[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-planning":3,"mdc--k14j58-key":36,"related-org-aws-labs-planning":890,"related-repo-aws-labs-planning":1071},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":19,"repoUrl":20,"updatedAt":21,"license":22,"forks":23,"topics":24,"repo":31,"sourceUrl":34,"mdContent":35},"planning","generate model customization plans","Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"aws-labs","AWS Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws-labs.png","awslabs",[13,16],{"name":14,"slug":4,"type":15},"Planning","tag",{"name":17,"slug":18,"type":15},"AI Infrastructure","ai-infrastructure",831,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagent-plugins","2026-07-12T08:39:35.922247",null,127,[25,26,27,28,29,30],"agent-plugins","agent-skills","agents","aws","coding-agent-skills","coding-agents",{"repoUrl":20,"stars":19,"forks":23,"topics":32,"description":33},[25,26,27,28,29,30],"Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagent-plugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fsagemaker-ai\u002Fskills\u002Fplanning","---\nname: planning\ndescription: Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.\nmetadata:\n  version: \"2.0.0\"\n---\n\n## Principles\n\n- **One question at a time.** Each question should resolve a branching decision in the plan. Avoid generic or out-of-domain questions.\n- **Surface constraints early.** If a user decision would constrain downstream options, flag it before the plan is finalized.\n- **Keep plans short.** Only include tasks that are necessary for the user's stated goal.\n- **Don't ask what you already know.** Check conversation history and project files before asking the user.\n\n---\n\n## Phase 1: Brainstorming\n\n**Goal:** Understand what the user wants to accomplish and identify which skills belong in the plan.\n\nRead `references\u002Finput-output-contracts.md`, `references\u002Fmodel-customization-plan.md`, and `references\u002Fevaluate-first-plan.md` to:\n\n- Identify which skills could be relevant to the user's stated goal.\n- Check whether the user has the necessary input artifacts for each skill. If not, find the skills that generate those inputs and add them first.\n- Order skills to allow a smooth transition from one to the next and avoid dead ends.\n- Check if a recommended workflow matches the user's needs. If not, assess what modifications are needed and verify they are possible against the contracts table.\n- Decide which skills in a matching workflow can be skipped.\n- Surface limitations early — if a user decision (model choice, region, evaluation method) would constrain downstream options, mention it proactively, get user feedback, and adapt the plan accordingly.\n\n**During brainstorming:**\n\n- **Workflow choice gate:** Before generating any plan, determine whether the user wants the evaluate-first workflow or the direct fine-tuning workflow. If the user has explicitly chosen (e.g., \"evaluate first\", \"skip evaluation\", \"already evaluated the base model\"), proceed with their choice. Otherwise, present both options with brief pros\u002Fcons and ask the user to choose. Saying \"fine-tune\" or naming a technique alone is NOT an explicit choice to skip evaluation — the user may not know evaluate-first is an option. Do NOT present a plan until the user has chosen a path. After they choose, read ONLY the corresponding reference plan.\n- Use the Restrictions column of the contracts table to flag constraints as soon as the relevant decision is made. Examples (non-comprehensive list, check contracts table for the full picture):\n  - User picks a Nova model → alert that deployment regions are limited.\n  - User picks a region → alert if it conflicts with model availability.\n- If a restriction applies, check whether it requires changes to other steps in the plan.\n- Do NOT ask the user about base model selection or preferences. Model selection is handled exclusively by the `model-selection` skill.\n- Move to Phase 2 as soon as you can determine which skills and tools the plan needs.\n\n---\n\n## Phase 2: Plan Generation\n\n**Goal:** Propose a structured plan for the user to review.\n\nGenerate a plan as a numbered list of tasks. Each task has:\n\n- A short name\n- A one-sentence description of what happens\n- Which skill handles it (if applicable)\n\n**Format:**\n\n```\nBased on what you've described, here's what I propose:\n\n1. ⬜ **[Task Name]** — [What happens]. *(Skill: [skill-name])*\n2. ⬜ **[Task Name]** — [What happens]. *(Skill: [skill-name])*\n3. ⬜ **[Task Name]** — [What happens]. *(Skill: [skill-name])*\n\nDoes this plan look right, or would you like to change anything?\n```\n\n**Rules for plan generation:**\n\n- Infer ordering from the Prerequisites column in the contracts table — a skill cannot appear before its prerequisites. If unsure, consult `references\u002Fskill-routing-constraints.md`.\n- Only offer capabilities covered by an available skill. If the user needs something no skill supports, say so.\n- Tailor the plan to the user's actual intent. Not every plan needs every skill.\n- If the user already has input artifacts (e.g., a trained model), skip the steps that produce them.\n\nWhen the user approves the plan, write it to `PLAN.md` and save it under the project directory structure defined by the directory-management skill.\n\n```markdown\n# Plan\n\n1. ⬜ **[Task Name]** — [Description]. _(Skill: [skill-name])_\n2. ⬜ **[Task Name]** — [Description]. _(Skill: [skill-name])_\n3. ⬜ **[Task Name]** — [Description]. _(Skill: [skill-name])_\n```\n\n**Status indicators:**\n\n- ⬜ Not Started\n- 🔄 In Progress\n- ✅ Completed\n\nUpdate `PLAN.md` whenever a task's status changes.\n\n---\n\n## Phase 3: Plan Iteration\n\n**Goal:** Refine the plan until the user approves it.\n\n- If the user suggests changes, regenerate the plan incorporating their feedback.\n- If the user approves, begin execution by handing off to the first task's skill.\n\n---\n\n## Execution\n\nOnce the plan is approved:\n\n1. Before starting a task, update its status in `PLAN.md` to 🔄 (In Progress).\n2. If the task maps to a skill, load that skill's full SKILL.md before doing any work. Do not attempt the task from general knowledge — always defer to the skill's instructions.\n3. Execute the task by following the loaded skill's workflow.\n4. When the task completes:\n   - Update its status in `PLAN.md` to ✅ (Completed). If the task generated output files (scripts, notebooks, manifests), record the file paths under the completed task:\n\n     ```\n     - [x] Fine-tune model\n       - Output: `scripts\u002F01_sft_finetuning.py`\n       - Output: `manifests\u002Fsft-llama-20260515.json`\n     ```\n\n   - Briefly confirm completion and move to the next task.\n5. If the user interrupts with a new request mid-execution:\n   - Completed tasks are immutable — do NOT modify them.\n   - Regenerate the remaining tasks to incorporate the user's new input.\n   - Present the updated remainder for approval before continuing.\n\n---\n\n## Plan Completion\n\nWhen all tasks in the plan are done:\nPresent to the user:\n\n> \"We've completed everything in the plan. What would you like to do next?\"\n\nThis re-enters Phase 1 (Brainstorming) for a new goal. There is no terminal state — the conversation continues as long as the user wants.\n\n---\n\n## References\n\nLoad the reference plan that matches the customer's intent, then adjust based on their needs.\n\n- `references\u002Fevaluate-first-plan.md` — The evaluate-first workflow: evaluate a base model before deciding whether to fine-tune.\n- `references\u002Fmodel-customization-plan.md` — The direct fine-tuning plan. Use when the user has explicitly committed to fine-tuning.\n- `references\u002Finput-output-contracts.md` - A table showing all skills, required inputs, produced outputs, prerequisites, and constraints.\n- `references\u002Fskill-routing-constraints.md` — Optional supplemental resource about Mandatory inclusion rules, ordering constraints, and skill boundary rules.\n",{"data":37,"body":40},{"name":4,"description":6,"metadata":38},{"version":39},"2.0.0",{"type":41,"children":42},"root",[43,52,98,102,108,119,149,182,190,244,247,253,262,267,285,293,305,313,344,357,633,641,659,671,674,680,689,702,705,711,716,799,802,808,813,822,827,830,836,841,884],{"type":44,"tag":45,"props":46,"children":48},"element","h2",{"id":47},"principles",[49],{"type":50,"value":51},"text","Principles",{"type":44,"tag":53,"props":54,"children":55},"ul",{},[56,68,78,88],{"type":44,"tag":57,"props":58,"children":59},"li",{},[60,66],{"type":44,"tag":61,"props":62,"children":63},"strong",{},[64],{"type":50,"value":65},"One question at a time.",{"type":50,"value":67}," Each question should resolve a branching decision in the plan. Avoid generic or out-of-domain questions.",{"type":44,"tag":57,"props":69,"children":70},{},[71,76],{"type":44,"tag":61,"props":72,"children":73},{},[74],{"type":50,"value":75},"Surface constraints early.",{"type":50,"value":77}," If a user decision would constrain downstream options, flag it before the plan is finalized.",{"type":44,"tag":57,"props":79,"children":80},{},[81,86],{"type":44,"tag":61,"props":82,"children":83},{},[84],{"type":50,"value":85},"Keep plans short.",{"type":50,"value":87}," Only include tasks that are necessary for the user's stated goal.",{"type":44,"tag":57,"props":89,"children":90},{},[91,96],{"type":44,"tag":61,"props":92,"children":93},{},[94],{"type":50,"value":95},"Don't ask what you already know.",{"type":50,"value":97}," Check conversation history and project files before asking the user.",{"type":44,"tag":99,"props":100,"children":101},"hr",{},[],{"type":44,"tag":45,"props":103,"children":105},{"id":104},"phase-1-brainstorming",[106],{"type":50,"value":107},"Phase 1: Brainstorming",{"type":44,"tag":109,"props":110,"children":111},"p",{},[112,117],{"type":44,"tag":61,"props":113,"children":114},{},[115],{"type":50,"value":116},"Goal:",{"type":50,"value":118}," Understand what the user wants to accomplish and identify which skills belong in the plan.",{"type":44,"tag":109,"props":120,"children":121},{},[122,124,131,133,139,141,147],{"type":50,"value":123},"Read ",{"type":44,"tag":125,"props":126,"children":128},"code",{"className":127},[],[129],{"type":50,"value":130},"references\u002Finput-output-contracts.md",{"type":50,"value":132},", ",{"type":44,"tag":125,"props":134,"children":136},{"className":135},[],[137],{"type":50,"value":138},"references\u002Fmodel-customization-plan.md",{"type":50,"value":140},", and ",{"type":44,"tag":125,"props":142,"children":144},{"className":143},[],[145],{"type":50,"value":146},"references\u002Fevaluate-first-plan.md",{"type":50,"value":148}," to:",{"type":44,"tag":53,"props":150,"children":151},{},[152,157,162,167,172,177],{"type":44,"tag":57,"props":153,"children":154},{},[155],{"type":50,"value":156},"Identify which skills could be relevant to the user's stated goal.",{"type":44,"tag":57,"props":158,"children":159},{},[160],{"type":50,"value":161},"Check whether the user has the necessary input artifacts for each skill. If not, find the skills that generate those inputs and add them first.",{"type":44,"tag":57,"props":163,"children":164},{},[165],{"type":50,"value":166},"Order skills to allow a smooth transition from one to the next and avoid dead ends.",{"type":44,"tag":57,"props":168,"children":169},{},[170],{"type":50,"value":171},"Check if a recommended workflow matches the user's needs. If not, assess what modifications are needed and verify they are possible against the contracts table.",{"type":44,"tag":57,"props":173,"children":174},{},[175],{"type":50,"value":176},"Decide which skills in a matching workflow can be skipped.",{"type":44,"tag":57,"props":178,"children":179},{},[180],{"type":50,"value":181},"Surface limitations early — if a user decision (model choice, region, evaluation method) would constrain downstream options, mention it proactively, get user feedback, and adapt the plan accordingly.",{"type":44,"tag":109,"props":183,"children":184},{},[185],{"type":44,"tag":61,"props":186,"children":187},{},[188],{"type":50,"value":189},"During brainstorming:",{"type":44,"tag":53,"props":191,"children":192},{},[193,203,221,226,239],{"type":44,"tag":57,"props":194,"children":195},{},[196,201],{"type":44,"tag":61,"props":197,"children":198},{},[199],{"type":50,"value":200},"Workflow choice gate:",{"type":50,"value":202}," Before generating any plan, determine whether the user wants the evaluate-first workflow or the direct fine-tuning workflow. If the user has explicitly chosen (e.g., \"evaluate first\", \"skip evaluation\", \"already evaluated the base model\"), proceed with their choice. Otherwise, present both options with brief pros\u002Fcons and ask the user to choose. Saying \"fine-tune\" or naming a technique alone is NOT an explicit choice to skip evaluation — the user may not know evaluate-first is an option. Do NOT present a plan until the user has chosen a path. After they choose, read ONLY the corresponding reference plan.",{"type":44,"tag":57,"props":204,"children":205},{},[206,208],{"type":50,"value":207},"Use the Restrictions column of the contracts table to flag constraints as soon as the relevant decision is made. Examples (non-comprehensive list, check contracts table for the full picture):\n",{"type":44,"tag":53,"props":209,"children":210},{},[211,216],{"type":44,"tag":57,"props":212,"children":213},{},[214],{"type":50,"value":215},"User picks a Nova model → alert that deployment regions are limited.",{"type":44,"tag":57,"props":217,"children":218},{},[219],{"type":50,"value":220},"User picks a region → alert if it conflicts with model availability.",{"type":44,"tag":57,"props":222,"children":223},{},[224],{"type":50,"value":225},"If a restriction applies, check whether it requires changes to other steps in the plan.",{"type":44,"tag":57,"props":227,"children":228},{},[229,231,237],{"type":50,"value":230},"Do NOT ask the user about base model selection or preferences. Model selection is handled exclusively by the ",{"type":44,"tag":125,"props":232,"children":234},{"className":233},[],[235],{"type":50,"value":236},"model-selection",{"type":50,"value":238}," skill.",{"type":44,"tag":57,"props":240,"children":241},{},[242],{"type":50,"value":243},"Move to Phase 2 as soon as you can determine which skills and tools the plan needs.",{"type":44,"tag":99,"props":245,"children":246},{},[],{"type":44,"tag":45,"props":248,"children":250},{"id":249},"phase-2-plan-generation",[251],{"type":50,"value":252},"Phase 2: Plan Generation",{"type":44,"tag":109,"props":254,"children":255},{},[256,260],{"type":44,"tag":61,"props":257,"children":258},{},[259],{"type":50,"value":116},{"type":50,"value":261}," Propose a structured plan for the user to review.",{"type":44,"tag":109,"props":263,"children":264},{},[265],{"type":50,"value":266},"Generate a plan as a numbered list of tasks. Each task has:",{"type":44,"tag":53,"props":268,"children":269},{},[270,275,280],{"type":44,"tag":57,"props":271,"children":272},{},[273],{"type":50,"value":274},"A short name",{"type":44,"tag":57,"props":276,"children":277},{},[278],{"type":50,"value":279},"A one-sentence description of what happens",{"type":44,"tag":57,"props":281,"children":282},{},[283],{"type":50,"value":284},"Which skill handles it (if applicable)",{"type":44,"tag":109,"props":286,"children":287},{},[288],{"type":44,"tag":61,"props":289,"children":290},{},[291],{"type":50,"value":292},"Format:",{"type":44,"tag":294,"props":295,"children":299},"pre",{"className":296,"code":298,"language":50},[297],"language-text","Based on what you've described, here's what I propose:\n\n1. ⬜ **[Task Name]** — [What happens]. *(Skill: [skill-name])*\n2. ⬜ **[Task Name]** — [What happens]. *(Skill: [skill-name])*\n3. ⬜ **[Task Name]** — [What happens]. *(Skill: [skill-name])*\n\nDoes this plan look right, or would you like to change anything?\n",[300],{"type":44,"tag":125,"props":301,"children":303},{"__ignoreMap":302},"",[304],{"type":50,"value":298},{"type":44,"tag":109,"props":306,"children":307},{},[308],{"type":44,"tag":61,"props":309,"children":310},{},[311],{"type":50,"value":312},"Rules for plan generation:",{"type":44,"tag":53,"props":314,"children":315},{},[316,329,334,339],{"type":44,"tag":57,"props":317,"children":318},{},[319,321,327],{"type":50,"value":320},"Infer ordering from the Prerequisites column in the contracts table — a skill cannot appear before its prerequisites. If unsure, consult ",{"type":44,"tag":125,"props":322,"children":324},{"className":323},[],[325],{"type":50,"value":326},"references\u002Fskill-routing-constraints.md",{"type":50,"value":328},".",{"type":44,"tag":57,"props":330,"children":331},{},[332],{"type":50,"value":333},"Only offer capabilities covered by an available skill. If the user needs something no skill supports, say so.",{"type":44,"tag":57,"props":335,"children":336},{},[337],{"type":50,"value":338},"Tailor the plan to the user's actual intent. Not every plan needs every skill.",{"type":44,"tag":57,"props":340,"children":341},{},[342],{"type":50,"value":343},"If the user already has input artifacts (e.g., a trained model), skip the steps that produce them.",{"type":44,"tag":109,"props":345,"children":346},{},[347,349,355],{"type":50,"value":348},"When the user approves the plan, write it to ",{"type":44,"tag":125,"props":350,"children":352},{"className":351},[],[353],{"type":50,"value":354},"PLAN.md",{"type":50,"value":356}," and save it under the project directory structure defined by the directory-management skill.",{"type":44,"tag":294,"props":358,"children":362},{"className":359,"code":360,"language":361,"meta":302,"style":302},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Plan\n\n1. ⬜ **[Task Name]** — [Description]. _(Skill: [skill-name])_\n2. ⬜ **[Task Name]** — [Description]. _(Skill: [skill-name])_\n3. ⬜ **[Task Name]** — [Description]. _(Skill: [skill-name])_\n","markdown",[363],{"type":44,"tag":125,"props":364,"children":365},{"__ignoreMap":302},[366,384,394,487,560],{"type":44,"tag":367,"props":368,"children":371},"span",{"class":369,"line":370},"line",1,[372,378],{"type":44,"tag":367,"props":373,"children":375},{"style":374},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[376],{"type":50,"value":377},"# ",{"type":44,"tag":367,"props":379,"children":381},{"style":380},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[382],{"type":50,"value":383},"Plan\n",{"type":44,"tag":367,"props":385,"children":387},{"class":369,"line":386},2,[388],{"type":44,"tag":367,"props":389,"children":391},{"emptyLinePlaceholder":390},true,[392],{"type":50,"value":393},"\n",{"type":44,"tag":367,"props":395,"children":397},{"class":369,"line":396},3,[398,403,409,415,421,425,430,435,441,446,451,457,463,467,473,477,482],{"type":44,"tag":367,"props":399,"children":400},{"style":374},[401],{"type":50,"value":402},"1.",{"type":44,"tag":367,"props":404,"children":406},{"style":405},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[407],{"type":50,"value":408}," ⬜ ",{"type":44,"tag":367,"props":410,"children":412},{"style":411},"--shiki-light:#39ADB5;--shiki-light-font-weight:bold;--shiki-default:#89DDFF;--shiki-default-font-weight:bold;--shiki-dark:#89DDFF;--shiki-dark-font-weight:bold",[413],{"type":50,"value":414},"**",{"type":44,"tag":367,"props":416,"children":418},{"style":417},"--shiki-light:#E53935;--shiki-light-font-weight:bold;--shiki-default:#F07178;--shiki-default-font-weight:bold;--shiki-dark:#F07178;--shiki-dark-font-weight:bold",[419],{"type":50,"value":420},"[Task Name]",{"type":44,"tag":367,"props":422,"children":423},{"style":411},[424],{"type":50,"value":414},{"type":44,"tag":367,"props":426,"children":427},{"style":405},[428],{"type":50,"value":429}," — ",{"type":44,"tag":367,"props":431,"children":432},{"style":374},[433],{"type":50,"value":434},"[",{"type":44,"tag":367,"props":436,"children":438},{"style":437},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[439],{"type":50,"value":440},"Description",{"type":44,"tag":367,"props":442,"children":443},{"style":374},[444],{"type":50,"value":445},"]",{"type":44,"tag":367,"props":447,"children":448},{"style":405},[449],{"type":50,"value":450},". ",{"type":44,"tag":367,"props":452,"children":454},{"style":453},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[455],{"type":50,"value":456},"_",{"type":44,"tag":367,"props":458,"children":460},{"style":459},"--shiki-light:#E53935;--shiki-light-font-style:italic;--shiki-default:#F07178;--shiki-default-font-style:italic;--shiki-dark:#F07178;--shiki-dark-font-style:italic",[461],{"type":50,"value":462},"(Skill: ",{"type":44,"tag":367,"props":464,"children":465},{"style":453},[466],{"type":50,"value":434},{"type":44,"tag":367,"props":468,"children":470},{"style":469},"--shiki-light:#91B859;--shiki-light-font-style:italic;--shiki-default:#C3E88D;--shiki-default-font-style:italic;--shiki-dark:#C3E88D;--shiki-dark-font-style:italic",[471],{"type":50,"value":472},"skill-name",{"type":44,"tag":367,"props":474,"children":475},{"style":453},[476],{"type":50,"value":445},{"type":44,"tag":367,"props":478,"children":479},{"style":459},[480],{"type":50,"value":481},")",{"type":44,"tag":367,"props":483,"children":484},{"style":453},[485],{"type":50,"value":486},"_\n",{"type":44,"tag":367,"props":488,"children":490},{"class":369,"line":489},4,[491,496,500,504,508,512,516,520,524,528,532,536,540,544,548,552,556],{"type":44,"tag":367,"props":492,"children":493},{"style":374},[494],{"type":50,"value":495},"2.",{"type":44,"tag":367,"props":497,"children":498},{"style":405},[499],{"type":50,"value":408},{"type":44,"tag":367,"props":501,"children":502},{"style":411},[503],{"type":50,"value":414},{"type":44,"tag":367,"props":505,"children":506},{"style":417},[507],{"type":50,"value":420},{"type":44,"tag":367,"props":509,"children":510},{"style":411},[511],{"type":50,"value":414},{"type":44,"tag":367,"props":513,"children":514},{"style":405},[515],{"type":50,"value":429},{"type":44,"tag":367,"props":517,"children":518},{"style":374},[519],{"type":50,"value":434},{"type":44,"tag":367,"props":521,"children":522},{"style":437},[523],{"type":50,"value":440},{"type":44,"tag":367,"props":525,"children":526},{"style":374},[527],{"type":50,"value":445},{"type":44,"tag":367,"props":529,"children":530},{"style":405},[531],{"type":50,"value":450},{"type":44,"tag":367,"props":533,"children":534},{"style":453},[535],{"type":50,"value":456},{"type":44,"tag":367,"props":537,"children":538},{"style":459},[539],{"type":50,"value":462},{"type":44,"tag":367,"props":541,"children":542},{"style":453},[543],{"type":50,"value":434},{"type":44,"tag":367,"props":545,"children":546},{"style":469},[547],{"type":50,"value":472},{"type":44,"tag":367,"props":549,"children":550},{"style":453},[551],{"type":50,"value":445},{"type":44,"tag":367,"props":553,"children":554},{"style":459},[555],{"type":50,"value":481},{"type":44,"tag":367,"props":557,"children":558},{"style":453},[559],{"type":50,"value":486},{"type":44,"tag":367,"props":561,"children":563},{"class":369,"line":562},5,[564,569,573,577,581,585,589,593,597,601,605,609,613,617,621,625,629],{"type":44,"tag":367,"props":565,"children":566},{"style":374},[567],{"type":50,"value":568},"3.",{"type":44,"tag":367,"props":570,"children":571},{"style":405},[572],{"type":50,"value":408},{"type":44,"tag":367,"props":574,"children":575},{"style":411},[576],{"type":50,"value":414},{"type":44,"tag":367,"props":578,"children":579},{"style":417},[580],{"type":50,"value":420},{"type":44,"tag":367,"props":582,"children":583},{"style":411},[584],{"type":50,"value":414},{"type":44,"tag":367,"props":586,"children":587},{"style":405},[588],{"type":50,"value":429},{"type":44,"tag":367,"props":590,"children":591},{"style":374},[592],{"type":50,"value":434},{"type":44,"tag":367,"props":594,"children":595},{"style":437},[596],{"type":50,"value":440},{"type":44,"tag":367,"props":598,"children":599},{"style":374},[600],{"type":50,"value":445},{"type":44,"tag":367,"props":602,"children":603},{"style":405},[604],{"type":50,"value":450},{"type":44,"tag":367,"props":606,"children":607},{"style":453},[608],{"type":50,"value":456},{"type":44,"tag":367,"props":610,"children":611},{"style":459},[612],{"type":50,"value":462},{"type":44,"tag":367,"props":614,"children":615},{"style":453},[616],{"type":50,"value":434},{"type":44,"tag":367,"props":618,"children":619},{"style":469},[620],{"type":50,"value":472},{"type":44,"tag":367,"props":622,"children":623},{"style":453},[624],{"type":50,"value":445},{"type":44,"tag":367,"props":626,"children":627},{"style":459},[628],{"type":50,"value":481},{"type":44,"tag":367,"props":630,"children":631},{"style":453},[632],{"type":50,"value":486},{"type":44,"tag":109,"props":634,"children":635},{},[636],{"type":44,"tag":61,"props":637,"children":638},{},[639],{"type":50,"value":640},"Status indicators:",{"type":44,"tag":53,"props":642,"children":643},{},[644,649,654],{"type":44,"tag":57,"props":645,"children":646},{},[647],{"type":50,"value":648},"⬜ Not Started",{"type":44,"tag":57,"props":650,"children":651},{},[652],{"type":50,"value":653},"🔄 In Progress",{"type":44,"tag":57,"props":655,"children":656},{},[657],{"type":50,"value":658},"✅ Completed",{"type":44,"tag":109,"props":660,"children":661},{},[662,664,669],{"type":50,"value":663},"Update ",{"type":44,"tag":125,"props":665,"children":667},{"className":666},[],[668],{"type":50,"value":354},{"type":50,"value":670}," whenever a task's status changes.",{"type":44,"tag":99,"props":672,"children":673},{},[],{"type":44,"tag":45,"props":675,"children":677},{"id":676},"phase-3-plan-iteration",[678],{"type":50,"value":679},"Phase 3: Plan Iteration",{"type":44,"tag":109,"props":681,"children":682},{},[683,687],{"type":44,"tag":61,"props":684,"children":685},{},[686],{"type":50,"value":116},{"type":50,"value":688}," Refine the plan until the user approves it.",{"type":44,"tag":53,"props":690,"children":691},{},[692,697],{"type":44,"tag":57,"props":693,"children":694},{},[695],{"type":50,"value":696},"If the user suggests changes, regenerate the plan incorporating their feedback.",{"type":44,"tag":57,"props":698,"children":699},{},[700],{"type":50,"value":701},"If the user approves, begin execution by handing off to the first task's skill.",{"type":44,"tag":99,"props":703,"children":704},{},[],{"type":44,"tag":45,"props":706,"children":708},{"id":707},"execution",[709],{"type":50,"value":710},"Execution",{"type":44,"tag":109,"props":712,"children":713},{},[714],{"type":50,"value":715},"Once the plan is approved:",{"type":44,"tag":717,"props":718,"children":719},"ol",{},[720,732,737,742,776],{"type":44,"tag":57,"props":721,"children":722},{},[723,725,730],{"type":50,"value":724},"Before starting a task, update its status in ",{"type":44,"tag":125,"props":726,"children":728},{"className":727},[],[729],{"type":50,"value":354},{"type":50,"value":731}," to 🔄 (In Progress).",{"type":44,"tag":57,"props":733,"children":734},{},[735],{"type":50,"value":736},"If the task maps to a skill, load that skill's full SKILL.md before doing any work. Do not attempt the task from general knowledge — always defer to the skill's instructions.",{"type":44,"tag":57,"props":738,"children":739},{},[740],{"type":50,"value":741},"Execute the task by following the loaded skill's workflow.",{"type":44,"tag":57,"props":743,"children":744},{},[745,747],{"type":50,"value":746},"When the task completes:\n",{"type":44,"tag":53,"props":748,"children":749},{},[750,771],{"type":44,"tag":57,"props":751,"children":752},{},[753,755,760,762],{"type":50,"value":754},"Update its status in ",{"type":44,"tag":125,"props":756,"children":758},{"className":757},[],[759],{"type":50,"value":354},{"type":50,"value":761}," to ✅ (Completed). If the task generated output files (scripts, notebooks, manifests), record the file paths under the completed task:",{"type":44,"tag":294,"props":763,"children":766},{"className":764,"code":765,"language":50},[297],"- [x] Fine-tune model\n  - Output: `scripts\u002F01_sft_finetuning.py`\n  - Output: `manifests\u002Fsft-llama-20260515.json`\n",[767],{"type":44,"tag":125,"props":768,"children":769},{"__ignoreMap":302},[770],{"type":50,"value":765},{"type":44,"tag":57,"props":772,"children":773},{},[774],{"type":50,"value":775},"Briefly confirm completion and move to the next task.",{"type":44,"tag":57,"props":777,"children":778},{},[779,781],{"type":50,"value":780},"If the user interrupts with a new request mid-execution:\n",{"type":44,"tag":53,"props":782,"children":783},{},[784,789,794],{"type":44,"tag":57,"props":785,"children":786},{},[787],{"type":50,"value":788},"Completed tasks are immutable — do NOT modify them.",{"type":44,"tag":57,"props":790,"children":791},{},[792],{"type":50,"value":793},"Regenerate the remaining tasks to incorporate the user's new input.",{"type":44,"tag":57,"props":795,"children":796},{},[797],{"type":50,"value":798},"Present the updated remainder for approval before continuing.",{"type":44,"tag":99,"props":800,"children":801},{},[],{"type":44,"tag":45,"props":803,"children":805},{"id":804},"plan-completion",[806],{"type":50,"value":807},"Plan Completion",{"type":44,"tag":109,"props":809,"children":810},{},[811],{"type":50,"value":812},"When all tasks in the plan are done:\nPresent to the user:",{"type":44,"tag":814,"props":815,"children":816},"blockquote",{},[817],{"type":44,"tag":109,"props":818,"children":819},{},[820],{"type":50,"value":821},"\"We've completed everything in the plan. What would you like to do next?\"",{"type":44,"tag":109,"props":823,"children":824},{},[825],{"type":50,"value":826},"This re-enters Phase 1 (Brainstorming) for a new goal. There is no terminal state — the conversation continues as long as the user wants.",{"type":44,"tag":99,"props":828,"children":829},{},[],{"type":44,"tag":45,"props":831,"children":833},{"id":832},"references",[834],{"type":50,"value":835},"References",{"type":44,"tag":109,"props":837,"children":838},{},[839],{"type":50,"value":840},"Load the reference plan that matches the customer's intent, then adjust based on their needs.",{"type":44,"tag":53,"props":842,"children":843},{},[844,854,864,874],{"type":44,"tag":57,"props":845,"children":846},{},[847,852],{"type":44,"tag":125,"props":848,"children":850},{"className":849},[],[851],{"type":50,"value":146},{"type":50,"value":853}," — The evaluate-first workflow: evaluate a base model before deciding whether to fine-tune.",{"type":44,"tag":57,"props":855,"children":856},{},[857,862],{"type":44,"tag":125,"props":858,"children":860},{"className":859},[],[861],{"type":50,"value":138},{"type":50,"value":863}," — The direct fine-tuning plan. Use when the user has explicitly committed to fine-tuning.",{"type":44,"tag":57,"props":865,"children":866},{},[867,872],{"type":44,"tag":125,"props":868,"children":870},{"className":869},[],[871],{"type":50,"value":130},{"type":50,"value":873}," - A table showing all skills, required inputs, produced outputs, prerequisites, and constraints.",{"type":44,"tag":57,"props":875,"children":876},{},[877,882],{"type":44,"tag":125,"props":878,"children":880},{"className":879},[],[881],{"type":50,"value":326},{"type":50,"value":883}," — Optional supplemental resource about Mandatory inclusion rules, ordering constraints, and skill boundary rules.",{"type":44,"tag":885,"props":886,"children":887},"style",{},[888],{"type":50,"value":889},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":891,"total":1070},[892,912,933,943,956,969,979,989,1010,1025,1040,1055],{"slug":893,"name":893,"fn":894,"description":895,"org":896,"tags":897,"stars":909,"repoUrl":910,"updatedAt":911},"agentcore-investigation","investigate Bedrock AgentCore runtime sessions","Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session\u002Ftrace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[898,900,903,906],{"name":899,"slug":28,"type":15},"AWS",{"name":901,"slug":902,"type":15},"Debugging","debugging",{"name":904,"slug":905,"type":15},"Logs","logs",{"name":907,"slug":908,"type":15},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":913,"name":914,"fn":915,"description":916,"org":917,"tags":918,"stars":909,"repoUrl":910,"updatedAt":932},"amazon-aurora-dsql","amazon aurora dsql","build applications with Aurora DSQL","Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django\u002FHibernate\u002FRails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[919,922,923,926,929],{"name":920,"slug":921,"type":15},"Aurora","aurora",{"name":899,"slug":28,"type":15},{"name":924,"slug":925,"type":15},"Database","database",{"name":927,"slug":928,"type":15},"Serverless","serverless",{"name":930,"slug":931,"type":15},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":934,"name":935,"fn":915,"description":916,"org":936,"tags":937,"stars":909,"repoUrl":910,"updatedAt":942},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[938,939,940,941],{"name":899,"slug":28,"type":15},{"name":924,"slug":925,"type":15},{"name":927,"slug":928,"type":15},{"name":930,"slug":931,"type":15},"2026-07-12T08:36:42.694299",{"slug":944,"name":945,"fn":915,"description":916,"org":946,"tags":947,"stars":909,"repoUrl":910,"updatedAt":955},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[948,949,950,953,954],{"name":899,"slug":28,"type":15},{"name":924,"slug":925,"type":15},{"name":951,"slug":952,"type":15},"Migration","migration",{"name":927,"slug":928,"type":15},{"name":930,"slug":931,"type":15},"2026-07-12T08:36:38.584057",{"slug":957,"name":958,"fn":915,"description":916,"org":959,"tags":960,"stars":909,"repoUrl":910,"updatedAt":968},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[961,962,963,966,967],{"name":899,"slug":28,"type":15},{"name":924,"slug":925,"type":15},{"name":964,"slug":965,"type":15},"PostgreSQL","postgresql",{"name":927,"slug":928,"type":15},{"name":930,"slug":931,"type":15},"2026-07-12T08:36:46.530743",{"slug":970,"name":971,"fn":915,"description":916,"org":972,"tags":973,"stars":909,"repoUrl":910,"updatedAt":978},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[974,975,976,977],{"name":899,"slug":28,"type":15},{"name":924,"slug":925,"type":15},{"name":927,"slug":928,"type":15},{"name":930,"slug":931,"type":15},"2026-07-12T08:36:48.104182",{"slug":980,"name":980,"fn":915,"description":916,"org":981,"tags":982,"stars":909,"repoUrl":910,"updatedAt":988},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[983,984,985,986,987],{"name":899,"slug":28,"type":15},{"name":924,"slug":925,"type":15},{"name":951,"slug":952,"type":15},{"name":927,"slug":928,"type":15},{"name":930,"slug":931,"type":15},"2026-07-12T08:36:36.374512",{"slug":990,"name":990,"fn":991,"description":992,"org":993,"tags":994,"stars":1007,"repoUrl":1008,"updatedAt":1009},"cost-efficiency-analyzer","analyze cost efficiency and expenses","Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for \"are we spending too much\", \"cost breakdown\", \"expense analysis\", or \"how efficient are our operations\". NOT for revenue or top-line analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[995,998,1001,1004],{"name":996,"slug":997,"type":15},"Accounting","accounting",{"name":999,"slug":1000,"type":15},"Analytics","analytics",{"name":1002,"slug":1003,"type":15},"Cost Optimization","cost-optimization",{"name":1005,"slug":1006,"type":15},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":1011,"name":1011,"fn":1012,"description":1013,"org":1014,"tags":1015,"stars":1007,"repoUrl":1008,"updatedAt":1024},"executive-financial-briefing","generate executive financial briefings","Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or \"how is the business doing\". Covers the full P&L picture in one page. Also use for \"give me the highlights\", \"what do I need to know\", or \"quick financial update\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1016,1017,1018,1021],{"name":899,"slug":28,"type":15},{"name":1005,"slug":1006,"type":15},{"name":1019,"slug":1020,"type":15},"Management","management",{"name":1022,"slug":1023,"type":15},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":1026,"name":1026,"fn":1027,"description":1028,"org":1029,"tags":1030,"stars":1007,"repoUrl":1008,"updatedAt":1039},"multi-quarter-trend-analysis","analyze multi-quarter financial trends","Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for \"how are we trending\", \"show me the trend\", \"track performance over time\", \"quarter over quarter comparison across all quarters\", or any multi-period longitudinal analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1031,1032,1033,1036],{"name":999,"slug":1000,"type":15},{"name":1005,"slug":1006,"type":15},{"name":1034,"slug":1035,"type":15},"Financial Statements","financial-statements",{"name":1037,"slug":1038,"type":15},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":1041,"name":1041,"fn":1042,"description":1043,"org":1044,"tags":1045,"stars":1007,"repoUrl":1008,"updatedAt":1054},"pdf","process and manipulate PDF documents","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1046,1049,1052],{"name":1047,"slug":1048,"type":15},"Automation","automation",{"name":1050,"slug":1051,"type":15},"Documents","documents",{"name":1053,"slug":1041,"type":15},"PDF","2026-07-12T08:41:44.135656",{"slug":1056,"name":1056,"fn":1057,"description":1058,"org":1059,"tags":1060,"stars":1007,"repoUrl":1008,"updatedAt":1069},"quarterly-kpi-calculator","calculate quarterly financial KPIs","Calculates quarterly financial KPIs from P&L data. P&L figures can be provided directly by the user or fetched from the financial data MCP server. Use when the user wants KPI calculations such as Gross Margin %, EBITDA Margin %, Operating Expense Ratio, or Revenue Growth % QoQ. Also use for quarterly performance review, P&L analysis, or interpreting financial ratios against benchmarks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1061,1062,1065,1066],{"name":996,"slug":997,"type":15},{"name":1063,"slug":1064,"type":15},"Data Analysis","data-analysis",{"name":1005,"slug":1006,"type":15},{"name":1067,"slug":1068,"type":15},"KPI","kpi","2026-07-12T08:39:59.54971",150,{"items":1072,"total":1173},[1073,1090,1108,1120,1137,1148,1158],{"slug":1074,"name":1074,"fn":1075,"description":1076,"org":1077,"tags":1078,"stars":19,"repoUrl":20,"updatedAt":1089},"amazon-location-service","integrate Amazon Location Service maps","Integrates Amazon Location Service APIs for AWS applications. Use this skill when users want to add maps (interactive MapLibre or static images); geocode addresses to coordinates or reverse geocode coordinates to addresses; calculate routes, travel times, or service areas; find places and businesses through text search, nearby search, or autocomplete suggestions; retrieve detailed place information including hours, contacts, and addresses; monitor geographical boundaries with geofences; or track device locations. Covers authentication, SDK integration, and all Amazon Location Service capabilities.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1079,1082,1083,1086],{"name":1080,"slug":1081,"type":15},"API Development","api-development",{"name":899,"slug":28,"type":15},{"name":1084,"slug":1085,"type":15},"Maps","maps",{"name":1087,"slug":1088,"type":15},"Navigation","navigation","2026-07-12T08:39:49.88311",{"slug":1091,"name":1091,"fn":1092,"description":1093,"org":1094,"tags":1095,"stars":19,"repoUrl":20,"updatedAt":1107},"amplify-workflow","build and deploy apps with AWS Amplify","Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). Covers auth (Cognito), data (AppSync\u002FDynamoDB including schema modeling, enum types, relationships, authorization rules), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock). Supports React, Next.js, Vue, Angular, React Native, Flutter, Swift, and Android. Always use this skill for Amplify Gen2 topics — even for questions you think you know — it contains validated, version-specific patterns that prevent common mistakes. TRIGGER when: user mentions Amplify Gen2; project has amplify\u002F directory or amplify_outputs; code imports @aws-amplify packages; user asks about defineBackend, defineAuth, defineData, defineStorage, or npx ampx. SKIP: Amplify Gen1 (amplify CLI v6), standalone SAM\u002FCDK without Amplify (use aws-serverless), direct Bedrock without Amplify AI Kit (use bedrock).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1096,1099,1100,1101,1104],{"name":1097,"slug":1098,"type":15},"Auth","auth",{"name":899,"slug":28,"type":15},{"name":924,"slug":925,"type":15},{"name":1102,"slug":1103,"type":15},"Deployment","deployment",{"name":1105,"slug":1106,"type":15},"TypeScript","typescript","2026-07-12T08:39:43.500162",{"slug":1109,"name":1109,"fn":1110,"description":1111,"org":1112,"tags":1113,"stars":19,"repoUrl":20,"updatedAt":1119},"api-gateway","build and manage Amazon API Gateway APIs","Build, manage, and operate APIs with Amazon API Gateway (REST, HTTP, and WebSocket). Triggers on phrases like: API Gateway, REST API, HTTP API, WebSocket API, custom domain, Lambda authorizer, usage plan, throttling, CORS, VPC link, private API. Also covers troubleshooting API Gateway errors (4xx, 5xx, timeout, CORS failures) and IaC templates containing API Gateway resources. For general REST API design unrelated to AWS, do not trigger.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1114,1115,1116],{"name":1080,"slug":1081,"type":15},{"name":899,"slug":28,"type":15},{"name":1117,"slug":1118,"type":15},"REST API","rest-api","2026-07-12T08:39:00.149339",{"slug":1121,"name":1121,"fn":1122,"description":1123,"org":1124,"tags":1125,"stars":19,"repoUrl":20,"updatedAt":1136},"aws-architecture-diagram","generate AWS architecture diagrams","Generate validated AWS architecture diagrams as draw.io XML using official AWS4 icon libraries. Use this skill whenever the user wants to create, generate, or design AWS architecture diagrams, cloud infrastructure diagrams, or system design visuals. Also triggers for requests to visualize existing infrastructure from CloudFormation, CDK, or Terraform code. Supports two modes: analyze an existing codebase to auto-generate diagrams, or brainstorm interactively from scratch. Exports .drawio files with optional PNG\u002FSVG\u002FPDF export via draw.io desktop CLI.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1126,1129,1130,1133],{"name":1127,"slug":1128,"type":15},"Architecture","architecture",{"name":899,"slug":28,"type":15},{"name":1131,"slug":1132,"type":15},"Design","design",{"name":1134,"slug":1135,"type":15},"Diagrams","diagrams","2026-07-12T08:37:11.012278",{"slug":1138,"name":1138,"fn":1139,"description":1140,"org":1141,"tags":1142,"stars":19,"repoUrl":20,"updatedAt":1147},"aws-lambda","build and deploy AWS Lambda functions","Design, build, deploy, test, and debug serverless applications with AWS Lambda. Triggers on phrases like: Lambda function, event source, serverless application, API Gateway, EventBridge, Step Functions, serverless API, event-driven architecture, Lambda trigger. For deploying non-serverless apps to AWS, use deploy-on-aws plugin instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1143,1144,1145,1146],{"name":1080,"slug":1081,"type":15},{"name":899,"slug":28,"type":15},{"name":1102,"slug":1103,"type":15},{"name":927,"slug":928,"type":15},"2026-07-12T08:38:58.598492",{"slug":1149,"name":1149,"fn":1150,"description":1151,"org":1152,"tags":1153,"stars":19,"repoUrl":20,"updatedAt":1157},"aws-lambda-durable-functions","build resilient AWS Lambda durable functions","Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait\u002Fcallback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like: lambda durable functions, workflow orchestration, state machines, retry\u002Fcheckpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, and reliable serverless applications.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1154,1155,1156],{"name":1127,"slug":1128,"type":15},{"name":899,"slug":28,"type":15},{"name":927,"slug":928,"type":15},"2026-07-12T08:39:05.546173",{"slug":1159,"name":1159,"fn":1160,"description":1161,"org":1162,"tags":1163,"stars":19,"repoUrl":20,"updatedAt":1172},"aws-lambda-managed-instances","configure AWS Lambda Managed Instances","Evaluate, configure, and migrate workloads to AWS Lambda Managed Instances (LMI). Triggers on: Lambda Managed Instances, LMI, capacity provider, multi-concurrency Lambda, dedicated instance Lambda, EC2-backed Lambda, cold start elimination, Graviton Lambda, instance type for Lambda, scheduled scaling for LMI, Lambda cost optimization with Reserved Instances or Savings Plans. Also trigger when users describe high-volume predictable workloads seeking cost savings, want to scale LMI capacity on a schedule, or compare Lambda vs EC2 for steady-state traffic. For standard Lambda without LMI, use the aws-lambda skill instead.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1164,1165,1166,1169],{"name":899,"slug":28,"type":15},{"name":1102,"slug":1103,"type":15},{"name":1167,"slug":1168,"type":15},"Infrastructure","infrastructure",{"name":1170,"slug":1171,"type":15},"Performance","performance","2026-07-12T08:39:07.007071",33]