[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSS446NA93DDPCPE0Y2GHS":3,"skill-same:01M7CSS446NA93DDPCPE0Y2GHS":48},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7CSS446NA93DDPCPE0Y2GHS","local-project-context",null,"The local task workspace, the build\u002Ftest commands the hand-off gate runs, and the file and exploration tools. Use when starting work in a task workspace or before running any build, test or verification command.","makifbaysal\u002Ftasktrooper","makifbaysal","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F25031940?v=4","01M7CRG3ZCSYZSSEVDMW3DEYC8","Mehmet Akif Baysal","01M7CRG401FJ8YAXH5ER730XYV",122,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fsystem-architect\u002Fskills\u002Flocal-project-context\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: local-project-context\ncategory: tools\ndescription: The local task workspace, the build\u002Ftest commands the hand-off gate runs, and the file and exploration tools. Use when starting work in a task workspace or before running any build, test or verification command.\n---\n# Local Project Context\n\n## Overview\n\nYou run on a local developer machine, not in a CI\u002FCD pipeline. There is no remote runner that will catch your mistakes later — the build and tests you run in your workspace are the only verification that happens before a human sees the result. Treat your workspace as production's last line of defense.\n\n**Core principle:** Explore before you change; verify in this environment before you claim.\n\n## The environment\n\n- **Task workspace:** each task is worked in a cloned checkout on its own branch. Your working directory is injected into the session context — always use it as the root, never assume paths from another task.\n- **Live codebase:** your changes take effect immediately in the workspace. There is no separate deploy step for verification.\n- **No inherited state:** if you build or test in this workspace, do it from scratch — never assume a prior session left a build artifact, a running server, or a seeded database.\n\n## Exploration tools (use before changing code)\n\n| Tool | Use for |\n|------|---------|\n| `codebase_search` | Concept\u002Fsemantic search — \"where is auth handled\" |\n| `grep_code` | Exact symbol\u002Fstring — a function name, an error message |\n| `get_repo_tree` | Structure and file layout of the repository |\n| `get_symbol_skeleton` | A symbol's signature and outline without its full body |\n| `expand_symbol_context` | Focused read of a symbol and its surroundings |\n| `read_file` | Read a file with line numbers — up to 800 lines per call |\n| `run_terminal` | Build, test, run the app, inspect output |\n\n## File tools (use instead of the shell for anything touching a file)\n\n| Tool | Use for |\n|------|---------|\n| `read_file` | Read with line numbers, whole file in one call |\n| `edit_file` | Replace an exact string; `replace_all: true` changes every occurrence at once |\n| `edit_lines` | Replace \u002F insert \u002F delete by line number — add a function, an import, remove a block |\n| `write_file` | Create a file, or replace one whole |\n| `delete_file` | Remove a file or directory |\n| `move_file` | Rename or move |\n\nNever `cat`, `sed -n`, `head`, `tail`, `sed -i`, `rm`, `mv` or a heredoc through the shell. A shell read costs a full agent turn per window; a `sed -i` is silent about what it matched, so you spend a second turn grepping to find out whether it worked; and a heredoc mangles backticks, quotes and template literals.\n\nEvery file tool reports what it did — the number of occurrences changed, the line numbers, the region as it now reads. **That is your confirmation. Do not grep or re-read the file to check.** One edit is one turn.\n\nIn a CLI runtime (Claude Code \u002F Codex \u002F opencode) `read_file`, `edit_file`, `write_file`, `run_terminal`, `grep_code` and `get_repo_tree` are your native Read\u002FEdit\u002FWrite\u002FBash\u002FGrep\u002FGlob — same rules apply.\n\nFind the existing pattern first (the neighboring endpoint, the similar component, the analogous test) and follow it. A parallel convention you invent is a review finding waiting to happen.\n\n## Verification (use before every handoff)\n\nThe build gate that runs after your run executes exactly the component's required checks — `list_component_checks` returns them with the local command that reproduces each. Run those commands, not a guessed one. The table below is only the fallback when no checks are mapped:\n\n| Stack | Build | Test |\n|-------|-------|------|\n| Go | `go build .\u002F... && go vet .\u002F...` | `go test .\u002F...` (or the affected `.\u002Fpath\u002F...`) |\n| Java | `.\u002Fmvnw -q verify` \u002F `.\u002Fgradlew build` | (included) |\n| Web | `npm run build` in the package that holds `package.json` | `npx vitest run` or `CI=1 npm test` — never watch mode |\n| Flutter | `flutter analyze` | `flutter test` (a build needs a target: `flutter build apk --debug`, `flutter build web`) |\n\nFull builds and suites outlast `run_terminal`'s 60s default: pass `timeout_seconds` (up to 900). Redirect long output to a file and read its tail (`mkdir -p \u002Ftmp\u002Ftt-\u003Ctask key> && … > \u002Ftmp\u002Ftt-\u003Ctask key>\u002Ftest.log 2>&1; tail -80 \u002Ftmp\u002Ftt-\u003Ctask key>\u002Ftest.log` — never a shared fixed path).\n\nIf the build or tests do not pass in this run, the task is not ready to move forward — say what failed.\n\n## Your role\n\n- **Developers:** all of the above — explore, edit, build and test the whole stack.\n- **QA:** black-box. Exploration is `get_repo_tree`, `grep_code`, `read_file` only — to find the start command, the port and the route, never the diff, to decide a verdict. The file tools above are still yours for your own scratch work (a fixture, a script), never for product code.\n- **Architect at code_review:** read, never run. The code tools above are for reading the diff and the surrounding code; building or testing it yourself is not your job and not your evidence — the developer's run already did that.\n\n## Common Mistakes\n\n- Reasoning about behavior from reading code instead of running it — except at code_review, where reading the diff IS the job.\n- Reusing a path or branch name from a previous task's workspace.\n- Assuming `npm install` \u002F `go mod download` already ran — check, don't assume.\n\n## Red Flags\n\n- \"It built last time\" — build again, now (unless you are the architect: you never build).\n- \"The server should still be running\" — never assume; start it.\n","# Local Project Context\n\n## Overview\n\nYou run on a local developer machine, not in a CI\u002FCD pipeline. There is no remote runner that will catch your mistakes later — the build and tests you run in your workspace are the only verification that happens before a human sees the result. Treat your workspace as production's last line of defense.\n\n**Core principle:** Explore before you change; verify in this environment before you claim.\n\n## The environment\n\n- **Task workspace:** each task is worked in a cloned checkout on its own branch. Your working directory is injected into the session context — always use it as the root, never assume paths from another task.\n- **Live codebase:** your changes take effect immediately in the workspace. There is no separate deploy step for verification.\n- **No inherited state:** if you build or test in this workspace, do it from scratch — never assume a prior session left a build artifact, a running server, or a seeded database.\n\n## Exploration tools (use before changing code)\n\n| Tool | Use for |\n|------|---------|\n| `codebase_search` | Concept\u002Fsemantic search — \"where is auth handled\" |\n| `grep_code` | Exact symbol\u002Fstring — a function name, an error message |\n| `get_repo_tree` | Structure and file layout of the repository |\n| `get_symbol_skeleton` | A symbol's signature and outline without its full body |\n| `expand_symbol_context` | Focused read of a symbol and its surroundings |\n| `read_file` | Read a file with line numbers — up to 800 lines per call |\n| `run_terminal` | Build, test, run the app, inspect output |\n\n## File tools (use instead of the shell for anything touching a file)\n\n| Tool | Use for |\n|------|---------|\n| `read_file` | Read with line numbers, whole file in one call |\n| `edit_file` | Replace an exact string; `replace_all: true` changes every occurrence at once |\n| `edit_lines` | Replace \u002F insert \u002F delete by line number — add a function, an import, remove a block |\n| `write_file` | Create a file, or replace one whole |\n| `delete_file` | Remove a file or directory |\n| `move_file` | Rename or move |\n\nNever `cat`, `sed -n`, `head`, `tail`, `sed -i`, `rm`, `mv` or a heredoc through the shell. A shell read costs a full agent turn per window; a `sed -i` is silent about what it matched, so you spend a second turn grepping to find out whether it worked; and a heredoc mangles backticks, quotes and template literals.\n\nEvery file tool reports what it did — the number of occurrences changed, the line numbers, the region as it now reads. **That is your confirmation. Do not grep or re-read the file to check.** One edit is one turn.\n\nIn a CLI runtime (Claude Code \u002F Codex \u002F opencode) `read_file`, `edit_file`, `write_file`, `run_terminal`, `grep_code` and `get_repo_tree` are your native Read\u002FEdit\u002FWrite\u002FBash\u002FGrep\u002FGlob — same rules apply.\n\nFind the existing pattern first (the neighboring endpoint, the similar component, the analogous test) and follow it. A parallel convention you invent is a review finding waiting to happen.\n\n## Verification (use before every handoff)\n\nThe build gate that runs after your run executes exactly the component's required checks — `list_component_checks` returns them with the local command that reproduces each. Run those commands, not a guessed one. The table below is only the fallback when no checks are mapped:\n\n| Stack | Build | Test |\n|-------|-------|------|\n| Go | `go build .\u002F... && go vet .\u002F...` | `go test .\u002F...` (or the affected `.\u002Fpath\u002F...`) |\n| Java | `.\u002Fmvnw -q verify` \u002F `.\u002Fgradlew build` | (included) |\n| Web | `npm run build` in the package that holds `package.json` | `npx vitest run` or `CI=1 npm test` — never watch mode |\n| Flutter | `flutter analyze` | `flutter test` (a build needs a target: `flutter build apk --debug`, `flutter build web`) |\n\nFull builds and suites outlast `run_terminal`'s 60s default: pass `timeout_seconds` (up to 900). Redirect long output to a file and read its tail (`mkdir -p \u002Ftmp\u002Ftt-\u003Ctask key> && … > \u002Ftmp\u002Ftt-\u003Ctask key>\u002Ftest.log 2>&1; tail -80 \u002Ftmp\u002Ftt-\u003Ctask key>\u002Ftest.log` — never a shared fixed path).\n\nIf the build or tests do not pass in this run, the task is not ready to move forward — say what failed.\n\n## Your role\n\n- **Developers:** all of the above — explore, edit, build and test the whole stack.\n- **QA:** black-box. Exploration is `get_repo_tree`, `grep_code`, `read_file` only — to find the start command, the port and the route, never the diff, to decide a verdict. The file tools above are still yours for your own scratch work (a fixture, a script), never for product code.\n- **Architect at code_review:** read, never run. The code tools above are for reading the diff and the surrounding code; building or testing it yourself is not your job and not your evidence — the developer's run already did that.\n\n## Common Mistakes\n\n- Reasoning about behavior from reading code instead of running it — except at code_review, where reading the diff IS the job.\n- Reusing a path or branch name from a previous task's workspace.\n- Assuming `npm install` \u002F `go mod download` already ran — check, don't assume.\n\n## Red Flags\n\n- \"It built last time\" — build again, now (unless you are the architect: you never build).\n- \"The server should still be running\" — never assume; start it.\n",{"name":5,"category":24,"description":7},"tools","main","910394a0b6db9fc8c9a8f36328ec421d3ebd8b38","catalog\u002Fagents\u002Fsystem-architect\u002Fskills\u002Flocal-project-context",18,"https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper","https:\u002F\u002Ftasktrooper.ai","https:\u002F\u002Fgithub.com\u002Fmakifbaysal","Senior Software Developer","2026-11-15 04:50:29",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add makifbaysal\u002Ftasktrooper --skill local-project-context",{"tool":40,"command":41},"bunx","bunx skills add makifbaysal\u002Ftasktrooper --skill local-project-context",{"tool":43,"command":44},"pnpm","pnpm dlx skills add makifbaysal\u002Ftasktrooper --skill local-project-context","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fsystem-architect\u002Fskills\u002Flocal-project-context\u002FSKILL.md",true,[],[49,55,62,69,76,83],{"skillNo":50,"name":51,"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":52,"categories":53,"keywords":54,"publishedAt":19},"01M7CSVEPQW6J6TD6CS2T5FPNZ","visual-craft","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fvisual-craft\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7CSVAQG91ETHQ0HBNZDG5FR","ux-copy","Use when you write any words a user reads in a mockup or a hand-off - content language and voice, buttons, labels, errors, empty states, confirmations, numbers and dates, and the longest-string check","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fux-copy\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7CSV6H0J38659NDXHJQ8396","screen-mockup-html","Use when you draw screens as the design task's HTML mockup - ONE canvas document holding every screen and every variant side by side, the sanitizer-safe recipe, phone and wide frames, the states grid, static control states, and the loopback self-check with screenshots at 375, 768 and 1440 attached to the task","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fscreen-mockup-html\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7CSV3JFRF3BM3XK52M7YEYR","performance-awareness","How the performance score moves for your role. Use when the score context shows a declining trend, or before handing off work you have not self-checked against every criterion.","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fperformance-awareness\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7CSTZDH00YRF5SCT7BRT9QD","design-variants","Use when a screen design needs variants - how many, variants as side-by-side rows on the one canvas, what makes two variants genuinely different, recommending one, how the human's choice is read, and narrowing to the chosen one in revision","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-variants\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7CSTV6P3SM3PAE28DB0RF77","design-system-authoring","Use when you derive, change or extend a design system - where tokens live per stack, the DTCG token tree, role-based names for both themes, base vs layer vs drift, the DESIGN.md section order, the inventory format, the contrast check and the lint every proposal returns","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-system-authoring\u002FSKILL.md",[],[]]