[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EGY2QCP2VNAC8P1CT4SA81":3,"skill-same:01M7EGY2QCP2VNAC8P1CT4SA81":49},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7EGY2QCP2VNAC8P1CT4SA81","speckit-c4-feature",null,"Generate a feature's C4 component diagrams, sequence diagrams and ER diagram in architecture.md","leejsinclair\u002Fspeckit-grill-specify","leejsinclair","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F707675?v=4","01M6DBMMX08NN71ZYZVVBPERES","Lee Sinclair","01M7EGWB5W5WN2X881JPFNY4KF",0,"MIT","https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fc4\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-c4-feature\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: speckit-c4-feature\ndescription: Generate a feature's C4 component diagrams, sequence diagrams and ER diagram in architecture.md\ncompatibility: Requires spec-kit project structure with .specify\u002F directory\nmetadata:\n  author: github-spec-kit\n  source: c4:commands\u002Fspeckit.c4.feature.md\n---\n\n# Generate Feature Architecture Diagrams\n\nWrite the architecture document for the current feature: C4 component views for the\ncontainers it touches, a sequence diagram per flow, an ER diagram of its data, and\nthe list of changes it makes to the project-level views.\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou **MUST** consider the user input before proceeding (if not empty). It may narrow\nthe scope (for example \"only the sequence diagrams\") or name extra flows to cover.\n\n## Prerequisites\n\n1. Run the prerequisites script from the repository root and parse `FEATURE_DIR`,\n   `FEATURE_SPEC` and `IMPL_PLAN` from its JSON output:\n   - **Bash**: `.specify\u002Fscripts\u002Fbash\u002Fcheck-prerequisites.sh --json --paths-only`\n   - **PowerShell**: `.specify\u002Fscripts\u002Fpowershell\u002Fcheck-prerequisites.ps1 -Json -PathsOnly`\n2. If `FEATURE_SPEC` does not exist, stop and tell the user to run\n   `\u002Fspeckit-specify` first.\n3. If `IMPL_PLAN` does not exist, stop and tell the user to run\n   `\u002Fspeckit-plan` first. Component and ER diagrams need the technical\n   decisions recorded there.\n\n## Configuration\n\nRead `.specify\u002Fextensions\u002Fc4\u002Fc4-config.yml` if it exists. Use these defaults for any\nkey that is missing or when the file is absent:\n\n- `architecture_dir`: `.specify\u002Fextensions\u002Fc4\u002Fdocs\u002Farchitecture`\n- `feature_file`: `architecture.md`\n- `mermaid_cli`: `mmdc`\n\nBelow, `ARCH_DIR` is `architecture_dir` resolved from the repository root and\n`FEATURE_ARCH` is `FEATURE_DIR\u002F\u003Cfeature_file>`.\n\n## Steps\n\n1. **Read the rules.** Read `.specify\u002Fextensions\u002Fc4\u002Ftemplates\u002Fc4-conventions.md` in full. Every diagram you\n   write must follow it.\n\n2. **Load the feature.** Read `FEATURE_SPEC` and `IMPL_PLAN`. Read these from\n   `FEATURE_DIR` when they exist: `research.md`, `data-model.md`, `quickstart.md`\n   and every file under `contracts\u002F`.\n\n3. **Load the system views.** Read `ARCH_DIR\u002Fcontext.md`, `ARCH_DIR\u002Fcontainers.md`\n   and `ARCH_DIR\u002Ferd.md` when they exist. Reuse their element aliases, labels and\n   technologies exactly. If none exist, continue: treat every container and entity\n   as new, and say in the final report that `\u002Fspeckit-c4-system` has not\n   been run yet.\n\n4. **Start from the template.** If `FEATURE_ARCH` does not exist, create it from\n   `.specify\u002Fextensions\u002Fc4\u002Ftemplates\u002Fc4-feature-architecture-template.md`. If it exists, update it in place\n   and keep any content that is not an unfilled placeholder.\n\n5. **Fill the header.** Set the feature name, branch and date. Write the system view\n   links as relative paths from `FEATURE_DIR` to `ARCH_DIR`. Remove the link to\n   `data-model.md` or `contracts\u002F` if that artifact does not exist.\n\n6. **Components.** Identify each container this feature adds or changes, from the\n   plan's Technical Context and Project Structure. For each one write a subsection\n   with one `C4Component` diagram and its component table. Show the components the\n   feature touches and the neighbours they call; mark each component New, Changed or\n   Existing, and give its source location from the plan's source tree. Once a\n   diagram's content is complete, choose its declaration order with the \"Layout\n   optimisation\" procedure in the conventions, using\n   `python3 .specify\u002Fextensions\u002Fc4\u002Fscripts\u002Fpython\u002Fc4_layout.py optimise` with `--mmdc \"\u003Cmermaid_cli>\"`. Do not\n   change boundary membership or relationships.\n\n7. **Flows.** Write one `sequenceDiagram` per user story's primary path, in priority\n   order. Add an alternate or failure flow where the spec's edge cases or the\n   contracts make it architecturally significant. Message labels must match the\n   operations in `contracts\u002F`. Fill **Covers** with the functional requirement ids\n   and acceptance scenarios the flow realises.\n\n8. **Data.** If `data-model.md` exists, write one `erDiagram` containing every entity\n   in it, with all attributes, keys and relationships, plus any existing entity they\n   reference (keys only). Fill the entity table. If the feature has no persistent\n   data, replace the section body with `Not applicable: [reason]`.\n\n9. **Architecture Impact.** Compare what you drew with the system views and list\n   every difference: new people or external systems (Context), new or changed\n   containers and container relationships (Containers), new or changed entities,\n   attributes and relationships (ERD). One row with `None` for an unaffected view.\n\n10. **Link from the plan.** Make sure `IMPL_PLAN` has an `## Architecture` section\n    that links to `FEATURE_ARCH` and the three system views with relative paths and\n    summarises the Architecture Impact in one or two sentences. Add the section at\n    the end of the file if it is missing; fill it in if it holds placeholders.\n\n11. **Self-check.** Re-read `FEATURE_ARCH` against the conventions: no placeholder\n    text or template examples left, every Mermaid block starts with its diagram type,\n    every sequence participant exists in a C4 view, every `FK` has a relationship.\n\n## Report\n\nTell the user the path of `FEATURE_ARCH`, how many component, sequence and ER\ndiagrams it contains, the Architecture Impact rows that are not `None`, and anything\nyou could not determine from the feature documents. For each component diagram, say\nwhether its layout was rendered and already sufficient, rendered and optimised (how\nmany candidates, which order was chosen), or not checked. Suggest\n`\u002Fspeckit-c4-validate` as the next step.","# Generate Feature Architecture Diagrams\n\nWrite the architecture document for the current feature: C4 component views for the\ncontainers it touches, a sequence diagram per flow, an ER diagram of its data, and\nthe list of changes it makes to the project-level views.\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou **MUST** consider the user input before proceeding (if not empty). It may narrow\nthe scope (for example \"only the sequence diagrams\") or name extra flows to cover.\n\n## Prerequisites\n\n1. Run the prerequisites script from the repository root and parse `FEATURE_DIR`,\n   `FEATURE_SPEC` and `IMPL_PLAN` from its JSON output:\n   - **Bash**: `.specify\u002Fscripts\u002Fbash\u002Fcheck-prerequisites.sh --json --paths-only`\n   - **PowerShell**: `.specify\u002Fscripts\u002Fpowershell\u002Fcheck-prerequisites.ps1 -Json -PathsOnly`\n2. If `FEATURE_SPEC` does not exist, stop and tell the user to run\n   `\u002Fspeckit-specify` first.\n3. If `IMPL_PLAN` does not exist, stop and tell the user to run\n   `\u002Fspeckit-plan` first. Component and ER diagrams need the technical\n   decisions recorded there.\n\n## Configuration\n\nRead `.specify\u002Fextensions\u002Fc4\u002Fc4-config.yml` if it exists. Use these defaults for any\nkey that is missing or when the file is absent:\n\n- `architecture_dir`: `.specify\u002Fextensions\u002Fc4\u002Fdocs\u002Farchitecture`\n- `feature_file`: `architecture.md`\n- `mermaid_cli`: `mmdc`\n\nBelow, `ARCH_DIR` is `architecture_dir` resolved from the repository root and\n`FEATURE_ARCH` is `FEATURE_DIR\u002F\u003Cfeature_file>`.\n\n## Steps\n\n1. **Read the rules.** Read `.specify\u002Fextensions\u002Fc4\u002Ftemplates\u002Fc4-conventions.md` in full. Every diagram you\n   write must follow it.\n\n2. **Load the feature.** Read `FEATURE_SPEC` and `IMPL_PLAN`. Read these from\n   `FEATURE_DIR` when they exist: `research.md`, `data-model.md`, `quickstart.md`\n   and every file under `contracts\u002F`.\n\n3. **Load the system views.** Read `ARCH_DIR\u002Fcontext.md`, `ARCH_DIR\u002Fcontainers.md`\n   and `ARCH_DIR\u002Ferd.md` when they exist. Reuse their element aliases, labels and\n   technologies exactly. If none exist, continue: treat every container and entity\n   as new, and say in the final report that `\u002Fspeckit-c4-system` has not\n   been run yet.\n\n4. **Start from the template.** If `FEATURE_ARCH` does not exist, create it from\n   `.specify\u002Fextensions\u002Fc4\u002Ftemplates\u002Fc4-feature-architecture-template.md`. If it exists, update it in place\n   and keep any content that is not an unfilled placeholder.\n\n5. **Fill the header.** Set the feature name, branch and date. Write the system view\n   links as relative paths from `FEATURE_DIR` to `ARCH_DIR`. Remove the link to\n   `data-model.md` or `contracts\u002F` if that artifact does not exist.\n\n6. **Components.** Identify each container this feature adds or changes, from the\n   plan's Technical Context and Project Structure. For each one write a subsection\n   with one `C4Component` diagram and its component table. Show the components the\n   feature touches and the neighbours they call; mark each component New, Changed or\n   Existing, and give its source location from the plan's source tree. Once a\n   diagram's content is complete, choose its declaration order with the \"Layout\n   optimisation\" procedure in the conventions, using\n   `python3 .specify\u002Fextensions\u002Fc4\u002Fscripts\u002Fpython\u002Fc4_layout.py optimise` with `--mmdc \"\u003Cmermaid_cli>\"`. Do not\n   change boundary membership or relationships.\n\n7. **Flows.** Write one `sequenceDiagram` per user story's primary path, in priority\n   order. Add an alternate or failure flow where the spec's edge cases or the\n   contracts make it architecturally significant. Message labels must match the\n   operations in `contracts\u002F`. Fill **Covers** with the functional requirement ids\n   and acceptance scenarios the flow realises.\n\n8. **Data.** If `data-model.md` exists, write one `erDiagram` containing every entity\n   in it, with all attributes, keys and relationships, plus any existing entity they\n   reference (keys only). Fill the entity table. If the feature has no persistent\n   data, replace the section body with `Not applicable: [reason]`.\n\n9. **Architecture Impact.** Compare what you drew with the system views and list\n   every difference: new people or external systems (Context), new or changed\n   containers and container relationships (Containers), new or changed entities,\n   attributes and relationships (ERD). One row with `None` for an unaffected view.\n\n10. **Link from the plan.** Make sure `IMPL_PLAN` has an `## Architecture` section\n    that links to `FEATURE_ARCH` and the three system views with relative paths and\n    summarises the Architecture Impact in one or two sentences. Add the section at\n    the end of the file if it is missing; fill it in if it holds placeholders.\n\n11. **Self-check.** Re-read `FEATURE_ARCH` against the conventions: no placeholder\n    text or template examples left, every Mermaid block starts with its diagram type,\n    every sequence participant exists in a C4 view, every `FK` has a relationship.\n\n## Report\n\nTell the user the path of `FEATURE_ARCH`, how many component, sequence and ER\ndiagrams it contains, the Architecture Impact rows that are not `None`, and anything\nyou could not determine from the feature documents. For each component diagram, say\nwhether its layout was rendered and already sufficient, rendered and optimised (how\nmany candidates, which order was chosen), or not checked. Suggest\n`\u002Fspeckit-c4-validate` as the next step.",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","c4:commands\u002Fspeckit.c4.feature.md","Requires spec-kit project structure with .specify\u002F directory","main","4c0d3d4835e0f1b888d86c883ee85fd22dd8682b",".specify\u002Fextensions\u002Fc4\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-c4-feature","https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify","https:\u002F\u002Fgithub.com\u002Fleejsinclair","http:\u002F\u002Fmetatheory.co","2026-10-11 15:59:39",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add leejsinclair\u002Fspeckit-grill-specify --skill speckit-c4-feature",{"tool":41,"command":42},"bunx","bunx skills add leejsinclair\u002Fspeckit-grill-specify --skill speckit-c4-feature",{"tool":44,"command":45},"pnpm","pnpm dlx skills add leejsinclair\u002Fspeckit-grill-specify --skill speckit-c4-feature","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fc4\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-c4-feature\u002FSKILL.md",true,[],[50,57,64,71,76,83],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7EGY90MMNNJSQHVGX5C1N3A","ship","Run this repo's checks, then commit and push to the branch the user names","https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify\u002Fblob\u002Fmain\u002F.specify\u002Fpresets\u002Fc4-model\u002F.claude\u002Fskills\u002Fship\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7EGY6XRV5V9BVNWFJMMV6D8","speckit-c4-validate","Check architecture diagrams for Mermaid syntax, C4 rule and consistency problems without changing files","https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fc4\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-c4-validate\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7EGY4WF61ZWYG76XD8TZQ2K","speckit-c4-system","Create or update the project-level C4 context view, container view and ER diagram","https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fc4\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-c4-system\u002FSKILL.md",[],[],{"skillNo":72,"name":52,"nameZh":6,"description":53,"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},"01M7EGY1FB7EA06CP7FD3FF71X","https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fc4\u002F.claude\u002Fskills\u002Fship\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},"01M7EGXZ00WQ3SGE5FVJJWZ0HJ","speckit-taskstoissues","Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.","https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspeckit-taskstoissues\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},"01M7EGXVWSXW6ZK2TBSYRZ0QW9","speckit-tasks","Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts, with every task labelled against the Verification Plan and test tasks ordered first.","https:\u002F\u002Fgithub.com\u002Fleejsinclair\u002Fspeckit-grill-specify\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspeckit-tasks\u002FSKILL.md",[],[]]