, the Part commands. Say nothing was committed.\n",{"name":5,"description":7,"allowed-tools":23,"argument-hint":24},"Bash(sh \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fpy\" scripts\u002Fguarda.py info)","\u003Crequest, topic or pasted plan>","main","bbde73350fc3c138bffa1e546839b190e0d415bc","skills\u002Fplan",0,"https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up","https:\u002F\u002Fgithub.com\u002Fstage2dev","Tuning the unnecessary.","2026-11-14 05:05:23",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add stage2dev\u002Ftune-up --skill plan",{"tool":39,"command":40},"bunx","bunx skills add stage2dev\u002Ftune-up --skill plan",{"tool":42,"command":43},"pnpm","pnpm dlx skills add stage2dev\u002Ftune-up --skill plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up\u002Fblob\u002Fmain\u002Fskills\u002Fplan\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":18},"01M7F6Z7DAMCW5ES2ED8FGCC8C","instalar","One-step setup of the WhatsApp sales screen on this computer: Docker, the local Evolution API and the sales service, step by step in plain words. Use on: install, set up WhatsApp, prepare sales; instalar, preparar, preparar o WhatsApp, setup WhatsApp, configurar vendas.","https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up\u002Fblob\u002Fmain\u002Fvendas\u002Fskills\u002Finstalar\u002FSKILL.md",[],[],{"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":18},"01M7F6Z0BKKW3MGNAM1NJ16JHV","video","Makes a hook-first, business-oriented silent vertical reel (9:16, 1080x1920 MP4, 10 or 15 s) from a briefing, using only the owner-approved brand: strategy, the reel composition of the studio kit filled with the script and a hero drawn for this briefing, motion by the studio JavaScript engine (seek-safe, no network), render or slide reserve, and the studio QA. Runs unattended from the panel actions estudio.video and estudio.video-motion. Use on: vídeo, reel, reels, story em vídeo.","https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up\u002Fblob\u002Fmain\u002Ftune-up-studio\u002Fskills\u002Fvideo\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":18},"01M7F6YS17B793E58C07S5EX5R","post","Makes a hook-first, business-oriented still post or carousel (PNG per frame) from a briefing, using only the owner-approved brand: strategy first, one chosen hook, a composition of the studio kit with a hero drawn for this briefing, one call to action, and every frame checked by the studio QA. Runs unattended from the panel action estudio.post. Use on: post, carrossel, carousel, peça estática, post do Instagram.","https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up\u002Fblob\u002Fmain\u002Ftune-up-studio\u002Fskills\u002Fpost\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M7F6YFJNJP6PT3YTFEBRQW9V","marca","Discovers the project's brand (colors, fonts, logo, name) from its own files and shows it to the owner for approval in the panel. Use on: discover the brand, descobrir marca, identidade visual do projeto, marca do estúdio.","https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up\u002Fblob\u002Fmain\u002Ftune-up-studio\u002Fskills\u002Fmarca\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M7F6YBJ20F1GJN7ZFJJK8Y7Y","marca-ler","Reads the project's brand (marca.json) and says whether the owner approved it. Read-only: never approves, edits or writes anything. Use on: read the brand, is the brand approved, ler marca, marca aprovada.","https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up\u002Fblob\u002Fmain\u002Ftune-up-studio\u002Fskills\u002Fmarca-ler\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M7F6Y4KXCDFMA88EHVM0DRVB","anuncio","Makes a hook-first, business-oriented ad from a briefing, using only the owner-approved brand: one master image plus the aspect-ratio adaptations the platform needs, text variations inside the platform limits, and an import sheet with everything Paused (Google Ads Editor CSV, or an experimental Meta sheet). Publishes nothing and calls no ad API. Runs unattended from the panel action estudio.anuncio. Use on: anúncio, anuncio, ad, Google Ads, Meta Ads.","https:\u002F\u002Fgithub.com\u002Fstage2dev\u002Ftune-up\u002Fblob\u002Fmain\u002Ftune-up-studio\u002Fskills\u002Fanuncio\u002FSKILL.md",[],[]]