[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70FKTSZJQ282MBA089WZGG5":3,"skill-same:01M70FKTSZJQ282MBA089WZGG5":66},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M70FKTSZJQ282MBA089WZGG5","agentic-engineering",null,"Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.","mdnaimul22\u002Fhuman-skills","mdnaimul22","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64520358?v=4","01M70FH95MH2H796Q01TYSFZ03","Naimul","01M70FH96798CQR4YHA13F17GA",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fagentic-engineering\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"agentic engineering","engineering","agentic","first","routing","cost","use","execution","planning","as","decomposition","work","when","eval","engineer","end","model","operate","2026-11-10 10:12:30",false,"---\nname: agentic-engineering\ndescription: Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.\nmetadata:\n  origin: ECC\n---\n\n# Agentic Engineering\n\nUse this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.\n\n## Operating Principles\n\n1. Define completion criteria before execution.\n2. Decompose work into agent-sized units.\n3. Route model tiers by task complexity.\n4. Measure with evals and regression checks.\n\n## Eval-First Loop\n\n1. Define capability eval and regression eval.\n2. Run baseline and capture failure signatures.\n3. Execute implementation.\n4. Re-run evals and compare deltas.\n\n## Task Decomposition\n\nApply the 15-minute unit rule:\n- each unit should be independently verifiable\n- each unit should have a single dominant risk\n- each unit should expose a clear done condition\n\n## Model Routing\n\n- Haiku: classification, boilerplate transforms, narrow edits\n- Sonnet: implementation and refactors\n- Opus: architecture, root-cause analysis, multi-file invariants\n\n## Session Strategy\n\n- Continue session for closely-coupled units.\n- Start fresh session after major phase transitions.\n- Compact after milestone completion, not during active debugging.\n\n## Review Focus for AI-Generated Code\n\nPrioritize:\n- invariants and edge cases\n- error boundaries\n- security and auth assumptions\n- hidden coupling and rollout risk\n\nDo not waste review cycles on style-only disagreements when automated format\u002Flint already enforce style.\n\n## Interpret Tool Results Before Comparing Data\n\nFor document reads and processing loops, check three boundaries in order:\n\n1. Check the tool\u002Ftransport envelope for an error or an indeterminate outcome.\n2. Decode the response and check operation status using that tool's documented\n   contract. An outer success flag or a present payload does not establish that\n   the requested operation succeeded. Status may live in structured content,\n   decoded text, or another documented field; `result.ok` is not a universal MCP\n   field. Missing or unrecognized status stays unknown.\n3. Only after confirmed operation success, validate the document shape and compare\n   its fields. An operation failure is not a document identity mismatch.\n\nKeep the operation name, request\u002Fcorrelation ID when available, relevant status\nand error details, and the original response needed for diagnosis. Redact secrets\nand private document data before logging or sharing. Do not reconstruct missing\nresponses from a later response's shape.\n\n### Portable Classification Example\n\nThe adapter below uses an **illustrative read-tool contract**, not an MCP schema:\n`isError` is a required boolean; when false, `result.ok` is a required operation\nstatus. A successful read returns `result.document` with a string `id`; a failed\nread may carry `result.error`. Replace this adapter with the actual tool's\ncontract, including its documented decoding and document validation rules.\n\n```javascript\nfunction decodeRead(response) {\n  if (!response || typeof response.isError !== 'boolean') {\n    return { kind: 'unknown_response' };\n  }\n  if (response.isError) return { kind: 'tool_error' };\n\n  const result = response.result;\n  if (result?.ok === false) {\n    return { kind: 'operation_error', error: result.error };\n  }\n  if (result?.ok !== true) return { kind: 'unknown_response' };\n\n  const document = result.document;\n  if (!document || typeof document.id !== 'string') {\n    return { kind: 'invalid_document' };\n  }\n  return { kind: 'document', document };\n}\n\nfunction inspectRead(response, expectedId, decode = decodeRead) {\n  const outcome = decode(response);\n  if (outcome.kind !== 'document') return outcome;\n\n  return outcome.document.id === expectedId\n    ? { kind: 'match', document: outcome.document }\n    : { kind: 'field_mismatch', actualId: outcome.document.id, expectedId };\n}\n```\n\nSynthetic evaluation cases (not a reproduction of any historical incident):\n\n| Input under this illustrative contract | Expected classification |\n| --- | --- |\n| `isError: true` | `tool_error`; no field comparison |\n| `isError: false`, `result.ok: false`, maintenance error, no document | `operation_error`; preserve maintenance details, no mismatch |\n| `isError: false`, missing operation status | `unknown_response`; no field comparison |\n| Confirmed success, missing document or non-string ID | `invalid_document`; no field comparison |\n| Confirmed success, valid document with expected ID | `match` |\n| Confirmed success, valid document with a different ID | `field_mismatch` |\n\nClassification does not authorize a write or retry. Temporary maintenance remains\nan operation failure with its own evidence; follow the tool's documented recovery\npolicy. A documented service-wide maintenance failure should stop a batch rather\nthan trigger the same request for every row; a lone authorization error does not\nestablish service-wide maintenance. If a write times out or its outcome is unknown,\npreserve that uncertainty\nand reconcile using a documented status\u002Fread-back mechanism before considering a\nretry. Never infer that a write failed, repeat it, or overwrite a document solely\nbecause a read failed or a returned field differs.\n\n## Cost Discipline\n\nTrack per task:\n- model\n- token estimate\n- retries\n- wall-clock time\n- success\u002Ffailure\n\nEscalate model tier only when lower tier fails with a clear reasoning gap.\n","# Agentic Engineering\n\nUse this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.\n\n## Operating Principles\n\n1. Define completion criteria before execution.\n2. Decompose work into agent-sized units.\n3. Route model tiers by task complexity.\n4. Measure with evals and regression checks.\n\n## Eval-First Loop\n\n1. Define capability eval and regression eval.\n2. Run baseline and capture failure signatures.\n3. Execute implementation.\n4. Re-run evals and compare deltas.\n\n## Task Decomposition\n\nApply the 15-minute unit rule:\n- each unit should be independently verifiable\n- each unit should have a single dominant risk\n- each unit should expose a clear done condition\n\n## Model Routing\n\n- Haiku: classification, boilerplate transforms, narrow edits\n- Sonnet: implementation and refactors\n- Opus: architecture, root-cause analysis, multi-file invariants\n\n## Session Strategy\n\n- Continue session for closely-coupled units.\n- Start fresh session after major phase transitions.\n- Compact after milestone completion, not during active debugging.\n\n## Review Focus for AI-Generated Code\n\nPrioritize:\n- invariants and edge cases\n- error boundaries\n- security and auth assumptions\n- hidden coupling and rollout risk\n\nDo not waste review cycles on style-only disagreements when automated format\u002Flint already enforce style.\n\n## Interpret Tool Results Before Comparing Data\n\nFor document reads and processing loops, check three boundaries in order:\n\n1. Check the tool\u002Ftransport envelope for an error or an indeterminate outcome.\n2. Decode the response and check operation status using that tool's documented\n   contract. An outer success flag or a present payload does not establish that\n   the requested operation succeeded. Status may live in structured content,\n   decoded text, or another documented field; `result.ok` is not a universal MCP\n   field. Missing or unrecognized status stays unknown.\n3. Only after confirmed operation success, validate the document shape and compare\n   its fields. An operation failure is not a document identity mismatch.\n\nKeep the operation name, request\u002Fcorrelation ID when available, relevant status\nand error details, and the original response needed for diagnosis. Redact secrets\nand private document data before logging or sharing. Do not reconstruct missing\nresponses from a later response's shape.\n\n### Portable Classification Example\n\nThe adapter below uses an **illustrative read-tool contract**, not an MCP schema:\n`isError` is a required boolean; when false, `result.ok` is a required operation\nstatus. A successful read returns `result.document` with a string `id`; a failed\nread may carry `result.error`. Replace this adapter with the actual tool's\ncontract, including its documented decoding and document validation rules.\n\n```javascript\nfunction decodeRead(response) {\n  if (!response || typeof response.isError !== 'boolean') {\n    return { kind: 'unknown_response' };\n  }\n  if (response.isError) return { kind: 'tool_error' };\n\n  const result = response.result;\n  if (result?.ok === false) {\n    return { kind: 'operation_error', error: result.error };\n  }\n  if (result?.ok !== true) return { kind: 'unknown_response' };\n\n  const document = result.document;\n  if (!document || typeof document.id !== 'string') {\n    return { kind: 'invalid_document' };\n  }\n  return { kind: 'document', document };\n}\n\nfunction inspectRead(response, expectedId, decode = decodeRead) {\n  const outcome = decode(response);\n  if (outcome.kind !== 'document') return outcome;\n\n  return outcome.document.id === expectedId\n    ? { kind: 'match', document: outcome.document }\n    : { kind: 'field_mismatch', actualId: outcome.document.id, expectedId };\n}\n```\n\nSynthetic evaluation cases (not a reproduction of any historical incident):\n\n| Input under this illustrative contract | Expected classification |\n| --- | --- |\n| `isError: true` | `tool_error`; no field comparison |\n| `isError: false`, `result.ok: false`, maintenance error, no document | `operation_error`; preserve maintenance details, no mismatch |\n| `isError: false`, missing operation status | `unknown_response`; no field comparison |\n| Confirmed success, missing document or non-string ID | `invalid_document`; no field comparison |\n| Confirmed success, valid document with expected ID | `match` |\n| Confirmed success, valid document with a different ID | `field_mismatch` |\n\nClassification does not authorize a write or retry. Temporary maintenance remains\nan operation failure with its own evidence; follow the tool's documented recovery\npolicy. A documented service-wide maintenance failure should stop a batch rather\nthan trigger the same request for every row; a lone authorization error does not\nestablish service-wide maintenance. If a write times out or its outcome is unknown,\npreserve that uncertainty\nand reconcile using a documented status\u002Fread-back mechanism before considering a\nretry. Never infer that a write failed, repeat it, or overwrite a document solely\nbecause a read failed or a returned field differs.\n\n## Cost Discipline\n\nTrack per task:\n- model\n- token estimate\n- retries\n- wall-clock time\n- success\u002Ffailure\n\nEscalate model tier only when lower tier fails with a clear reasoning gap.\n",{"name":5,"metadata":42,"description":7},{"origin":43},"ECC","main","7092b664627bf326748a6fcbf27fee6a34c4da1d","skills\u002Fstorage\u002Faffaan-m_ECC\u002Fagentic-engineering",0,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills","https:\u002F\u002Fgithub.com\u002Fmdnaimul22","AI Agents Workflows Automation | Specializing in Python, FastAPI, MCP Agents & Custom ERP.","2026-11-11 21:16:57",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add mdnaimul22\u002Fhuman-skills --skill agentic-engineering",{"tool":58,"command":59},"bunx","bunx skills add mdnaimul22\u002Fhuman-skills --skill agentic-engineering",{"tool":61,"command":62},"pnpm","pnpm dlx skills add mdnaimul22\u002Fhuman-skills --skill agentic-engineering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fagentic-engineering\u002FSKILL.md",true,[],[67,75,83,90,97,104],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":74},"01M767791C1KRP2ZRW2Z73VZ5Q","system-lifecycle-designer","Universal architectural methodology for designing granular, atomic, and sub-atomic lifecycles and end-to-end workflows for single functionality integrations across any domain (daemons, batch jobs, request transactions, resource pools). Provides patterns for deterministic identity, pre-commit validation, differential reconciliation, sticky leasing, state machines, transactional persistence, and closed-loop feedback.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fmy_skills\u002Fsystem-lifecycle-designer\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":82},"01M748ABPN5F1FANHH6HKZQMXT","style-sampling","Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for \"an episode of\", \"in the style of\", \"sample this style\", 「用这个风格做一集」. One video to copy is reverse-any-video.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Fstyle-sampling\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"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":82},"01M748A59V04PKW4HA0XQ81FGP","reverse-any-video","Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage - checked against the original frame by frame. Use to reverse, recreate, remake, replicate or copy a video, or 「复刻这个视频」「照着这个视频做一个」.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Freverse-any-video\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":82},"01M7487T50P55CSXMWXZ0G9KRG","typescript-patterns","TypeScript patterns for strict, type-safe, maintainable code in modern TypeScript and JavaScript applications. Covers strict compiler configuration, type design, narrowing, discriminated unions, generics, async and error handling, module boundaries, dependency hygiene, and type-level testing. Use when writing or reviewing TypeScript or JavaScript code.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftypescript-patterns\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":82},"01M7487ERZRGPC5NJ75077Y238","test-collaboration","Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit\u002Fintegration\u002Fcontract\u002FE2E\u002Fsmoke classification, bug-to-test regression protection, consumer\u002Fprovider contract testing, test-necessity review, and pre-delivery evidence review.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftest-collaboration\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":82},"01M748721J3GKR2WS6K0QWFC35","story-lifecycle","Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira\u002FLinear\u002FTaiga but needs structured delivery tracking.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fstory-lifecycle\u002FSKILL.md",[],[]]