[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77V35KHA8M5MCD4REMNP8EH":3,"skill-same:01M77V35KHA8M5MCD4REMNP8EH":50},{"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":34,"updatedAt":35,"install":36,"resources":49},"01M77V35KHA8M5MCD4REMNP8EH","skill-library-and-agent",null,"Use when working with the skill library subsystem — skills\u002F data layout, the router, the skilllib CLI (sync\u002Fbuild\u002Froute\u002Fstats\u002Fexport\u002Fimport\u002Follama\u002Fagent\u002Fchat), the local Ollama agent, or adding\u002Fexporting skills.","BangerSoul\u002Fwhatsapp-mtd-sales-automation","BangerSoul","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F107968141?v=4","01M77SHZ543JA3G93SJKCCS416","Azmathulla Shaik","01M77SHZ6BBGSHYRHBMY9ATQSG",0,"MIT","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-library-and-agent\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-library-and-agent\ndescription: Use when working with the skill library subsystem — skills\u002F data layout, the router, the skilllib CLI (sync\u002Fbuild\u002Froute\u002Fstats\u002Fexport\u002Fimport\u002Follama\u002Fagent\u002Fchat), the local Ollama agent, or adding\u002Fexporting skills.\nversion: 1.0.0\nsources:\n  - vercel-labs\u002Fskills (find-skills, update flow)\n  - anthropics\u002Fskills\nlicense: MIT\n---\n\n# Skill Library & Local Agent\n\n## Layout\n\n```\nskills\u002F            sources\u002F (gitignored clones) · normalized\u002F · index\u002F · manifests\u002F\nrouter\u002F            stdlib-only tokenizer + scorer + route()\nscripts\u002F           skilllib CLI: sync · build · route · stats · export · import · ollama · agent · chat · modelfile\nagent\u002F             ollama_client (streaming REST) · solver (route→inject→generate) · modelfile\nconfig\u002F            library.toml — sources, paths, router weights, [agent] knobs (DATA-ONLY: no __init__.py, must never shadow config.py)\nprompts\u002F           route.md · skill-use.md · agent-system.md\n```\n\n## The pipeline\n\n`skilllib sync` shallow-clones the `enabled = true` repos in `config\u002Flibrary.toml` → `build` normalizes each SKILL.md (frontmatter → metadata, sha256 hash, names sanitized to `[a-z0-9-]`, duplicates disambiguated), writes `skills\u002Fnormalized\u002F`, then builds `skills\u002Findex\u002Findex.json` and the manifests. **Curated project skills** (`.agents\u002Fskills\u002F\u003Cname>\u002FSKILL.md`) are indexed too, with `source: \"curated\u002Flocal\"` — `build` must be re-run after adding one.\n\n## Router & agent flow\n\n`route(query, index, top_k)` scores name\u002Fdescription\u002Fkeywords\u002Fbigrams; hits feed `agent.solver.solve()` which excerpts each skill body (curated ones read from `.agents\u002Fskills\u002F`), composes them with the system personality (`prompts\u002Fagent-system.md`) and the task, then calls Ollama — streaming, `max_tokens`-capped. `skilllib chat` is a REPL that re-routes every turn and keeps the last `max_history_turns` exchanges.\n\n## Export \u002F import\n\n`skilllib export` → `export\u002Fskills-bundle.json` (self-contained: curated + library + index + manifests) and `export\u002Fskills-prompt.md` (for handing to another model). `skilllib import bundle.json` restores everything offline with zero pip installs (PyYAML is lazily imported); `build` afterwards regenerates identical index\u002Fmanifests from the restored tree when no source clones exist. See `skills-migration.md`.\n\n## Common mistakes\n\n- Editing `config\u002F` — it's data-only by design; adding `__init__.py` would shadow the app's `config.py`.\n- Adding a curated skill without re-running `build` — it won't appear in the index or route.\n- Regenerating export artifacts after changes — the bundle is a snapshot; re-export to keep it current.\n- Testing the agent with a real model when a stub suffices — `tests\u002Ftest_agent.py` runs a stub Ollama server; live calls take minutes on CPU.\n","# Skill Library & Local Agent\n\n## Layout\n\n```\nskills\u002F            sources\u002F (gitignored clones) · normalized\u002F · index\u002F · manifests\u002F\nrouter\u002F            stdlib-only tokenizer + scorer + route()\nscripts\u002F           skilllib CLI: sync · build · route · stats · export · import · ollama · agent · chat · modelfile\nagent\u002F             ollama_client (streaming REST) · solver (route→inject→generate) · modelfile\nconfig\u002F            library.toml — sources, paths, router weights, [agent] knobs (DATA-ONLY: no __init__.py, must never shadow config.py)\nprompts\u002F           route.md · skill-use.md · agent-system.md\n```\n\n## The pipeline\n\n`skilllib sync` shallow-clones the `enabled = true` repos in `config\u002Flibrary.toml` → `build` normalizes each SKILL.md (frontmatter → metadata, sha256 hash, names sanitized to `[a-z0-9-]`, duplicates disambiguated), writes `skills\u002Fnormalized\u002F`, then builds `skills\u002Findex\u002Findex.json` and the manifests. **Curated project skills** (`.agents\u002Fskills\u002F\u003Cname>\u002FSKILL.md`) are indexed too, with `source: \"curated\u002Flocal\"` — `build` must be re-run after adding one.\n\n## Router & agent flow\n\n`route(query, index, top_k)` scores name\u002Fdescription\u002Fkeywords\u002Fbigrams; hits feed `agent.solver.solve()` which excerpts each skill body (curated ones read from `.agents\u002Fskills\u002F`), composes them with the system personality (`prompts\u002Fagent-system.md`) and the task, then calls Ollama — streaming, `max_tokens`-capped. `skilllib chat` is a REPL that re-routes every turn and keeps the last `max_history_turns` exchanges.\n\n## Export \u002F import\n\n`skilllib export` → `export\u002Fskills-bundle.json` (self-contained: curated + library + index + manifests) and `export\u002Fskills-prompt.md` (for handing to another model). `skilllib import bundle.json` restores everything offline with zero pip installs (PyYAML is lazily imported); `build` afterwards regenerates identical index\u002Fmanifests from the restored tree when no source clones exist. See `skills-migration.md`.\n\n## Common mistakes\n\n- Editing `config\u002F` — it's data-only by design; adding `__init__.py` would shadow the app's `config.py`.\n- Adding a curated skill without re-running `build` — it won't appear in the index or route.\n- Regenerating export artifacts after changes — the bundle is a snapshot; re-export to keep it current.\n- Testing the agent with a real model when a stub suffices — `tests\u002Ftest_agent.py` runs a stub Ollama server; live calls take minutes on CPU.\n",{"name":5,"license":15,"sources":24,"version":27,"description":7},[25,26],"vercel-labs\u002Fskills (find-skills, update flow)","anthropics\u002Fskills","1.0.0","main","182274ecfa933218655fd53561d9ecba872da942",".agents\u002Fskills\u002Fskill-library-and-agent","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation","https:\u002F\u002Fgithub.com\u002FBangerSoul","https:\u002F\u002Ft.me\u002FBangerSoul","Linux\u002FDebian Systems • Remote IT Support • Tech Content Creator @ Tech Made Easy India • B2B Sales Specialist 🚀","2026-08-11 01:21:10",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add BangerSoul\u002Fwhatsapp-mtd-sales-automation --skill skill-library-and-agent",{"tool":42,"command":43},"bunx","bunx skills add BangerSoul\u002Fwhatsapp-mtd-sales-automation --skill skill-library-and-agent",{"tool":45,"command":46},"pnpm","pnpm dlx skills add BangerSoul\u002Fwhatsapp-mtd-sales-automation --skill skill-library-and-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-library-and-agent\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M77VMH7JZB1H3Z4KHH0KQQH6","vercel-react-view-transitions","Guide for implementing smooth, native-feeling animations using React's View Transition API (`\u003CViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter\u002Fexit of components, animate list reorder, implement directional (forward\u002Fback) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002Fskills\u002Fsources\u002Fvercel-labs\u002Fagent-skills\u002Fskills\u002Freact-view-transitions\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M77VMCSEYYNSQF8GQXYPCK8N","vercel-react-native-skills","React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002Fskills\u002Fsources\u002Fvercel-labs\u002Fagent-skills\u002Fskills\u002Freact-native-skills\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M77VM551DK61K4Q8MXMFPVDN","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002Fskills\u002Fsources\u002Fvercel-labs\u002Fagent-skills\u002Fskills\u002Freact-best-practices\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M77VKVKNN092NCJ1VJW99Y7A","vercel-composition-patterns","React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002Fskills\u002Fsources\u002Fvercel-labs\u002Fagent-skills\u002Fskills\u002Fcomposition-patterns\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M77VKCCT492PXAQV6MB9HDNQ","supabase-postgres-best-practices","Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector\u002Fsemantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002Fskills\u002Fsources\u002Fsupabase\u002Fagent-skills\u002Fskills\u002Fsupabase-postgres-best-practices\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M77VK8HNK8XKJPMTWYWVBREC","skill-installer","Install Codex skills into $CODEX_HOME\u002Fskills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).","Apache-2.0","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002Fskills\u002Fsources\u002Fopenai\u002Fskills\u002Fskills\u002F.system\u002Fskill-installer\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FBangerSoul\u002Fwhatsapp-mtd-sales-automation\u002Fblob\u002Fmain\u002Fskills\u002Fsources\u002Fopenai\u002Fskills\u002Fskills\u002F.system\u002Fskill-installer\u002FSKILL.md",[],[]]