[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74ED6HYMPB279NE0DWMJZP0":3,"skill-same:01M74ED6HYMPB279NE0DWMJZP0":56},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M74ED6HYMPB279NE0DWMJZP0","sdd-yolo",null,"SDD fast path. Runs the full pipeline (spec, plan, analyze, implement and converge until done, review, archive) with a single confirmation gate before implementation begins. Stops automatically if analyze says FIX-FIRST, converge cannot close, or review finds Critical or Major issues. Use when you want to ship a well-understood feature with minimal interruptions.","CarlosCaPe\u002Foctorato","CarlosCaPe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F39838249?v=4","01M72WXX4ZRR8MBH1EP1QND2FQ","dataqbs","01M72WXX5NA7YCKRSJ54GW1GQ8",18,"MIT","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fsdd-yolo\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: sdd-yolo\ndescription: >\n  SDD fast path. Runs the full pipeline (spec, plan, analyze, implement and converge until\n  done, review, archive) with a single confirmation gate before implementation begins.\n  Stops automatically if analyze says FIX-FIRST, converge cannot close, or review finds\n  Critical or Major issues.\n  Use when you want to ship a well-understood feature with minimal interruptions.\nargument-hint: \u003Cfeature description>\n---\n\n# SDD: YOLO Full Pipeline\n\nYou are running the full SDD workflow end-to-end with minimal interruptions.\nThe pipeline is: **spec → plan → analyze → implement ⇄ converge → review → archive**.\n\nThere is exactly **one confirmation gate**: after the spec and plan are produced,\nbefore implementation begins. Everything else runs automatically.\n\n## Required Inputs\n\nBefore starting, collect these inputs. If any are missing, ask for them now: do not proceed without them.\n\n| Input                 | Description                     | Example                                             |\n|-----------------------|---------------------------------|-----------------------------------------------------|\n| `feature_description` | The feature to build end-to-end | \"Add JWT authentication with refresh token support\" |\n\n## Steps\n\n### Step 0: Validate Inputs (ALWAYS DO THIS FIRST)\n\nCheck the conversation for `feature_description` and for `docs\u002Fproject.md`.\n\n- If `docs\u002Fproject.md` does not exist → stop and tell the user to run `\u002Fsdd-init` first.\n- If `feature_description` is present → proceed to Phase 1.\n- If `feature_description` is missing → ask: \"What feature would you like to build?\" Do NOT proceed until the user provides it.\n\n---\n\n## Phase 1: Spec\n\nFollow the full `sdd-feature` process:\n\n1. Read `docs\u002Fproject.md`.\n2. Analyse the request: **`feature_description`** (collected in Step 0).\n3. Create the spec directory `docs\u002Fspecs\u002F\u003CyyyymmddHHMM>-\u003Cfeature-name>\u002F` and write `feature.md`\n   in it, in the ears-1 format of `sdd-feature`: `Spec-Format: ears-1` header,\n   Glossary, EARS acceptance criteria. Anything you cannot decide becomes an inline\n   `[NEEDS CLARIFICATION: ...]` marker (at most 3).\n4. If markers remain, resolve them with the user one question at a time, each with a\n   recommended answer, as `sdd-refine` does. The pipeline does not continue with open markers.\n5. Run `python3 ~\u002F.claude\u002Fscripts\u002Fspec_lint.py --ready \u003Cspec-directory>` and fix every finding.\n6. Print a compact summary of the spec (3 to 5 bullet points, not the full file).\n\n---\n\n## Phase 2: Plan\n\nFollow the full `sdd-plan` process immediately after Phase 1:\n\n1. Read `feature.md` and `docs\u002Fproject.md`.\n2. Write `plan.md` in the task grammar `- [ ] T## [AC-##] \u003Cpath>: \u003Caction>`, at most 20 tasks.\n3. Run the linter again: every criterion must be covered by a task.\n4. Run `\u002Fsdd-analyze` as an independent verifier subagent. On `FIX-FIRST`, fix the spec or\n   the plan and re-run it; do not reach the gate with a `FIX-FIRST` verdict.\n5. Print a compact summary of the plan (task names only, not full detail) and the analyze verdict.\n\n---\n\n## Confirmation Gate\n\nPresent the following prompt and **wait for the user's response** before continuing:\n\n```\n## Ready to implement\n\nSpec: feature.md ✓\nPlan: plan.md ✓\n\n[Compact spec summary: 3–5 bullets]\n[Plan steps: numbered list of step names]\n\nType PROCEED to start implementation, or describe any changes you want first.\n```\n\n- If the user types **PROCEED** (or equivalent confirmation): continue to Phase 3.\n- If the user requests changes: apply them to `feature.md` and\u002For `plan.md`, show what changed, then re-present the gate.\n- If the user aborts: stop and leave `feature.md` and `plan.md` in place for manual continuation.\n\n---\n\n## Phase 3: Implement\n\nFollow the full `sdd-implement` process:\n\n1. Read `plan.md`, `feature.md`, and `docs\u002Fproject.md`.\n2. Execute each step in `plan.md` in order.\n3. Compile and run tests after each layer. Fix failures before moving on: never carry failures forward.\n4. Do not introduce new dependencies without flagging them to the user.\n5. After all tasks, run the full test suite once and print the completion summary (files\n   created and modified, test result). Do not grade the criteria yourself.\n\n### Converge loop\n\n6. Run `\u002Fsdd-converge` as an independent verifier subagent.\n7. On `GAPS`, implement the tasks it appended under `## Convergence \u003Cn>`, then run it again.\n8. Stop the pipeline if the same criterion stays unmet after 3 converge passes. Continue only\n   on `CONVERGED`. When you stop, print:\n\n```\n## YOLO Pipeline Stopped: converge did not close\n\nFeature: \u003CFeature Name>\nUnmet after 3 passes: \u003CAC ids, with the converge evidence for each>\n\nfeature.md and plan.md stay in place. Decide whether the criterion or the code is wrong:\n\u002Fsdd-refine for the criterion, \u002Fsdd-implement for the code, then \u002Fsdd-converge.\n```\n\n---\n\n## Phase 4: Review\n\nFollow the full `sdd-review` process immediately after Phase 3:\n\n1. Run `git diff main...HEAD --name-only` to determine changed files.\n2. Review across the 7 quality dimensions (language and framework practices, security,\n   duplication, design, performance, test quality, observability), quoting the converge verdict.\n3. Produce the full structured review report.\n\n---\n\n## Phase 5: Archive or Stop\n\nEvaluate the review verdict:\n\n### If verdict is ✅ Ready to merge OR 🟡 Merge after minor fixes\n\nProceed automatically to archive:\n\n1. Follow the full `sdd-archive` process.\n2. Update `docs\u002Fproject.md` (features list, architecture decisions, API surface, env config).\n3. Show the proposed `project.md` changes and ask for confirmation before writing.\n4. The spec directory `docs\u002Fspecs\u002F\u003CyyyymmddHHMM>-\u003Cfeature-name>\u002F` stays where it is.\n5. Create `README.md` in it.\n\nThen print the final pipeline summary:\n\n```\n## YOLO Pipeline Complete ✓\n\nFeature: \u003CFeature Name>\nSpec directory: docs\u002Fspecs\u002F\u003CyyyymmddHHMM>-\u003Cfeature-name>\u002F\n\nPhase results:\n  Spec        ✓\n  Plan        ✓  (analyze: READY)\n  Implement   ✓  (N files created, M files modified)\n  Converge    ✓  (CONVERGED after \u003Ck> pass(es))\n  Review      ✓  (\u003Cverdict>)\n  Archive     ✓\n\nNext: commit the spec directory and docs\u002Fproject.md to version control.\n```\n\n### If verdict is 🟠 Requires fixes and re-review OR 🔴 Do not merge\n\n**Stop. Do not archive.**\n\nPrint:\n\n```\n## YOLO Pipeline Stopped: Review issues require attention\n\nFeature: \u003CFeature Name>\n\nPhase results:\n  Spec        ✓\n  Plan        ✓\n  Implement   ✓\n  Converge    ✓\n  Review      ✗  (\u003Cverdict>)\n  Archive     skipped\n\nCritical\u002FMajor findings must be resolved before archiving.\nFix the issues above, then run \u002Fsdd-review to re-review, and \u002Fsdd-archive when clean.\n```\n\nLeave the spec directory as it is so the user can continue manually.\n","# SDD: YOLO Full Pipeline\n\nYou are running the full SDD workflow end-to-end with minimal interruptions.\nThe pipeline is: **spec → plan → analyze → implement ⇄ converge → review → archive**.\n\nThere is exactly **one confirmation gate**: after the spec and plan are produced,\nbefore implementation begins. Everything else runs automatically.\n\n## Required Inputs\n\nBefore starting, collect these inputs. If any are missing, ask for them now: do not proceed without them.\n\n| Input                 | Description                     | Example                                             |\n|-----------------------|---------------------------------|-----------------------------------------------------|\n| `feature_description` | The feature to build end-to-end | \"Add JWT authentication with refresh token support\" |\n\n## Steps\n\n### Step 0: Validate Inputs (ALWAYS DO THIS FIRST)\n\nCheck the conversation for `feature_description` and for `docs\u002Fproject.md`.\n\n- If `docs\u002Fproject.md` does not exist → stop and tell the user to run `\u002Fsdd-init` first.\n- If `feature_description` is present → proceed to Phase 1.\n- If `feature_description` is missing → ask: \"What feature would you like to build?\" Do NOT proceed until the user provides it.\n\n---\n\n## Phase 1: Spec\n\nFollow the full `sdd-feature` process:\n\n1. Read `docs\u002Fproject.md`.\n2. Analyse the request: **`feature_description`** (collected in Step 0).\n3. Create the spec directory `docs\u002Fspecs\u002F\u003CyyyymmddHHMM>-\u003Cfeature-name>\u002F` and write `feature.md`\n   in it, in the ears-1 format of `sdd-feature`: `Spec-Format: ears-1` header,\n   Glossary, EARS acceptance criteria. Anything you cannot decide becomes an inline\n   `[NEEDS CLARIFICATION: ...]` marker (at most 3).\n4. If markers remain, resolve them with the user one question at a time, each with a\n   recommended answer, as `sdd-refine` does. The pipeline does not continue with open markers.\n5. Run `python3 ~\u002F.claude\u002Fscripts\u002Fspec_lint.py --ready \u003Cspec-directory>` and fix every finding.\n6. Print a compact summary of the spec (3 to 5 bullet points, not the full file).\n\n---\n\n## Phase 2: Plan\n\nFollow the full `sdd-plan` process immediately after Phase 1:\n\n1. Read `feature.md` and `docs\u002Fproject.md`.\n2. Write `plan.md` in the task grammar `- [ ] T## [AC-##] \u003Cpath>: \u003Caction>`, at most 20 tasks.\n3. Run the linter again: every criterion must be covered by a task.\n4. Run `\u002Fsdd-analyze` as an independent verifier subagent. On `FIX-FIRST`, fix the spec or\n   the plan and re-run it; do not reach the gate with a `FIX-FIRST` verdict.\n5. Print a compact summary of the plan (task names only, not full detail) and the analyze verdict.\n\n---\n\n## Confirmation Gate\n\nPresent the following prompt and **wait for the user's response** before continuing:\n\n```\n## Ready to implement\n\nSpec: feature.md ✓\nPlan: plan.md ✓\n\n[Compact spec summary: 3–5 bullets]\n[Plan steps: numbered list of step names]\n\nType PROCEED to start implementation, or describe any changes you want first.\n```\n\n- If the user types **PROCEED** (or equivalent confirmation): continue to Phase 3.\n- If the user requests changes: apply them to `feature.md` and\u002For `plan.md`, show what changed, then re-present the gate.\n- If the user aborts: stop and leave `feature.md` and `plan.md` in place for manual continuation.\n\n---\n\n## Phase 3: Implement\n\nFollow the full `sdd-implement` process:\n\n1. Read `plan.md`, `feature.md`, and `docs\u002Fproject.md`.\n2. Execute each step in `plan.md` in order.\n3. Compile and run tests after each layer. Fix failures before moving on: never carry failures forward.\n4. Do not introduce new dependencies without flagging them to the user.\n5. After all tasks, run the full test suite once and print the completion summary (files\n   created and modified, test result). Do not grade the criteria yourself.\n\n### Converge loop\n\n6. Run `\u002Fsdd-converge` as an independent verifier subagent.\n7. On `GAPS`, implement the tasks it appended under `## Convergence \u003Cn>`, then run it again.\n8. Stop the pipeline if the same criterion stays unmet after 3 converge passes. Continue only\n   on `CONVERGED`. When you stop, print:\n\n```\n## YOLO Pipeline Stopped: converge did not close\n\nFeature: \u003CFeature Name>\nUnmet after 3 passes: \u003CAC ids, with the converge evidence for each>\n\nfeature.md and plan.md stay in place. Decide whether the criterion or the code is wrong:\n\u002Fsdd-refine for the criterion, \u002Fsdd-implement for the code, then \u002Fsdd-converge.\n```\n\n---\n\n## Phase 4: Review\n\nFollow the full `sdd-review` process immediately after Phase 3:\n\n1. Run `git diff main...HEAD --name-only` to determine changed files.\n2. Review across the 7 quality dimensions (language and framework practices, security,\n   duplication, design, performance, test quality, observability), quoting the converge verdict.\n3. Produce the full structured review report.\n\n---\n\n## Phase 5: Archive or Stop\n\nEvaluate the review verdict:\n\n### If verdict is ✅ Ready to merge OR 🟡 Merge after minor fixes\n\nProceed automatically to archive:\n\n1. Follow the full `sdd-archive` process.\n2. Update `docs\u002Fproject.md` (features list, architecture decisions, API surface, env config).\n3. Show the proposed `project.md` changes and ask for confirmation before writing.\n4. The spec directory `docs\u002Fspecs\u002F\u003CyyyymmddHHMM>-\u003Cfeature-name>\u002F` stays where it is.\n5. Create `README.md` in it.\n\nThen print the final pipeline summary:\n\n```\n## YOLO Pipeline Complete ✓\n\nFeature: \u003CFeature Name>\nSpec directory: docs\u002Fspecs\u002F\u003CyyyymmddHHMM>-\u003Cfeature-name>\u002F\n\nPhase results:\n  Spec        ✓\n  Plan        ✓  (analyze: READY)\n  Implement   ✓  (N files created, M files modified)\n  Converge    ✓  (CONVERGED after \u003Ck> pass(es))\n  Review      ✓  (\u003Cverdict>)\n  Archive     ✓\n\nNext: commit the spec directory and docs\u002Fproject.md to version control.\n```\n\n### If verdict is 🟠 Requires fixes and re-review OR 🔴 Do not merge\n\n**Stop. Do not archive.**\n\nPrint:\n\n```\n## YOLO Pipeline Stopped: Review issues require attention\n\nFeature: \u003CFeature Name>\n\nPhase results:\n  Spec        ✓\n  Plan        ✓\n  Implement   ✓\n  Converge    ✓\n  Review      ✗  (\u003Cverdict>)\n  Archive     skipped\n\nCritical\u002FMajor findings must be resolved before archiving.\nFix the issues above, then run \u002Fsdd-review to re-review, and \u002Fsdd-archive when clean.\n```\n\nLeave the spec directory as it is so the user can continue manually.\n",{"name":5,"description":24,"argument-hint":25},"SDD fast path. Runs the full pipeline (spec, plan, analyze, implement and converge until done, review, archive) with a single confirmation gate before implementation begins. Stops automatically if analyze says FIX-FIRST, converge cannot close, or review finds Critical or Major issues. Use when you want to ship a well-understood feature with minimal interruptions.\n","\u003Cfeature description>","master","b4414608cd5a3f87d1525b518f1c6add8363540d","skills\u002Fsdd-yolo",6,"https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato","https:\u002F\u002Fwww.dataqbs.com\u002Foctorato","https:\u002F\u002Fgithub.com\u002FCarlosCaPe","www.dataqbs.com"," AI-powered data engineering\r\n& consulting\r\n\r\nWe build data platforms that turn complexity into clarity — from cloud architecture and ETL pipelines to AI-driven","2026-11-14 00:21:00",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add CarlosCaPe\u002Foctorato --skill sdd-yolo",{"tool":42,"command":43},"bunx","bunx skills add CarlosCaPe\u002Foctorato --skill sdd-yolo",{"tool":45,"command":46},"pnpm","pnpm dlx skills add CarlosCaPe\u002Foctorato --skill sdd-yolo","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fsdd-yolo\u002FSKILL.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"skill.json","REFERENCE","参考文档",472,"https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fsdd-yolo\u002Fskill.json",[57,66,74,81,89,97],{"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":61,"licenseFileUrl":62,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M74EVAA4A4B4AKR5TT732GP4","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M74EV4WMRDKP2NQS4YWR8PXH","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwrangler\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwrangler\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M74EV05MHTXKEXD4B2QJEYTF","workspace-skill-discovery","Discover and include ALL skills across the workspace — not just global ones. Use at the start of every session or when the user asks about available skills. Ensures project-level skills (under .claude\u002Fskills\u002F or skills\u002F in any repo) are never missed.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkspace-skill-discovery\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M74ETV78525B4VP2F28Z6NRD","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkers-best-practices\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkers-best-practices\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M74ETR75NF67WGVEN7288ACV","winui-app","Create, build and design WinUI 3 desktop apps with C# and the Windows App SDK following Microsoft's official guidance and CommunityToolkit. Covers XAML, navigation, theming, accessibility and deployment.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwinui-app\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwinui-app\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M74ETJFRNPPNSQZ36C6HD6CW","windows-brain-script-portability","Scripts in ~\u002F.claude\u002Fscripts\u002F that run on a Windows brain: use the python3.cmd shim and not bare python3, and reconfigure stdout to UTF-8 if you print symbols. Use it when writing a brain script or triaging a Windows-only crash.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwindows-brain-script-portability\u002FSKILL.md",[],[]]