[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79ZFD74B4DGZCHM5RCHPBXB":3,"skill-same:01M79ZFD74B4DGZCHM5RCHPBXB":116},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M79ZFD74B4DGZCHM5RCHPBXB","claude-memory-kit",null,"Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; agent captures, audits, proposes promotions, and writes. Four layers — daily logs, hot cache (MEMORY.md), role-based reference skills (Anthropic-native, user-invocable: false), canonical rules. \u002Fclose-day runs the audit ritual at end of day. Multi-project isolation via projects\u002F\u003Cname>\u002F. Zero external dependencies.","leemiracle\u002Fwork4ai","leemiracle","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10385913?v=4","01M79YCHARF56CHMGGTECMZN8Z","lee","01M79YCHBY9VH2CJW4P65D3DHR",4,"MIT","https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: claude-memory-kit\ndescription: \"Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; agent captures, audits, proposes promotions, and writes. Four layers — daily logs, hot cache (MEMORY.md), role-based reference skills (Anthropic-native, user-invocable: false), canonical rules. \u002Fclose-day runs the audit ritual at end of day. Multi-project isolation via projects\u002F\u003Cname>\u002F. Zero external dependencies.\"\ntags: [memory, context-management, productivity, claude-code, agent-memory, knowledge-base, reference-skills, multi-project]\nversion: 4.0.0\nauthor: awrshift\nlicense: MIT\nrepository: https:\u002F\u002Fgithub.com\u002Fawrshift\u002Fclaude-memory-kit\n---\n\n# Claude Memory Kit v4\n\nPersistent memory for Claude Code agents. Four-layer architecture, agent-driven promotion, zero manual file editing.\n\n## Core invariant\n\n**User only talks. Agent captures, proposes, writes.** Every architectural decision passes this test.\n\n## What's different from v3.2\n\n- **Agent-driven promotion ritual** via `\u002Fclose-day` (was: background `promote-patterns.py` detection, killed as unreliable)\n- **Role-based reference skills** (`.claude\u002Fskills\u002F\u003Crole>-guidance\u002FSKILL.md` with `user-invocable: false`) alongside topic-based `knowledge\u002Fconcepts\u002F` — two axes, no overlap. Uses Anthropic-native auto-invoke via `description` matching — no custom trigger tables.\n- **Multi-project isolation** via `projects\u002F\u003Cname>\u002F` — shared layers load always, per-project scope on demand\n- **`\u002Fmemory-audit`** operator for oversized-reference-skill detection + semantic split execution\n- **Killed:** `experiences\u002F` staging layer, `promote-patterns.py` background script, `flush.py` auto-flush, separate `playbooks\u002F` directory (merged into reference skills)\n\nSee [CHANGELOG.md](CHANGELOG.md) for full migration notes.\n\n## Quick start\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fawrshift\u002Fclaude-memory-kit.git my-project\ncd my-project\nclaude\n```\n\nFirst session: agent greets you, asks 2-3 setup questions, loads you in. Type `\u002Ftour` for a guided walkthrough.\n\n## Daily workflow\n\n1. Open a session — hooks auto-load NSP + MEMORY + knowledge index\n2. Work normally — agent captures patterns in MEMORY.md as you speak\n3. `\u002Fclose-day` when done — agent synthesizes today, audits for promotions, proposes verbally, writes on your verbal \"yes\"\n\nTomorrow starts where today left off.\n\n## Included skills\n\n| Skill | Description |\n|---|---|\n| `\u002Fclose-day` | End-of-day audit ritual: synthesis + promotion proposals |\n| `\u002Fmemory-audit` | Oversized-reference-skill structural check + split proposals |\n| `\u002Fmemory-lint` | Hygiene (broken links, sparse articles, orphans, oversized reference skills) |\n| `\u002Fmemory-compile` | Compile daily logs into `knowledge\u002Fconcepts\u002F` articles |\n| `\u002Fmemory-query` | Natural-language search across all memory layers |\n| `\u002Ftour` | Interactive guided walkthrough |\n\n## Architecture\n\nFour layers, each with its own purpose:\n\n| Layer | Answers | Written by |\n|---|---|---|\n| `daily\u002FYYYY-MM-DD.md` | «what happened today» | `\u002Fclose-day` |\n| `.claude\u002Fmemory\u002FMEMORY.md` | «what patterns repeat across sessions» | agent as you speak |\n| `.claude\u002Fskills\u002F\u003Crole>-guidance\u002FSKILL.md` | «how should a \u003Crole> think about X» | `\u002Fclose-day` promotion |\n| `.claude\u002Frules\u002F*.md` | «what must always \u002F never happen» | `\u002Fclose-day` after 6+ months stable |\n\nSee [ARCHITECTURE.md](ARCHITECTURE.md) for full details and [CLAUDE.md](CLAUDE.md) for the agent's session workflow.\n\n## Built from production use\n\nIteration on 700+ real sessions across 7+ projects. Every component earns its place; `experiences\u002F` and background-detection scripts didn't survive review.\n","# Claude Memory Kit v4\n\nPersistent memory for Claude Code agents. Four-layer architecture, agent-driven promotion, zero manual file editing.\n\n## Core invariant\n\n**User only talks. Agent captures, proposes, writes.** Every architectural decision passes this test.\n\n## What's different from v3.2\n\n- **Agent-driven promotion ritual** via `\u002Fclose-day` (was: background `promote-patterns.py` detection, killed as unreliable)\n- **Role-based reference skills** (`.claude\u002Fskills\u002F\u003Crole>-guidance\u002FSKILL.md` with `user-invocable: false`) alongside topic-based `knowledge\u002Fconcepts\u002F` — two axes, no overlap. Uses Anthropic-native auto-invoke via `description` matching — no custom trigger tables.\n- **Multi-project isolation** via `projects\u002F\u003Cname>\u002F` — shared layers load always, per-project scope on demand\n- **`\u002Fmemory-audit`** operator for oversized-reference-skill detection + semantic split execution\n- **Killed:** `experiences\u002F` staging layer, `promote-patterns.py` background script, `flush.py` auto-flush, separate `playbooks\u002F` directory (merged into reference skills)\n\nSee [CHANGELOG.md](CHANGELOG.md) for full migration notes.\n\n## Quick start\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fawrshift\u002Fclaude-memory-kit.git my-project\ncd my-project\nclaude\n```\n\nFirst session: agent greets you, asks 2-3 setup questions, loads you in. Type `\u002Ftour` for a guided walkthrough.\n\n## Daily workflow\n\n1. Open a session — hooks auto-load NSP + MEMORY + knowledge index\n2. Work normally — agent captures patterns in MEMORY.md as you speak\n3. `\u002Fclose-day` when done — agent synthesizes today, audits for promotions, proposes verbally, writes on your verbal \"yes\"\n\nTomorrow starts where today left off.\n\n## Included skills\n\n| Skill | Description |\n|---|---|\n| `\u002Fclose-day` | End-of-day audit ritual: synthesis + promotion proposals |\n| `\u002Fmemory-audit` | Oversized-reference-skill structural check + split proposals |\n| `\u002Fmemory-lint` | Hygiene (broken links, sparse articles, orphans, oversized reference skills) |\n| `\u002Fmemory-compile` | Compile daily logs into `knowledge\u002Fconcepts\u002F` articles |\n| `\u002Fmemory-query` | Natural-language search across all memory layers |\n| `\u002Ftour` | Interactive guided walkthrough |\n\n## Architecture\n\nFour layers, each with its own purpose:\n\n| Layer | Answers | Written by |\n|---|---|---|\n| `daily\u002FYYYY-MM-DD.md` | «what happened today» | `\u002Fclose-day` |\n| `.claude\u002Fmemory\u002FMEMORY.md` | «what patterns repeat across sessions» | agent as you speak |\n| `.claude\u002Fskills\u002F\u003Crole>-guidance\u002FSKILL.md` | «how should a \u003Crole> think about X» | `\u002Fclose-day` promotion |\n| `.claude\u002Frules\u002F*.md` | «what must always \u002F never happen» | `\u002Fclose-day` after 6+ months stable |\n\nSee [ARCHITECTURE.md](ARCHITECTURE.md) for full details and [CLAUDE.md](CLAUDE.md) for the agent's session workflow.\n\n## Built from production use\n\nIteration on 700+ real sessions across 7+ projects. Every component earns its place; `experiences\u002F` and background-detection scripts didn't survive review.\n",{"name":5,"tags":24,"author":33,"license":15,"version":34,"repository":35,"description":7},[25,26,27,28,29,30,31,32],"memory","context-management","productivity","claude-code","agent-memory","knowledge-base","reference-skills","multi-project","awrshift","4.0.0","https:\u002F\u002Fgithub.com\u002Fawrshift\u002Fclaude-memory-kit","main","ffa016d3c9a8d32821f71f6d9d916c30e04fcb67","讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs",0,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai","https:\u002F\u002Fgithub.com\u002Fleemiracle","i have some experience that make me better, so i want more. follow and star me would be a good choice.","2026-11-12 17:16:40",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add leemiracle\u002Fwork4ai --skill claude-memory-kit",{"tool":50,"command":51},"bunx","bunx skills add leemiracle\u002Fwork4ai --skill claude-memory-kit",{"tool":53,"command":54},"pnpm","pnpm dlx skills add leemiracle\u002Fwork4ai --skill claude-memory-kit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002FSKILL.md",true,[58,64,68,72,76,80,84,88,92,96,100,104,108,112],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"_filelist.txt","REFERENCE","参考文档",356,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002F_filelist.txt",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},".kit\u002FARCHITECTURE.md",16081,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002F.kit\u002FARCHITECTURE.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},".kit\u002FCHANGELOG.md",23920,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002F.kit\u002FCHANGELOG.md",{"path":73,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":74,"sourceHtmlUrl":75},".kit\u002FCONTRIBUTING.md",2935,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002F.kit\u002FCONTRIBUTING.md",{"path":77,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":78,"sourceHtmlUrl":79},"CLAUDE.md",10401,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002FCLAUDE.md",{"path":81,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":82,"sourceHtmlUrl":83},"context\u002Fnext-session-prompt.md",2248,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002Fcontext\u002Fnext-session-prompt.md",{"path":85,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":86,"sourceHtmlUrl":87},"daily\u002FREADME.md",1073,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002Fdaily\u002FREADME.md",{"path":89,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":90,"sourceHtmlUrl":91},"daily\u002FTEMPLATE.md",1717,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002Fdaily\u002FTEMPLATE.md",{"path":93,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":94,"sourceHtmlUrl":95},"experiments\u002FEXPERIMENT-TEMPLATE.md",1654,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002Fexperiments\u002FEXPERIMENT-TEMPLATE.md",{"path":97,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":98,"sourceHtmlUrl":99},"experiments\u002FREADME.md",2795,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002Fexperiments\u002FREADME.md",{"path":101,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":102,"sourceHtmlUrl":103},"knowledge\u002Findex.md",2252,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002Fknowledge\u002Findex.md",{"path":105,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":106,"sourceHtmlUrl":107},"knowledge\u002Flog.md",158,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002Fknowledge\u002Flog.md",{"path":109,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":110,"sourceHtmlUrl":111},"projects\u002Fmy-first-project\u002FBACKLOG.md",3360,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002Fprojects\u002Fmy-first-project\u002FBACKLOG.md",{"path":113,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":114,"sourceHtmlUrl":115},"README.md",7714,"https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F01-学\u002F讲透Agent\u002F讲透AgentEco\u002Fawrshift_claude-memory-kit\u002Frepo-docs\u002FREADME.md",[117,125,132,139,146,153],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M7A57J4E78QJZS8MA72P82DV","agentic-ecology-ui","Guidelines and templates for creating a generic web UI to visualize, rank, filter, and annotate vector databases. The UI has a hierarchical structure covering database selection, label selection\u002Fdefinition, ranking\u002Ffiltering configuration, and row visualization\u002Fannotation. Use when building, serving, or adapting an interactive web UI for Hoplite vector databases.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F05-侦\u002F讲透google-deepmind\u002Fagentic_ecology\u002Frepo-docs\u002Fskills\u002Fagentic-ecology-ui\u002FSKILL.md",[],[],{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":19},"01M7A57C4RGS1A7VM6CNPNQDBH","agentic-ecology-init","Initializes a local uv-managed project directory for agentic ecology workloads. Sets up Python dependencies using reference pyproject.toml and uv.lock, configures workspace rules, and ensures Agentic Ecology skills are discoverable. Use when initializing a new project workspace or bootstrapping a clean environment.","https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F05-侦\u002F讲透google-deepmind\u002Fagentic_ecology\u002Frepo-docs\u002Fskills\u002Fagentic-ecology-init\u002FSKILL.md",[],[],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":19},"01M7A576Q1GYF5GAQCWGPPDQWZ","agentic-ecology-camera-traps","Provides capabilities to run SpeciesNet detector and classifier on camera trap images, extract crop-level feature embeddings, and populate a Hoplite vector database for downstream search and agile modeling. Use when ingesting camera trap images, classifying wildlife photos, or indexing camera trap data.","https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F05-侦\u002F讲透google-deepmind\u002Fagentic_ecology\u002Frepo-docs\u002Fskills\u002Fagentic-ecology-camera-traps\u002FSKILL.md",[],[],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":19},"01M7A5708M54MMTKXQARDCJQMW","agentic-ecology-bioacoustics","Provides bioacoustic analysis capabilities for ecologists and researchers using the perch-hoplite Python package. A typical use case is to use agile modeling to bootstrap the creation and deployment of a bespoke detector for targeted species on an existing collection of passive acoustic monitoring recordings. Use when processing and annotating audio recordings for bioacoustic applications.","https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F05-侦\u002F讲透google-deepmind\u002Fagentic_ecology\u002Frepo-docs\u002Fskills\u002Fagentic-ecology-bioacoustics\u002FSKILL.md",[],[],{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":19},"01M7A53GYCZY3AT9C2FR44TC35","sample-skill","Sample skill used by agent-env integration tests. Exercises SKILL.md parsing plus supporting scripts and references.","https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F05-侦\u002F讲透browser-use\u002Fagentenv-framework\u002Frepo-docs\u002Ftst\u002Fdata\u002Fskills\u002Fsample_skill\u002FSKILL.md",[],[],{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":19},"01M7A4KD50DHSNH1SCNKP1J6S1","simready-foundation-validate-foundation-change","Use for auditing SimReady requirement, validator, feature, profile, adapter, test, and skill consistency.","https:\u002F\u002Fgithub.com\u002Fleemiracle\u002Fwork4ai\u002Fblob\u002Fmain\u002F讲透宇宙\u002F05-侦\u002F讲透NVIDIA\u002Fsimready-foundation\u002Frepo-docs\u002F.codex\u002Fskills\u002Fsimready-foundation-validate-foundation-change\u002FSKILL.md",[],[]]