routing
Skill0 starsChanged 4 days agoMITView on GitHub
How navigation works with GoRouter, the single shell that holds the assistant, screen-context entries for new routes, and deep links. Use when adding a screen or route, navigating between screens, or changing the app shell.
16 other projects use a version of this.
Adopted by
Most recently taken up by
- NVIDIA/nvcftheir own version, first seen Nov 15, 2026
- Velavalapallisairam/Auto-Routertheir own version, first seen Nov 15, 2026
- AnyOrgName/php-skillstheir own version, first seen Nov 8, 2026
- github/replicatheir own version, first seen Nov 1, 2026
- darknecrocities/SkillBuildertheir own version, first seen Nov 1, 2026
- EONRaider/agent-routertheir own version, first seen Oct 20, 2026
Used with
Projects with it also use parallelization and prompt-chaining.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
hajekimSkillparallelization
This skill should be used when the user wants to "run tasks in parallel", "concurrent LLM calls", "fan-out and fan-in", "parallel agents", "simultaneous execution", "reduce latency with concurrency", "parallel sub-tasks", "parallel processing", "concurrent agent execution", "run agents simultaneously", "speed up with parallelism", "async agent execution", "batch LLM calls", "parallel workflow", "parallelize agent tasks", or needs to execute multiple independent tasks simultaneously. Also responds to Korean: "병렬 작업 실행", "동시 LLM 호출", "팬아웃 팬인 패턴", "병렬 에이전트", "동시 실행", "동시성으로 지연 시간 감소", "병렬로 실행", "동시에 여러 작업", "병렬 처리", "동시에 돌려줘", "빠르게 병렬로", "여러 작업 동시 실행해줘". Also responds to Japanese: "並列処理", "同時実行", "並列エージェント", "並行LLM呼び出し", "ファンアウト・ファンイン", "複数タスクを同時に実行したい", "処理速度を上げたい", "非同期エージェント", "バッチ処理", "並列で動かしたい" Also responds to Chinese: "并行处理", "并发执行", "并行智能体", "同时调用多个LLM", "扇出扇入模式", "多任务并行运行", "加快处理速度", "异步智能体", "批量LLM调用", "同时运行多个任务".. Apply this skill to design or implement the Parallelization agentic design pattern.
Also in 3 projects that use this
hajekimSkillprompt-chaining
This skill should be used when the user wants to "chain prompts", "build a pipeline", "break down complex tasks into steps", "sequential LLM calls", "multi-step reasoning", "pipeline pattern", "sequential agent pipeline", "multi-step prompt pipeline", "LLM chain", "step-by-step agent", "prompt pipeline", "decompose task into prompts", "stage-by-stage processing", "chained LLM calls", or when a task is too complex for a single prompt and needs to be decomposed into sequential sub-tasks. Also responds to Korean: "프롬프트 체이닝", "체인 방식 에이전트", "단계별 LLM 호출", "복잡한 작업 분해", "순차적 프롬프트 파이프라인", "단계적 작업 처리", "단계별 처리", "순차 처리 에이전트", "파이프라인 만들어줘", "단계적으로 처리해줘", "연속 프롬프트", "체이닝 해줘". Also responds to Japanese: "プロンプトチェーニング", "ステップごとに処理", "順次LLM呼び出し", "パイプライン構築", "複雑なタスクを分解", "段階的エージェント", "連続プロンプト", "LLMパイプライン", "順番に処理してほしい", "チェーン方式エージェント" Also responds to Chinese: "提示词链", "顺序调用LLM", "构建流水线", "分解复杂任务", "逐步处理", "链式提示", "多步骤流水线", "按顺序处理任务", "提示词管道", "帮我一步一步处理".. Apply this skill to design, implement, or explain the Prompt Chaining agentic design pattern.
Also in 3 projects that use this
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- github/replica★ 275same name
- NVIDIA/nvcf★ 268same name
- ypollak2/llm-router★ 123same name
- ThomasLangbroek/frugal★ 37same name
- darknecrocities/SkillBuilder★ 13same name
- flpbalada/fb-skills★ 8same name
- AnyOrgName/php-skills★ 4same name
- hajekim/agentic-design-patterns-skills★ 4same name
- jkaninda/okapi-skills★ 3same name
- ffsshhttiikk/opencode-agents-skills★ 2same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessibilitySkill
- actionsSkill
- adding-a-featureSkill
- agent-workflowSkill
- app-contextSkill
- approval-and-safetySkill
- backend-proxySkill
- background-workSkill
- build-an-appSkill
- capture-learningsSkill
- clean-architectureSkill
- customizing-the-assistantSkill
- delegate-to-agentSkill
- edit-boundariesSkill
- i18n-and-rtlSkill
- model-providersSkill
- performanceSkill
- permissions-and-platformSkill
- read-the-docsSkill
- reliable-mutationsSkill
- secretsSkill
- state-managementSkill
- storing-dataSkill
- testingSkill
- ui-designSkill
- upgrade-the-frameworkSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 0 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Don't load this for what the assistant is told about a screen.
- Very specific: line 13
All routes live inside the one ShellRoute in lib/utils/routes/app_router.dart.
- Very specific: line 14
Every new GoRoute needs an entry in buildScreenContexts in lib/ai/screen_contexts.dart, keyed by the route's full path pattern.
- Very specific: line 24
Write the screen under lib/presentation/<feature>/.
- Very specific: line 26
Add the same pattern to buildScreenContexts.
“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Routing
Don't load this for what the assistant is told about a screen; see app-context.
Rule
- Navigate with GoRouter only:
context.go('/settings')orcontext.push(...). NeverNavigator.push…. Popping dialogs and sheets withNavigator.of(context).pop()is fine. - All routes live inside the one
ShellRouteinlib/utils/routes/app_router.dart. Its builder returnsAssistantShell(child: child)(lib/presentation/assistant/assistant_shell.dart), so the assistant is mounted once and keeps its conversation across navigation. Do not add a second shell or a route outside it. - Every new
GoRouteneeds an entry inbuildScreenContextsinlib/ai/screen_contexts.dart, keyed by the route's full path pattern.
Enforced by the lint rule no_navigator_push and by test/ai/parity_test.dart, which fails when a route has no screen entry.
Why
The assistant reads AppContext navigation (route, location, params) to know where the person is, and attachRouter in lib/ai/go_router_adapter.dart keeps it in step with GoRouter. A screen opened with Navigator.push is invisible to that, and a second shell would rebuild and lose the chat.
How
- Write the screen under
lib/presentation/<feature>/. - Add
GoRoute(path: '/thing/:id', builder: ...)inside the shell'srouteslist. A screen opened from another goes in that screen'sroutes(Settings sits under/assettings), socontext.gostacks it and back returns there. A nested path is joined to its parent;routePatternsinlib/ai/go_router_adapter.dartcomputes the full pattern that the parity test compares. - Add the same pattern to
buildScreenContexts. Return a short summary with counts and the first rows, always with ids, never a key./and/settingsthere are the models. - Link with
context.go('/thing/$id'). Read path values fromstate.pathParametersin the route builder. - The assistant's
navigateaction callsrouter.go(location)throughappContext.onNavigate, set inattachRouter. Anything it can reach must be a real route. - Deep links: a deep link is a route path, so
/thing/42opens that screen if the route exists. The repo configures no platform URL scheme or app link (no intent filter inandroid/, no URL types inios/); add that only when the task asks for it.
Anti-patterns
Navigator.of(context).push(MaterialPageRoute(...)).- A route with no screen-context entry (the parity test names it).
- Putting an id or secret in a query string that is sent to the model as
location. - Building a second
MaterialApp.routeror shell for a "full screen" page. - Mutating data inside a route builder.
Verification
flutter test test/ai/parity_test.dart test/ai/go_router_adapter_test.dart test/ai/screen_contexts_test.dartdart analyze --fatal-infosreportsno_navigator_push.test/presentation/assistant/assistant_shell_test.dartcovers the shell.tool/check.shends withAll checks passed.
Related skills
app-context— how the screen summary is built and used.adding-a-feature— the full list for a new feature.ui-design— what the new screen must handle.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

